JP7648165B2 - Cattle evaluation device and cattle evaluation method - Google Patents

Description

The present invention relates to a cow evaluation device and a cow evaluation method.

To evaluate the energy balance in cattle feeding management, the state of body fat (fleshyness) of cattle is evaluated. One index showing the state of body fat is the body condition score. Normally, the body condition score is judged by veterinarians or dairy experts, but because it is judged by humans, the judgment criteria are vague and there is variation in the judgment. On the other hand, there are known methods for evaluating a score indicating the body condition based on a three-dimensional image of an animal (e.g., Patent Document 1) and a method for evaluating a score indicating the body condition based on a two-dimensional image of an animal (e.g., Patent Document 2).

Special Publication No. 2012-510278 European Patent No. 2027770

The evaluation method described in Patent Document 1 uses three-dimensional images of the animals to calculate a score indicating the physical condition of the animals, so it is necessary to take images at a specific location where large-scale equipment is installed, making it difficult to apply to a variety of breeding sites. The evaluation method described in Patent Document 2 uses two-dimensional images of the animals, but because it uses two-dimensional images taken from above, it is necessary to take images at a specific location where equipment capable of taking images from above is installed, and like Patent Document 1, it is difficult to apply to a variety of breeding sites.

The present invention has been made in consideration of the above problems, and aims to provide a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites.

The cattle evaluation device of the present invention comprises an image acquisition unit that acquires a two-dimensional image of a standing cattle taken from approximately directly behind or approximately in front, an extraction unit that extracts the contour line of the cattle from the captured image, a determination unit that determines a first point on a first curved portion extending from an approximately central point on the contour line of one of two peaks present on both the left and right sides of the upper part of the contour line to the other peak side, and a second point on a second curved portion extending on the opposite side to the first curved portion, and a determination unit that connects the first point and the second point. a calculation unit that calculates at least one of the length of a first line segment that connects the first line segment to a third point where a straight line that passes through the approximate midpoint of the first line segment and is approximately perpendicular to the first line segment intersects with one of the peaks, the length of a second line segment that connects the approximate midpoint of the first line segment to a third point where the straight line that passes through the approximate midpoint of the first line segment and is approximately perpendicular to the first line segment intersects with one of the peaks, the ratio of the length of the first line segment to the length of the second line segment, and the angle formed by a third line segment that connects the first point and the third point and a fourth line segment that connects the second point and the third point, and an evaluation unit that evaluates the beefiness of the cow from the values calculated by the calculation unit.

The present invention provides a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites.

FIG. 1 is a block diagram showing the configuration of a cattle evaluation device according to the first embodiment. FIG. 2 is a block diagram showing the functional configuration of the control unit in the first embodiment. FIG. 3 is a diagram showing an example of an image acquired by the image acquisition unit. FIG. 4 is a diagram for explaining the process executed by the extraction unit. FIG. 5 is a diagram for explaining the process executed by the determination unit. 6A and 6B are diagrams for explaining the process executed by the calculation unit in the first embodiment. 7(a) to 7(c) are images of cows with different body sizes. 8(a) to 8(c) are diagrams showing the relationship between the meatiness of a cow and the angle ω1 calculated by the calculation unit. FIG. 9 shows the results of an experiment investigating the correlation between the body condition score and the angles ω1, ω2, and the average values of the angles ω1 and ω2 calculated by the calculation unit. FIG. 10 is a block diagram showing the hardware configuration of the cow evaluation device according to the embodiment. FIG. 11 is a flowchart showing an example of a method for evaluating beef meatiness in the first embodiment. 12(a) to 12(c) are diagrams showing other determination methods by the determination unit. 13A and 13B are diagrams for explaining the process executed by the calculation unit in the second embodiment. 14(a) to 14(c) are diagrams showing the relationship between the fleshiness of a cow and the lengths X1a and X2a calculated by the calculation unit. FIG. 15 shows the results of an experiment investigating the correlation between the body condition score and the lengths X1a, X1b, and the average values of the lengths X1a and X1b calculated by the calculation unit. FIG. 16 shows the results of an experiment investigating the correlation between the body condition score and the length X2a, the length X2b, and the average value of the length X2a and the length X2b calculated by the calculation unit. FIG. 17 shows the results of an experiment investigating the correlation between the body condition score and the length ratio (X1a/X2a) of length X1 to length X2a, the length ratio (X1b/X2b) of length X1b to length X2b, and the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b), all calculated by the calculation unit. FIG. 18(a) is an image of a cow in an upright position captured from substantially directly behind, and FIG. 18(b) is an image of the cow in FIG. 18(a) captured from substantially the front. FIGS. 19(a) and 19(b) are images in which the contour lines of the cow are extracted from the captured images of FIGS. 18(a) and 18(b).

First Embodiment
A cow evaluation device 100 according to a first embodiment will be described below with reference to Figs. 1 to 12. Fig. 1 shows in a block diagram the configuration of the cow evaluation device 100 according to the first embodiment. Fig. 2 shows in a block diagram the functional configuration of a control unit 22. In this first embodiment, the evaluation device 100 is a portable information device carried and used by an operator. Examples of portable information devices include smartphones, tablet computers, PDAs (Personal Digital Assistants), and smart glasses. The evaluation device 100 has, for example, a telephone function, an email function, a communication function for connecting to the Internet, etc., and a data processing function for executing a program.

As shown in FIG. 1, the evaluation device 100 includes a display unit 12, an operation unit 14, a communication unit 16, an imaging unit 18, a memory unit 20, and a control unit 22.

The display unit 12 is a display device that displays images, various information, and images for operation input such as touch operation buttons.

The operation unit 14 is a device such as a touch panel or a switch. The touch panel accepts information input in response to a worker's touch and transmits the accepted information to the control unit 22. The touch panel is, for example, incorporated in the display unit 12. Thus, the touch panel accepts various information inputs in response to the worker touching the surface of the display unit 12. The switch is an operating member that accepts operations on the evaluation device 100 from the worker and transmits the accepted information to the control unit 22.

The communication unit 16 is a communication interface that performs short-range wireless communication (e.g., NFC (Near Field Communication)) with other devices, and wireless communication (e.g., communication using a mobile phone line or a wireless LAN (Local Area Network)) with other devices connected to the network.

The imaging unit 18 is a device that captures images such as still images and videos. The imaging unit 18 captures images in response to an operator carrying the evaluation device 100 operating the operation unit 14. When evaluating the fleshiness of a cow, the operator uses the imaging unit 18 to capture an image of the cow in a standing position from approximately directly behind. Capturing an image from approximately directly behind means capturing an image in a range that captures the outline of the cow's left and right hip angles. Therefore, the operator captures an image from a position several meters (e.g., 1 m to 2 m) behind the cow so that the outline of the cow's left and right hip angles is captured.

The memory unit 20 stores various information such as captured images of the cow, extracted images of the cow's contours, and evaluation results of the cow's body fatness.

The control unit 22 is a processing unit that controls each part of the cow evaluation device 100. As shown in FIG. 2, the control unit 22 has an image acquisition unit 30, an extraction unit 32, a determination unit 38, a calculation unit 34, and an evaluation unit 36.

Figure 3 shows an example of an image acquired by the image acquisition unit 30. As shown in Figure 3, the image acquisition unit 30 acquires an image 50, for example, of a cow in an upright position, captured from approximately directly behind. The image 50 of the cow to be acquired may be an image captured by the imaging unit 18, or an image captured by another device and received by the communication unit 16. The image 50 of the cow to be acquired may be an image selected by the operator using the operation unit 14 from those stored in the memory unit 20. The image acquisition unit 30 may display the acquired image 50 of the cow on the display unit 12. This allows the operator to visually recognize on the display unit 12 the cow to be evaluated for its fleshiness.

