CN116137079A - Image processing method, device and equipment method - Google Patents

Abstract

The invention discloses an image processing method, device and equipment, wherein the method includes: acquiring multiple grayscale regions of the image to be detected; point, obtain the three-dimensional coordinates of the spatial point corresponding to the pixel point; obtain the spatial gradient histogram of the image to be detected according to the three-dimensional coordinates of the spatial point; identify the image to be detected according to the spatial gradient histogram target object in . Through the above method, the present invention can more comprehensively extract image features and improve the accuracy of image recognition.

Description

An image processing method, device and equipment method

technical field

The present invention relates to the technical field of image processing, in particular to an image processing method, device and equipment.

Background technique

In recent years, pedestrian detection and face recognition have become more and more common in daily life, and computer vision has become a research hotspot for current scholars. The Histogram of Oriented Gradient (HOG) feature is a feature description used in computer vision and image processing for object detection. The HOG feature constitutes a feature by calculating and counting the gradient orientation histogram of the local area of the image.

The main disadvantages of the existing HOG feature implementation methods are: the feature dimension is large, and the feature extraction sensitivity for pictures with high pixels or long-distance pictures is low. The amount of calculation is large, and the time complexity of processing complex images is high. There are certain errors in the HOG feature extraction method.

Contents of the invention

In view of the above problems, embodiments of the present invention are proposed to provide an image processing method, device, and device that overcome the above problems or at least partially solve the above problems.

According to an aspect of an embodiment of the present invention, an image processing method is provided, the method comprising:

Obtain multiple grayscale regions of the image to be detected;

Acquiring the three-dimensional coordinates of the spatial points corresponding to the pixel points according to the pixel points in each gray-scale area of the plurality of gray-scale areas;

Acquiring a spatial gradient histogram of the image to be detected according to the three-dimensional coordinates of the spatial point;

A target object in the image to be detected is identified according to the spatial gradient histogram.

According to another aspect of the embodiments of the present invention, an image processing device is provided, and the device includes:

An acquisition module, configured to acquire multiple grayscale regions of the image to be detected;

A processing module, configured to obtain the three-dimensional coordinates of the spatial point corresponding to the pixel according to the pixel points in each gray-scale region of the plurality of gray-scale regions; obtain the three-dimensional coordinates of the spatial point according to the three-dimensional coordinates of the spatial point A spatial gradient histogram of the image to be detected; identifying a target object in the image to be detected according to the spatial gradient histogram.

According to still another aspect of the embodiments of the present invention, a computing device is provided, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete the mutual communication via the communication bus. communication between

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the above image processing method.

According to yet another aspect of the embodiments of the present invention, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform operations corresponding to the above image processing method.

According to the solutions provided by the above-mentioned embodiments of the present invention, according to the pixel points in each gray-scale area of the plurality of gray-scale areas, the three-dimensional coordinates of the spatial points corresponding to the pixel points are obtained; according to the three-dimensional coordinates of the spatial points Coordinates, to obtain the spatial gradient histogram of the image to be detected; according to the spatial gradient histogram, identify the target object in the image to be detected; thus, the image features can be analyzed while maintaining the image geometry and optical deformation invariance Extraction is performed to ensure the comprehensiveness of image feature extraction and further improve the accuracy of image recognition.

The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and The advantages can be more obvious and understandable, and the specific implementation manners of the embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered as limiting the embodiments of the present invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a flowchart of an image processing method provided by an embodiment of the present invention;

FIG. 2 shows a schematic diagram of image cells to be detected in the flow of an image processing method provided by another embodiment of the present invention;

Fig. 3 shows a schematic diagram of image cells to be detected in the flow of an image processing method provided by another embodiment of the present invention;

FIG. 4 shows a schematic structural diagram of an image processing device provided by an embodiment of the present invention;

Fig. 5 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

FIG. 1 shows a flowchart of an image processing method provided by an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

Step 11, obtaining multiple grayscale regions of the image to be detected;

Step 12, according to the pixel points in each gray-scale area of the plurality of gray-scale areas, obtain the three-dimensional coordinates of the spatial points corresponding to the pixel points;

Step 13