Figure 4 is a diagram for explaining the processing executed by the extraction unit 32. As shown in Figure 4, the extraction unit 32 extracts a contour line 60 that traces the outline of the cow from the captured image 50 of the cow acquired by the image acquisition unit 30. A commonly known image processing technique can be used to extract the contour line 60. The extraction unit 32 may display an extracted image 51 that shows only the extracted contour line 60 of the cow on the display unit 12. This allows the operator to visually recognize on the display unit 12 the outline of the cow whose fleshiness is to be evaluated. The outer shape of the extracted image 51 is the same as that of the captured image 50, and the position of the cow relative to the image frame is the same in the extracted image 51 and the captured image 50.

There are peaks 61a and 61b on both the left and right sides of the upper part of the contour line 60. The peaks 61a and 61b correspond to the cow's hips. The peak 61a has a vertex 62a at the approximate center of the peak 61a on the contour line 60, a first curved portion 63a extending from the vertex 62a to the upper center side of the contour line 60 (the cow's spine side), and a second curved portion 64a extending from the vertex 62a to the lower side of the side of the contour line 60 (the cow's belly side). Similarly, the peak 61b has a vertex 62b at the approximate center of the peak 61b on the contour line 60, a first curved portion 63b extending from the vertex 62b to the upper center side of the contour line 60 (the cow's spine side), and a second curved portion 64b extending from the vertex 62b to the lower side of the contour line 60 (the cow's belly side). The first curved portions 63a, 63b can be considered to be curved portions that extend from approximately the center point (vertices 62a, 62b) on the contour line 60 of the peaks 61a, 61b to the other peak side (the cow's spine side). The second curved portions 64a, 64b can be considered to be curved portions that extend from approximately the center point (vertices 62a, 62b) on the contour line 60 of the peaks 61a, 61b to the opposite side to the first curved portions 63a, 63b.

The apex 62a of the mountain 61a and the apex 62b of the mountain 61b can be identified by the following method. For example, an inclined straight line 55 inclined from the top to the bottom left in the extracted image 51 can be moved from the top left end point 52 of the extracted image 51 toward the contour line 60, and the point where the inclined straight line 55 first touches the contour line 60 can be identified as the apex 62a of the mountain 61a located on the left side. Similarly, an inclined straight line 56 inclined from the top to the bottom right in the extracted image 51 can be moved from the top right end point 54 of the extracted image 51 toward the contour line 60, and the point where the inclined straight line 56 first touches the contour line 60 can be identified as the apex 62b of the mountain 61b located on the right side. The inclined straight lines 55 and 56 are preferably inclined at 30° to 60° from the horizontal line in the extracted image 51, more preferably at 40° to 50°, and even more preferably at 45°.

The apex 62a of the mountain portion 61a and the apex 62b of the mountain portion 61b may be identified by other methods, not limited to the above-mentioned method. For example, a first point of contact may be identified by approaching an inclined straight line 55a inclined from the top to the bottom left in the extracted image 51 from the upper left end point 52 toward the contour line 60, and a second point of contact may be identified by approaching an inclined straight line 55b inclined at a second predetermined angle from the upper left end point 52 toward the contour line 60, and a point located approximately in the center between the first point and the second point on the contour line 60 may be identified as the apex 62a of the mountain portion 61a. Similarly, a third point where an inclined straight line 56a inclined from the top to the bottom right in the extracted image 51 first touches the contour line 60 from the upper right end point 54 may be approached, and a fourth point where an inclined straight line 56b inclined at a fourth predetermined angle may be approached from the upper right end point 54 to the contour line 60 to identify the fourth point where the first touches the contour line 60. A point on the contour line 60 located approximately in the middle between the third point and the fourth point may be identified as the apex 62b of the mountain portion 61b. The first and third predetermined angles are preferably 15° to 30° from the horizontal line in the extracted image 51, and the second and fourth predetermined angles are preferably 60° to 75° from the horizontal line in the extracted image 51.

In addition, for example, the extracted image 51 may be converted into an X-Y coordinate system, and the vertices 62a, 62b of the two peaks 61a, 61b may be identified from the X and Y coordinates of each pixel of the extracted image 51. For example, the point on the contour 60 that is the shortest distance from the upper left corner 52 of the extracted image 51 may be set as the vertex 62a of the peak 61a, and the point on the contour 60 that is the shortest distance from the upper right corner 54 of the extracted image 51 may be set as the vertex 62b of the peak 61b.

Alternatively, the apex of either the peak 61a or the peak 61b may be specified by any of the above methods, and the point where the horizontal line in the extracted image 51 passing through the specified apex intersects with the contour line 60 of the other peak may be specified as the apex of the other peak. Note that the apex 62a of the peak 61a and the apex 62b of the peak 61b may be specified by a method other than the above methods. Note that the range of the peaks 61a and 61b can be specified by various methods. For example, the range of the peak 61a can be the range of the contour line 60 contained in a circle of a predetermined radius centered on the apex 62a of the peak 61a. The predetermined radius can be, for example, a value obtained by multiplying the distance between the apex 62a of the peak 61a and the uppermost point 91 located at the uppermost side of the contour line 60 by a predetermined value (for example, 0.5), but may be a value obtained by other methods. Also, the range of the peak 61a may be a range of a predetermined length on both sides from the apex 62a of the peak 61a. The predetermined length may be, for example, the length of the above-mentioned predetermined radius, or may be the length of the entire contour line 60 multiplied by a predetermined value. The same applies to the peak portion 61b. The range of the peak portions 61a and 61b may also be determined by machine learning or the like.

Figure 5 is a diagram for explaining the process executed by the determination unit 38. Figure 5 is an enlarged view of the upper part of the contour line 60, and is illustrated diagrammatically for clarity (the same applies to the following similar figures). As shown in Figure 5, the determination unit 38 determines a point 403a on the first curved portion 63a and a point 404a on the second curved portion 64a of one of the peaks 61a, 61b present on both the left and right sides of the upper part of the contour line 60. In this first embodiment, the determination unit 38 determines the point on the first curved portion 63a to be the point 403a by approaching the horizontal line 420 extending in the left-right direction (horizontal direction) in the extracted image 51 (captured image 50) from above the peak 61a toward the peak 61a. The determination unit 38 also determines the point on the second curved portion 64a that first touches the peak 61a when the vertical line 422a, which extends in the up-down direction (vertical direction) in the extracted image 51 (captured image 50), approaches the peak 61a from the left side of the peak 61a toward the peak 61a as the point 404a. In this way, in the first embodiment, the determination unit 38 determines the point on the first curved portion 63a that protrudes most upward as the point 403a, and determines the point on the second curved portion 64a that protrudes most to the side as the point 404a.

Instead of or in addition to determining the point 403a on the first curved portion 63a of the peak 61a and the point 404a on the second curved portion 64a, the determination unit 38 may determine the point 403b on the first curved portion 63b of the peak 61b and the point 404b on the second curved portion 64b. The determination unit 38 can determine the point at which the horizontal line 420 first touches the peak 61b when it approaches the peak 61b from above the peak 61b as the point 403b on the first curved portion 63b, and determine the point at which the vertical line 422b extending in the up-down direction (vertical direction) in the extracted image 51 first touches the peak 61b when it approaches the peak 61b from the right side of the peak 61b as the point 404b on the second curved portion 64b.

6(a) and 6(b) are diagrams for explaining the process executed by the calculation unit 34 in the first embodiment. As shown in FIG. 6(a), the calculation unit 34 identifies a point 406a at which a straight line 424a that passes through a midpoint 405a of a line segment 410a connecting points 403a and 404a and is perpendicular to the line segment 410a intersects with the peak 61a. The calculation unit 34 then calculates an angle ω1 between a line segment 412a connecting points 403a and 406a and a line segment 414a connecting points 404a and 406a. The angle ω1 calculated by the calculation unit 34 is one of the index values that indicates the degree of inclination of the peak 61a.

The evaluation unit 36 evaluates the fleshiness of the cow captured in the captured image 50 from the angle ω1 calculated by the calculation unit 34. For example, the body condition score is evaluated as the fleshiness.

As shown in FIG. 6B, when the determination unit 38 determines a point 403b on the first curved portion 63b and a point 404b on the second curved portion 64b of the mountain portion 61b, the calculation unit 34 identifies a point 406b where a straight line 424b that passes through a midpoint 405b of a line segment 410b connecting the points 403b and 404b and is perpendicular to the line segment 410b intersects with the mountain portion 61b. The calculation unit 34 then calculates an angle ω2 between a line segment 412b connecting the points 403b and 406b and a line segment 414b connecting the points 404b and 406b. The angle ω2 calculated by the calculation unit 34 is one of the index values that indicates the degree of inclination of the mountain portion 61b. In this case, the evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the angle ω2 calculated by the calculation unit 34.

In addition, when the determination unit 38 determines point 403b on the first curved portion 63a of the peak 61a and point 404a on the second curved portion 64a of the peak 61a, and also determines point 403b on the first curved portion 63b and point 404b on the second curved portion 64b of the peak 61b, the calculation unit 34 may calculate both angles ω1 and ω2 and calculate the average value of angles ω1 and ω2. In this case, the evaluation unit 36 may evaluate the beefiness of the cow captured in the captured image 50 from the average value of angles ω1 and ω2 calculated by the calculation unit 34.

Here, the relationship between the angles ω1 and ω2 calculated by the calculation unit 34 and the body condition score will be described. The body condition score is an index that indicates the state of body fat deposition, and may be given a score of, for example, 1.00 to 5.00, with a higher value indicating better fleshiness.

Figures 7(a) to 7(c) are images 50 of cows with different levels of fleshiness. Figure 7(a) is an image 50 of a cow with poor fleshiness, Figure 7(b) is an image 50 of a cow that is more fleshy than the cow in Figure 7(a), and Figure 7(c) is an image 50 of a cow that is even more fleshy. The cow in Figure 7(a) was given a body condition score of 2.25 by an expert. The cow in Figure 7(b) was given a score of 3.00, and the cow in Figure 7(c) was given a score of 4.00. As shown in Figures 7(a) to 7(c), it can be seen that the fleshiness around the hip angle changes due to differences in fleshiness (i.e., different body condition scores), and the shape of the hip angle changes when the cow is viewed from approximately directly behind in a standing position.

8(a) to 8(c) are diagrams showing the relationship between the beefiness of a cow and the angle ω1 calculated by the calculation unit 34. FIG. 8(a) shows the contour line 60 of a thin cow, FIG. 8(b) shows the contour line 60 of a cow that is fatter (fattier) than the cow in FIG. 8(a), and FIG. 8(c) shows the contour line 60 of a cow that is fatter (fattier) than the cow in FIG. 8(b). As shown in FIG. 8(a) to FIG. 8(c), the more beefy the cow is, the more rounded the peak portion 61a, which is the part corresponding to the waist angle. Therefore, it was found that the more beefy the cow is, the smaller the value of the angle ω1 is. Although not shown in the figure, the same applies to the relationship between the beefiness of a cow and the angle ω2 calculated by the calculation unit 34. From these facts, it is considered that the beefiness of a cow can be evaluated by calculating the angle ω1, the angle ω2, or the average value of the angles ω1 and ω2, and using these.

[experiment]
An experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the angles ω1, ω2, and the average value of the angles ω1 and ω2 calculated by the calculation unit 34. The experiment was conducted on dairy cows (Holstein breed).

FIG. 9 shows the results of an experiment investigating the correlation between the body condition score and the angles ω1, ω2, and the average value of the angles ω1 and ω2 calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 9 is the body condition score evaluated by an expert, and the vertical axis is the angle. A plurality of black circles in FIG. 9 show the results of each dairy cow when the angle ω1 is used, and the dotted straight line shows the approximation line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the angle ω2 is used, and the dashed straight line shows the approximation line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average value of the angles ω1 and ω2 is used, and the dashed straight line shows the approximation line (regression line) at that time. As shown in FIG. 9, the body condition score increases as the angle decreases, regardless of whether the angle ω1, the angle ω2, or the average value of the angles ω1 and ω2 is used. The approximate dotted line using angle ω1 was calculated as y = -7.4724x + 162.85, and the coefficient of determination ^R2 was 0.6478. The approximate dashed line using angle ω2 was calculated as y = -10.594x + 171.76, and the coefficient of determination ^R2 was 0.7048. The approximate dashed line using the average values of angle ω1 and angle ω2 was calculated as y = -9.0331x + 167.31, and the coefficient of determination ^R2 was 0.7397. This confirmed that there is a strong correlation between the body condition score and the angles ω1, ω2, and the average values of angle ω1 and angle ω2 calculated by the calculation unit 34.

In this way, since there is a strong correlation between the body condition score and the angles ω1, ω2, and the average value of angles ω1 and ω2 calculated by the calculation unit 34, it can be seen that the evaluation unit 36 can accurately evaluate the beefiness of the cow by evaluating the angles ω1, ω2, or the average value of angles ω1 and ω2. The evaluation unit 36 evaluates the body condition score using, for example, score information stored in the memory unit 20 that associates angles with the body condition score.

Table 1 shows an example of score information stored in the storage unit 20. As shown in Table 1, in the score information, angles and body condition scores are associated with each other. For example, when the angle is less than a°, the body condition score is 5.00, and when the angle is equal to or greater than a° and less than b°, the body condition score is 4.50. In Table 1, the body condition score is in increments of 0.5, but other increments are also acceptable. For example, increments of 0.25 are acceptable, or increments of 0.25 are acceptable between 2.00 and 4.00, and increments of 0.50 are acceptable otherwise. As the score information as in Table 1, separate score information may be created for the angle ω1, the angle ω2, and the average value of the angle ω1 and the angle ω2, or score information may be created and shared for either the angle ω1, the angle ω2, or the average value of the angle ω1 and the angle ω2. When score information is shared, by sharing score information created from the average value of angles ω1 and ω2, the body condition score can be evaluated with high accuracy even when evaluating the body condition score from angles ω1 and ω2.

The score information stored in the memory unit 20 may be other than the score information shown in Table 1, as long as it is information that associates the angle with the body condition score. For example, a linear function (y = ax + b) such as the approximate straight line shown in Figure 9 may be stored in the memory unit 20 as the score information. In this case, the body condition score may be evaluated by performing fractional processing such as rounding up, rounding up, or rounding down on the value of x obtained by substituting the angle for y.

Figure 10 is a block diagram showing the hardware configuration of the cow evaluation device 100 according to the first embodiment. As shown in Figure 10, the cow evaluation device 100 has a storage device 70, a memory 71, a processor 72, a communication interface 73, an input device 74, a display device 75, and an imaging device 76. These components are interconnected by a bus 77.

The storage device 70 is a non-volatile semiconductor memory such as a flash memory, and stores the cow evaluation program 78.

Memory 71 is hardware that temporarily stores data, such as a dynamic random access memory (DRAM). The memory unit 20 in FIG. 1 is realized by the storage device 70 and memory 71.

The processor 72 is hardware such as a CPU (Central Processing Unit) that controls each part of the cow evaluation device 100. The processor 72 executes the cow evaluation program 78 in cooperation with the memory 71. In this way, the memory 71 and the processor 72 cooperate to execute the cow evaluation program 78, thereby realizing each function of the control unit 22 in FIG. 2.

The communication interface 73 is hardware that enables the cow evaluation device 100 to communicate with other devices by short-range wireless communication or wireless communication via a network. The communication interface 73 realizes the communication unit 16 in FIG. 1.

The input device 74 is an input device such as a touch panel or a switch that allows the operator to operate the cattle evaluation device 100. The input device 74 realizes the operation unit 14 in FIG. 1.

The display device 75 is hardware for implementing the display unit 12 in FIG. 1, and is a display device such as an LCD display for displaying the captured image 50 of the cow, the extracted image 51, the evaluation results of the beefiness of the cow, etc.

The imaging device 76 is hardware for implementing the imaging unit 18 in FIG. 1, and includes a lens, an imaging element, etc.

Next, an example of a method for evaluating beef meatiness in the first embodiment will be described with reference to the flowchart in FIG. 11. The process in FIG. 11 is executed by the control unit 22 of the evaluation device 100. It is assumed that the memory unit 20 stores score information such as that shown in Table 1, for example.

In the process of FIG. 11, first, in step S10, the image acquisition unit 30 of the control unit 22 waits until the cow evaluation program 78 is started. In this case, the process moves to step S12 when the control unit 22 starts the cow evaluation program 78 in response to an operation by the operator (e.g., an input operation to the operation unit 14 or a voice input to a microphone (not shown)).

When the process proceeds to step S12, the image acquisition unit 30 acquires an image 50 of the cow to be evaluated for meatiness (see FIG. 3). The image 50 of the cow is an image of the cow in an upright position captured from almost directly behind. The image acquisition unit 30 acquires, for example, an image of the cow captured by the operator using the imaging unit 18. The image acquisition unit 30 may acquire an image of the cow received from another device via the communication unit 16, or an image of the cow selected by the operator by operating the operation unit 14 from among multiple images of the cow stored in the storage unit 20. The image acquisition unit 30 may start a camera function so that the operator can capture an image of the cow using the imaging unit 18 after the cow evaluation program 78 is started. When the operator captures an image of the cow using the imaging unit 18, the image of the captured cow and a selection button asking whether or not to select this image may be displayed on the display unit 12, and if the operator chooses not to select the image, the camera function may be started again.

In step S14, the extraction unit 32 of the control unit 22 extracts a contour line 60 that traces the outline of the cow from the captured image 50 of the cow acquired in step S12 (see FIG. 4). This generates an extracted image 51 showing the cow's contour line 60. When extracting the contour line 60, the extraction unit 32 may perform a process to remove background other than the cow from the captured image 50 in order to extract the contour line 60 with good accuracy.

Next, in step S16, in this first embodiment, the determination unit 38 of the control unit 22 determines a point 403a on the first curved portion 63a of the peak 61a and a point 404a on the second curved portion 64a. The determination unit 38 determines the point on the first curved portion 63a that first touches the peak 61a when the horizontal line 420 approaches the peak 61a from above the peak 61a toward the peak 61a as point 403a, and determines the point on the second curved portion 64a that first touches the peak 61a when the vertical line 422a approaches the peak 61a from the left side of the peak 61a toward the peak 61a as point 404a (see FIG. 5).

Next, in step S18, the calculation unit 34 of the control unit 22 first identifies a point 406a where a straight line 424a that passes through a midpoint 405a of a line segment 410a connecting points 403a and 404a and is perpendicular to the line segment 410a intersects with the peak portion 61a. The calculation unit 34 then calculates an angle ω1 between a line segment 412a connecting points 403a and 406a and a line segment 414a connecting points 404a and 406a (see FIG. 6(a)).

Next, in step S20, the evaluation unit 36 of the control unit 22 evaluates the body condition score of the cow captured in the captured image 50 based on the angle ω1 calculated in step S18 and the score information such as that in Table 1 stored in the memory unit 20.

Next, in step S22, the evaluation unit 36 displays the body condition score evaluated in step S20 on the display unit 12 and stores it in the memory unit 20. For example, the evaluation unit 36 may display the body condition score on the display unit 12 together with the captured image 50 of the cow. The evaluation unit 36 may also associate individual identification information, such as the individual identification number of the cow, input by the operator operating the operation unit 14 with the evaluated body condition score and store it in the memory unit 20. Note that the evaluation unit 36 is not limited to acquiring individual identification information input by the operator operating the operation unit 14, but may also acquire individual identification information from an image captured by the imaging unit 18 of an image of an identification tag attached to the body of the cow, or may acquire individual identification information by using RFID (Radio Frequency Identification) technology and having the communication unit 16 receive the individual identification information from an RF tag attached to the body of the cow. Alternatively, cameras and communication devices may be installed in the passages inside and outside the barn so that the sensors can detect cows passing through the passages, and the images of the cows passing through the passages captured by the cameras may be acquired by the communication unit 16, and the individual identification information may be acquired from the images of the identification tags captured in the images. Alternatively, the communication device may receive the individual identification information from RF tags attached to the cows passing through the passages, and the communication unit 16 may receive the individual identification information from the communication device. Also, the evaluation unit 36 may store in the memory unit 20 the individual identification number of the cow whose body condition score has been evaluated, the image 50 of the cow, the image date, and the body condition score of the cow as a single piece of associated information.

As described above, according to the first embodiment, the image acquisition unit 30 acquires a two-dimensional captured image 50 of a cow in a standing position captured from almost directly behind (see FIG. 3). The extraction unit 32 extracts the cow's contour line 60 from the captured image 50 (see FIG. 4). The determination unit 38 determines a point 403a (first point) on the first curved portion 63a of the peak portion 61a of the two peak portions 61a, 61b that exist on both the left and right sides of the upper part of the contour line 60, and a point 404a (second point) on the second curved portion 64a (see FIG. 5). The calculation unit 34 identifies a point 406a (third point) where a straight line 424a that passes through a midpoint 405a of a line segment 410a (first line segment) that connects the points 403a and 404a and is perpendicular to the line segment 410a intersects the peak portion 61a. Then, the calculation unit 34 calculates the angle ω1 between the line segment 412a (third line segment) connecting the point 403a and the point 406a and the line segment 414a (fourth line segment) connecting the point 404a and the point 406a (see FIG. 6A). The evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the angle ω1 calculated by the calculation unit 34. In this way, in the first embodiment, the beefiness of the cow is evaluated using the two-dimensional captured image 50 in which the cow in an upright position is captured from substantially behind, so that it is possible to apply the present invention to a variety of breeding sites without requiring special equipment for capturing images of the cow in three dimensions or special equipment for capturing images of the cow from above. In addition, the angle ω1 does not change whether the cow is captured large or small in the captured image 50, which is a two-dimensional image. Therefore, by using the angle ω1 to evaluate the beefiness of the cow, the beefiness of the cow can be evaluated well without performing processing such as normalization. Furthermore, when a person evaluates the fleshiness of a cow, the judgment criteria become vague and the judgment varies, but in this first embodiment, the control unit 22 judges the fleshiness of the cow, so the variation in judgment can be suppressed. Furthermore, since the fleshiness of the cow is evaluated using a two-dimensional captured image 50 captured from almost directly behind a cow in an upright position, the evaluation device 100, which is highly portable and versatile, such as a smartphone, can be used.

In addition, in this first embodiment, as shown in FIG. 5, the determination unit 38 determines the point of the first curved portion 63a of the peak portion 61a that protrudes most upward as point 403a on the first curved portion 63a. Also, the determination unit 38 determines the point of the second curved portion 64a of the peak portion 61a that protrudes most outward as point 404a on the second curved portion 64a. The angle ω1 calculated using such points 403a and 404a has a high correlation with the body condition score, as shown in FIG. 9. Therefore, by evaluating the beefiness of the cow using the angle ω1, it is possible to accurately evaluate the beefiness of the cow.

In the first embodiment, the determination unit 38 determines the first point of contact when the horizontal line 420 approaches the peak 61a from above the peak 61a as point 403a on the first curved portion 63a, as shown in FIG. 5. The determination unit 38 also determines the first point of contact when the vertical line 422a approaches the peak 61a from the side of the peak 61a as point 404a on the second curved portion 64a. This makes it possible to determine the point of the first curved portion 63a that protrudes most upward as point 403a, and the point of the second curved portion 64a that protrudes most outward as point 404a, by simple processing.

As described above, the determination unit 38 may determine a point 403b (first point) on the first curved portion 63b of the peak portion 61b of the two peak portions 61a, 61b present on both the left and right sides of the upper part of the contour line 60, and a point 404b (second point) on the second curved portion 64b (see FIG. 5). The calculation unit 34 may identify a point 406b (third point) at which a straight line 424b passing through a midpoint 405b of a line segment 410b (first line segment) connecting the points 403b and 404b and perpendicular to the line segment 410b intersects with the peak portion 61b, and calculate an angle ω2 between a line segment 412b (third line segment) connecting the points 403b and 406b and a line segment 414b (fourth line segment) connecting the points 404b and 406b (see FIG. 6B). The evaluation unit 36 may then evaluate the beefiness of the cow captured in the captured image 50 from the angle ω2 calculated by the calculation unit 34. In this case, the same effect can be obtained as when evaluating the beefiness of the cow from the angle ω1.

The determination unit 38 may determine points 403a, 403b (first points) on the first curved portions 63a, 63b and points 404a, 404b (second points) on the second curved portions 64a, 64b for both of the two peaks 61a, 61b on the left and right sides of the upper part of the contour line 60 as described above (see FIG. 5). The calculation unit 34 may calculate the average value of the angle ω1 between the line segment 412a and the line segment 414a in the peak portion 61a and the angle ω2 between the line segment 412b and the line segment 414b in the peak portion 61b. The evaluation unit 36 may evaluate the fleshiness of the cow captured in the captured image 50 from the average value of the angles ω1 and ω2 calculated by the calculation unit 34. The average value of the angles ω1 and ω2 has a high coefficient of determination ^R2 , which indicates a correlation with the body condition score, as described in FIG. 9. Therefore, the meatiness of the cow can be evaluated with high accuracy. Also, by using the average value of the angles ω1 and ω2, the effect of the shooting angle when the cow is imaged from almost directly behind is reduced.

In the first embodiment, the evaluation unit 36 may determine the body condition score from at least two of the angles ω1, ω2, and the average value of the angles ω1 and ω2, and evaluate the average value of the determined body condition scores.

When evaluating the beefiness of a cow, the user can select whether to use angle ω1, angle ω2, or the average value of angles ω1 and ω2.

[Other Determination Methods by Determination Unit 38]
12(a) to 12(c) are diagrams showing other determination methods by the determination unit 38. As shown in Fig. 12(a), there are cases where a part of the second curved portion 64a of the peak portion 61a is parallel to the vertical line 422a, and the point where the vertical line 422a first touches the second curved portion 64a is not a point but a range 426. In this case, the determination unit 38 determines the central point of the range 426 to be point 404a. The same applies to points 403a, 403b, and 404b.

As shown in FIG. 12(b), there are cases where the first curved portion 63a of the mountain portion 61a continues to rise from the apex 62a toward the uppermost point 91 without forming a depression. In this case, the determination unit 38 determines the inflection point on the apex 62a side of the contour line 60, which is the point of the first curved portion 63a located closest to the cow's spine, to be point 403a. The same applies to point 403b.

As shown in FIG. 12(c), there are cases where the second curved portion 64a of the mountain portion 61a continues to descend from the apex 62a downward without forming a depression. In this case, the determination unit 38 determines the point on the second curved portion 64a that is located closest to the abdomen, that is, the boundary point between the waist angle and the abdomen, as point 404a. The same applies to point 404b.

Even in the cases of Figures 12(a) to 12(c), the determination unit 38 determines the point of the first curved portion 63a that protrudes most upward as point 403a, and determines the point of the second curved portion 64a that protrudes most to the side as point 404a. Therefore, as in the first embodiment, the beefiness of the cow can be evaluated with high accuracy.

Second Embodiment
The functional configuration and hardware configuration of the cattle evaluation device according to the second embodiment are the same as those of the first embodiment shown in Fig. 1 and Fig. 10. The functional configuration of the control unit 22 in the second embodiment is the same as that of the first embodiment shown in Fig. 2, but the processing executed by the calculation unit 34 differs from that in the first embodiment. The following description will focus on the processing executed by the calculation unit 34.

13(a) and 13(b) are diagrams for explaining the process executed by the calculation unit 34 in the second embodiment. As shown in FIG. 13(a), when the determination unit 38 determines the point 403a on the first curved portion 63a of the peak 61a and the point 404a on the second curved portion 64a, the calculation unit 34 calculates the length X1a of the line segment 410a connecting the points 403a and 404a, the length X2a of the line segment 416a connecting the midpoint 405a and the point 406a, or the length ratio (X1a/X2a) of the length X1a to the length X2a. The length X1a, the length X2a, and the length ratio (X1a/X2a) calculated by the calculation unit 34 are one of the index values indicating the degree of inclination of the peak 61a.

The evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the length X1a, the length X2a, or the length ratio (X1a/X2a) calculated by the calculation unit 34.

As shown in FIG. 13(b), when the determination unit 38 determines point 403b on the first curved portion 63b of the peak 61b and point 404b on the second curved portion 64b, the calculation unit 34 calculates the length X1b of the line segment 410b connecting point 403b and point 404b, the length X2b of the line segment 416b connecting midpoint 405b and point 406b, or the length ratio (X1b/X2b) of length X1b to length X2b. The length X1b, length X2b, and length ratio (X1b/X2b) calculated by the calculation unit 34 are one of the index values indicating the degree of inclination of the peak 61b.

The evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the length X1b, the length X2b, or the length ratio (X1b/X2b) calculated by the calculation unit 34.

In addition, when the determination unit 38 determines all of the points 403a on the first curved portion 63a of the crest 61a, the points 404a on the second curved portion 64a, and the points 403b on the first curved portion 63b of the crest 61b, and the points 404b on the second curved portion 64b, the calculation unit 34 may calculate the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b). In this case, the evaluation unit 36 may evaluate the beefiness of the cow captured in the captured image 50 from the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b) calculated by the calculation unit 34.

14(a) to 14(c) are diagrams showing the relationship between the fatness of a cow and the lengths X1a and X2a calculated by the calculation unit 34. FIG. 14(a) shows the contour line 60 of a thin cow, FIG. 14(b) shows the contour line 60 of a cow that is fatter (fattier) than the cow in FIG. 14(a), and FIG. 14(c) shows the contour line 60 of a cow that is fatter (fattier) than the cow in FIG. 14(b). As shown in FIG. 14(a) to FIG. 14(c), it was found that the length X1a of the line segment 410a connecting the points 403a and 404a, and the length X2a of the line segment 416a connecting the midpoint 405a and 406a, are larger as the cow is more fleshy. It was also found that the length ratio (X1a/X2a) of the length X1a to the length X2a is smaller as the cow is more fleshy. From these facts, it is considered that the fleshiness of a cow can be evaluated by determining the length X1a, the length X2a, or the length ratio (X1a/X2a). Although not shown in the figure, the same applies to the relationship between the fleshiness of a cow and the length X1b, the length X2b, and the length ratio (X1b/X2b) calculated by the calculation unit 34.

[experiment]
An experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the value calculated by the calculation unit 34. The experiment was conducted on dairy cows (Holstein breed).

FIG. 15 shows the results of an experiment investigating the correlation between the body condition score and the length X1a, length X1b, and the average value of the length X1a and length X1b calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 15 is the body condition score evaluated by an expert, and the vertical axis is the length. A plurality of black circles in FIG. 15 show the results of each dairy cow when the length X1a is used, and the dotted straight line shows the approximation straight line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the length X1b is used, and the dashed straight line shows the approximation straight line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average value of the length X1a and the length X1b is used, and the dashed straight line shows the approximation straight line (regression line) at that time. As shown in FIG. 15, whether the length X1a, the length X1b, or the average value of the length X1a and the length X1b is used, the body condition score increases as the length increases. The approximate dotted line using the length X1a was calculated as y = 5.8314x + 3.8135, and the coefficient of determination ^R2 was 0.6037. The approximate dashed line using the length X1b was calculated as y = 5.9771x + 2.7028, and the coefficient of determination ^R2 was 0.6084. The approximate dashed line using the average values of the lengths X1a and X1b was calculated as y = 5.9042x + 3.2582, and the coefficient of determination ^R2 was 0.6537. This confirmed that there is a strong correlation between the body condition score and the lengths X1a, X1b, and the average values of the lengths X1a and X1b calculated by the calculation unit 34.

In this way, since there is a strong correlation between the body condition score and the length X1a, length X1b, and the average value of length X1a and length X1b calculated by the calculation unit 34, the evaluation unit 36 evaluates the fleshiness of the cow using length X1a, length X1b, or the average value of length X1a and length X1b. For example, the fleshiness of the cow is evaluated using score information similar to that shown in Table 1, which associates length X1a, length X1b, or the average value of length X1a and length X1b with the body condition score. This allows the fleshiness of the cow to be evaluated with high accuracy.

FIG. 16 shows the results of an experiment investigating the correlation between the body condition score and the length X2a, length X2b, and the average value of the length X2a and length X2b calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 16 is the body condition score evaluated by an expert, and the vertical axis is the length. A plurality of black circles in FIG. 16 show the results of each dairy cow when the length X2a is used, and the dotted straight line shows the approximation straight line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the length X2b is used, and the dashed straight line shows the approximation straight line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average value of the length X2a and the length X2b is used, and the dashed straight line shows the approximation straight line (regression line) at that time. As shown in FIG. 16, whether the length X2a, the length X2b, or the average value of the length X2a and the length X2b is used, the body condition score increases as the length increases. The approximate dotted line using the length X2a was calculated as y = 2.0388x - 2.2042, and the coefficient of determination ^R2 was 0.7707. The approximate dashed line using the length X2b was calculated as y = 2.5939x - 3.9392, and the coefficient of determination ^R2 was 0.7297. The approximate dashed line using the average values of the lengths X2a and X2b was calculated as y = 2.3164x - 3.0717, and the coefficient of determination ^R2 was 0.8098. This confirmed that there is a strong correlation between the body condition score and the lengths X2a, X2b, and the average values of the lengths X2a and X2b calculated by the calculation unit 34.

In this way, since there is a strong correlation between the body condition score and the length X2a, length X2b, and the average value of length X2a and length X2b calculated by the calculation unit 34, the evaluation unit 36 evaluates the fleshiness of the cow using length X2a, length X2b, or the average value of length X2a and length X2b. For example, the fleshiness of the cow is evaluated using score information similar to that shown in Table 1, which associates length X2a, length X2b, or the average value of length X2a and length X2b with the body condition score. This allows the fleshiness of the cow to be evaluated with high accuracy.

FIG. 17 shows the results of an experiment investigating the correlation between the body condition score and the length ratio (X1a/X2a) of the length X1a to the length X2a calculated by the calculation unit 34, the length ratio (X1b/X2b) of the length X1b to the length X2b, and the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b). The horizontal axis (x-axis) of FIG. 17 is the body condition score evaluated by an expert, and the vertical axis is the length ratio. A plurality of black circles in FIG. 17 show the results of each dairy cow when the length ratio (X1a/X2a) is used, and the dotted straight line shows the approximation straight line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the length ratio (X1b/X2b) is used, and the dashed straight line shows the approximation straight line (regression line) at that time. The black triangles indicate the results for each dairy cow when the average length ratio ((X1a/X2a)+(X1b/X2b))/2) is used, and the dashed straight line indicates the approximation line (regression line) at that time. As shown in FIG. 17, the body condition score increases as the length ratio decreases, regardless of whether the length ratio (X1a/X2a), the length ratio (X1b/X2b), or the average length ratio (X1a/X2a) and the length ratio (X1b/X2b) is used. The dotted approximation line using the length ratio (X1a/X2a) was calculated as y=-1.0967x+9.0164, and the coefficient of determination ^R2 was 0.5676. The dashed-dotted approximation line using the length ratio (X1b/X2b) was calculated as y=-1.5338x+10.441, and the coefficient of determination ^R2 was 0.5985. The dashed approximation line using the average values of the length ratios (X1a/X2a) and (X1b/X2b) was calculated as y = -1.3152x + 9.7286, with a coefficient of determination ^R2 of 0.6353. This confirmed that there is a strong correlation between the body condition score and the length ratios (X1a/X2a), (X1b/X2b), and the average values of the length ratios (X1a/X2a) and (X1b/X2b) calculated by the calculation unit 34.

In this way, since there is a strong correlation between the body condition score and the length ratio (X1a/X2a), the length ratio (X1b/X2b), and the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b) calculated by the calculation unit 34, the evaluation unit 36 evaluates the beefiness of the cow using the length ratio (X1a/X2a), the length ratio (X1b/X2b), or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b). For example, the beefiness of the cow is evaluated using score information that associates the length ratio (X1a/X2a), the length ratio (X1b/X2b), or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b) with the body condition score, as shown in Table 1. This allows the beefiness of the cow to be evaluated with high accuracy.

As described above, according to the second embodiment, the calculation unit 34 calculates the length X1a of the line segment 410a connecting the points 403a and 404a, the length X2a of the line segment 416a (second line segment) connecting the midpoint 405a and 406a, or the length ratio (X1a/X2a) of the length X1a to the length X2a (see FIG. 13(a)). The evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the length X1a, length X2a, or length ratio (X1a/X2a) calculated by the calculation unit 34. Even in this case, as in the first embodiment, the beefiness of the cow is evaluated using a two-dimensional captured image 50 in which a cow in an upright position is captured from approximately behind, so that it can be applied to a variety of breeding sites. In addition, when the beefiness of the cow is evaluated using the length ratio (X1a/X2a), the beefiness of the cow can be evaluated well without performing processing such as normalization, as in the first embodiment. Furthermore, because the control unit 22 judges the beefiness of the cow, the variation in the judgment can be suppressed. Furthermore, because the beefiness of the cow is evaluated using a two-dimensional captured image 50 captured from almost directly behind the cow in an upright position, it is possible to use an evaluation device such as a smartphone that is highly portable and versatile.

In addition, when the determination unit 38 determines the point 403b (first point) on the first curved portion 63b of the mountain portion 61b and the point 404b (second point) on the second curved portion 64b, the calculation unit 34 calculates the length X1b of the line segment 410b (first line segment) connecting the points 403b and 404b, the length X2b of the line segment 416b (second line segment) connecting the midpoint 405b and the point 406b, or the length ratio (X1b/X2b) of the length X1b to the length X2b (see FIG. 13(b)). The evaluation unit 36 evaluates the beefiness of the cow captured in the captured image 50 from the length X1b, length X2b, or length ratio (X1b/X2b) calculated by the calculation unit 34. Even in this case, the same effect as when evaluating the beefiness of the cow from the length X1a, length X2a, or length ratio (X1a/X2a) can be obtained.

In addition, when the determination unit 38 determines points 403a, 403b (first points) on the first curved portions 63a, 63b and points 404a, 404b (second points) on the second curved portions 64a, 64b for both of the peaks 61a, 61b, the calculation unit 34 may calculate the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b). The evaluation unit 36 may evaluate the fleshiness of the cow captured in the captured image 50 from the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a/X2a) and the length ratio (X1b/X2b) calculated by the calculation unit 34. As explained in Figures 15 to 17, the average values of the lengths X1a and X1b, the average values of the lengths X2a and X2b, and the average values of the length ratios (X1a/X2a) and (X1b/X2b) have a high coefficient of determination ^R2 , which indicates a correlation with the body condition score. This allows the meatiness of the cow to be evaluated with high accuracy. In addition, by using the average values of the lengths X1a and X1b, the average values of the lengths X2a and X2b, and the average values of the length ratios (X1a/X2a) and (X1b/X2b), the cow is less susceptible to the influence of the shooting angle when the cow is imaged from approximately directly behind.

When evaluating the fleshiness of a cow using length X1a, length X1b, length X2a, length X2b, the average of length X1a and length X1b, and the average of length X2a and length X2b, it is preferable to photograph a reference object that serves as a standard for length when photographing the cow from approximately directly behind, or to photograph it at the same distance and at the same magnification.

When evaluating the fleshiness of a cow, the user can select which of the following will be used: length X1a, length X1b, length X2a, length X2b, length ratio (X1a/X2a), length ratio (X1b/X2b), average value of length X1a and length X1b, average value of length X2a and length X2b, or average value of length ratio (X1a/X2a) and length ratio (X1b/X2b).

In the first and second embodiments, the calculation unit 34 may calculate two or more of the angle ω1, the length X1a, the length X2a, and the length ratio (X1a/X2a) for the peak 61a. The evaluation unit 36 may evaluate the beefiness of the cow by the maximum, minimum, or average value of the body condition score obtained from each of the two or more values of the angle ω1, the length X1a, the length X2a, and the length ratio (X1a/X2a). Similarly, the calculation unit 34 may calculate two or more of the angle ω2, the length X1b, the length X2b, and the length ratio (X1b/X2b) for the peak 61b. The evaluation unit 36 may evaluate the beefiness of the cow by the maximum, minimum, or average value of the body condition score obtained from each of the two or more values of the angle ω2, the length X1b, the length X2b, and the length ratio (X1b/X2b). The evaluation unit 36 may also evaluate the beefiness of the cattle based on the maximum, minimum, or average body condition score obtained from two or more of the average values of the angles ω1 and ω2, the average values of the lengths X1a and X1b, the average values of the lengths X2a and X2b, and the average values of the length ratios (X1a/X2a) and (X1b/X2b).

In the above first and second embodiments, the midpoints 405a and 405b of the line segments 410a and 410b are used as an example, but approximate midpoints located within a range of 1/50 or less of the length of the line segments 410a and 410b from the midpoints of the line segments 410a and 410b may be used. The straight lines 424a and 424b and the line segments 416a and 416b are perpendicular to the line segments 410a and 410b as an example, but they may be approximate perpendicular lines inclined within a range of ±5° from the perpendicular to the line segments 410a and 410b.

In the first and second embodiments, the determination unit 38 may convert the extracted image 51 into an X-Y coordinate system, and determine the points of the first curved portions 63a and 63b that protrude most upward from the X and Y coordinates of each pixel of the extracted image 51 as points 403a and 403b, and determine the points of the second curved portions 64a and 64b that protrude most to the side as points 404a and 404b.

[Acceptable angles of horizontal line 420 and vertical lines 422a, 422b]
In the above first and second embodiments, a case has been shown in which points 403a, 403b on the first curved portions 63a, 63b are determined using the horizontal line 420 in the extracted image 51. A case has been shown in which points 404a, 404b on the second curved portions 64a, 64b are determined using the vertical lines 422a, 422b in the extracted image 51. Here, an investigation was conducted to determine to what extent an inclination angle is permissible when a slightly inclined approximately horizontal line is used instead of the horizontal line 420, and when a slightly inclined approximately vertical line is used instead of the vertical lines 422a, 422b.

[experiment]
Points 403a, 403b on the first curved portions 63a, 63b were determined using approximately horizontal lines with inclination angles of -20°, -10°, 0°, 10°, and 20° from the horizontal line in the extracted image 51. The inclination angle when the approximately horizontal line extends from the lower left to the upper right was determined as positive, and the inclination angle when the approximately horizontal line extends from the lower right to the upper left was determined as negative. Furthermore, points 404a, 404b on the second curved portions 64a, 64b were determined using approximately vertical lines with inclination angles of 80°, 90°, and 100° from the horizontal line in the extracted image 51. When the inclination angle is 80°, the approximately vertical line extends from the lower left to the upper right, and when the inclination angle is 100°, the approximately vertical line extends from the lower right to the upper left.

Using the determined points, the coefficient of determination R2 between the average values of the angles ω1 and ω2 and the body condition score was calculated as in the first embodiment. Using the determined points, the coefficient of determination ^R2 between the average values of the lengths X1a and X1b and the body condition score, the coefficient of determination ^R2 between the average values of the lengths X2a and X2b and the body condition score, and the coefficient of determination ^R2 between the average values of the length ratio (X1a/X2a) of the length X1a to the length X2a and the length ratio (X1b/X2b) of the length X1b to the length X2b and the body condition score were calculated as in the ^second embodiment. The experimental results are shown in Table 2.

As shown in Table 2, when the average values of the angles ω1 and ω2 were used, a large coefficient of determination R ² was obtained when an approximately horizontal line with an inclination angle of -10° to 20° and an approximately vertical line with an inclination angle of 80° to 90° were used. When the average values of the lengths X1a and X1b were used, a large coefficient of determination R ² was obtained when an approximately horizontal line with an inclination angle of -20° to 20° and an approximately vertical line with an inclination angle of 90° were used. When the average values of the lengths X2a and X2b were used, a large coefficient of determination R ² was obtained when an approximately horizontal line with an inclination angle of -10° to 20° and an approximately vertical line with an inclination angle of 80° to 90° were used. When the average value of the length ratio was used, a large coefficient of determination R ² was obtained when an approximately horizontal line with an inclination angle of -10° to 20° and an approximately vertical line with an inclination angle of 90° were used. From these results, points 403a, 403b on the first curved portions 63a, 63b are determined using an approximately horizontal line with an inclination angle of -10° to 20° from the horizontal direction (left-right direction) in the extracted image 51. Points 404a, 404b on the second curved portions 64a, 64b are determined using an approximately vertical line with an inclination angle of 80° to 90° from the horizontal direction (left-right direction) in the extracted image 51. This allows the beefiness of the cow to be evaluated with high accuracy. From the viewpoint of evaluating the beefiness of the cow with high accuracy, the inclination of the approximately horizontal line is more preferably -5° to 10°, and even more preferably -5° to 5°, and the inclination of the approximately vertical line is more preferably 85° to 90°.

In the above first and second embodiments, the image acquisition unit 30 has been described as acquiring an image of a cow in a standing position taken from approximately directly behind, but it may also be possible to acquire an image of a cow in a standing position taken from approximately the front. FIG. 18(a) is an image 50 of a cow in a standing position taken from approximately directly behind, and FIG. 18(b) is an image 50a of the cow in FIG. 18(a) taken from approximately the front. As shown in FIG. 18(a), it is not limited to the case where a cow in a standing position is imaged from approximately directly behind. Even if a cow in a standing position is imaged from approximately the front, as shown in FIG. 18(b), it is possible to image the cow so that the contours around the left and right hip angles of the cow are visible.

Figures 19(a) and 19(b) are extracted images 51 in which the contour line 60 of the cow is extracted from the captured images 50 and 50a of Figures 18(a) and 18(b). As shown in Figure 19(a), even if the image of the cow in a standing position is taken from almost directly behind, as shown in Figure 19(b), the ridges 61a and 61b corresponding to the hip angle can be present on both the left and right sides of the upper part of the contour line 60. Therefore, even if the captured image 50a of the cow in a standing position taken from almost directly in front is used, the beefiness of the cow can be evaluated in the same manner as when the captured image 50 taken from almost directly behind is used. In addition, even if the two-dimensional captured image 50a of the cow in a standing position taken from almost directly in front is used, as in the case of using the captured image 50 taken from almost directly behind, no special equipment is required to capture the image of the cow from above, and it can be applied to various breeding sites, and a portable information device such as a smartphone, which is highly portable and versatile, can be used as the evaluation device.

In the above first and second embodiments, the evaluation device for evaluating the beefiness of the cattle is a portable information device equipped with an image capturing unit 18 that is carried by the worker, but other cases are also possible. For example, it may be a stationary information device such as a server that can communicate with other devices connected to a network. In this case, the worker transmits an image of the cattle taken using a portable information device such as a smartphone to a stationary information device such as a server via the network. The stationary information device performs the same process as the evaluation device 100 to evaluate the beefiness of the cattle. The stationary information device then transmits the evaluation result of the beefiness of the cattle to a portable information device carried by the worker via the network. This reduces the load on the smartphone. In addition, a camera may be installed in the cattle shed so that it can be fixed or moved, and the portable information device such as a smartphone and the stationary information device such as a server may acquire an image of the cattle standing upright, captured by the camera installed in the cattle shed, from approximately directly behind or approximately in front of the cattle.

In the above first and second embodiments, the body condition score is evaluated as the amount of meat in the cow, but other indices for evaluating the amount of meat in the cow may be evaluated. In addition, although each experiment was performed on dairy cows, it is believed that beef cows, which have a similar skeletal structure, would produce similar results. Therefore, each of the above embodiments can be applied not only to dairy cows but also to beef cows.

Although the embodiment of the present invention has been described in detail above, the present invention is not limited to such a specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention as described in the claims.

REFERENCE SIGNS LIST 12 display unit 14 operation unit 16 communication unit 18 imaging unit 20 storage unit 22 control unit 30 image acquisition unit 32 extraction unit 34 calculation unit 36 evaluation unit 38 determination unit 50, 50a captured image 51 extracted image 52 upper left end point 54 upper right end point 55, 55a, 55b, 56, 56a, 56b inclined straight line 60 contour line 61a, 61b mountain portion 62a, 62b apex 63a, 63b first curved portion 64a, 64b second curved portion 91 uppermost point 100 evaluation device 403a, 403b points 404a, 404b points 405a, 405b midpoint 406a, 406b points 410a, 410b Line segment 412a, 412b Line segment 414a, 414b Line segment 416a, 416b Line segment 420 Horizontal line 422a, 422b Vertical line 424a, 424b Straight line 426 Range

Claims (8)

an image acquisition unit for acquiring a two-dimensional image of a cow in a standing position from approximately directly behind or approximately directly in front of the cow;
an extraction unit that extracts a contour line of the cow from the captured image;
a determination unit that determines a first point on a first curved portion extending from a substantially central point on the contour line of one of two peak portions present on both the left and right sides of an upper portion of the contour line toward the other peak portion, and a second point on a second curved portion extending to an opposite side to the first curved portion;
a calculation unit that calculates at least one of a length of a first line segment connecting the first point and the second point, a length of a second line segment connecting a third point at which a straight line passing through an approximate midpoint of the first line segment and approximately perpendicular to the first line segment intersects with the one mountain portion and approximately the midpoint of the first line segment, a ratio of a length of the first line segment to a length of the second line segment, and an angle formed by a third line segment connecting the first point and the third point and a fourth line segment connecting the second point and the third point;
A cattle evaluation device comprising: an evaluation unit that evaluates the fleshiness of the cattle from the value calculated by the calculation unit. The cattle evaluation device according to claim 1, wherein the determination unit determines the point of the first curved portion that protrudes most upward as the first point, and determines the point of the second curved portion that protrudes most laterally as the second point. The cattle evaluation device according to claim 1 or 2, wherein the determination unit determines the first point as the point where a first line extending in a substantially left-right direction in the captured image first touches one of the peaks when the first line approaches the one of the peaks from above the one of the peaks, and determines the second point as the point where a second line extending in a substantially up-down direction in the captured image first touches one of the peaks when the second line approaches the one of the peaks from the side of the one of the peaks. the determination unit determines the first point on the first curved portion and the second point on the second curved portion for the other of the two peak portions;
4. The cattle evaluation device according to claim 1, wherein the calculation unit calculates at least one of the length of the first line segment, the length of the second line segment, the ratio of the length of the first line segment to the length of the second line segment, and the angle formed between the third line segment and the fourth line segment for the other ridge portion, and calculates at least one of the average length of the first line segment for each of the two ridge portions, the average length of the second line segment for each of the two ridge portions, the average ratio of the length of the first line segment to the length of the second line segment for each of the two ridge portions, and the average angle formed between the third line segment and the fourth line segment for each of the two ridge portions. The cattle evaluation device according to any one of claims 1 to 4, wherein the two peaks correspond to the hip angles of the cattle. The cattle evaluation device according to any one of claims 1 to 5, wherein the evaluation unit evaluates the body condition score as an evaluation of the beefiness of the cattle. The cattle evaluation device according to any one of claims 1 to 6, comprising an imaging unit that images the cattle. A contour line of a cow is extracted from a two-dimensional captured image of the cow in a standing position taken from approximately directly behind or approximately directly in front of the cow;
determining a first point on a first curved portion extending from a substantially central point on the contour line of one of two peaks present on both the left and right sides of an upper portion of the extracted contour line toward the other peak, and a second point on a second curved portion extending to an opposite side to the first curved portion;
calculating at least one of the following: a length of a first line segment connecting the determined first point and the second point; a length of a second line segment connecting a third point at which a straight line passing through the approximate midpoint of the first line segment and approximately perpendicular to the first line segment intersects with the one mountain portion and the approximate midpoint of the first line segment; a ratio of the length of the first line segment to the length of the second line segment; and an angle formed by a third line segment connecting the first point and the third point and a fourth line segment connecting the second point and the third point;
The meatiness of the cattle is evaluated based on the calculated value.
A method for evaluating cattle, characterized in that processing is carried out by a computer.

Images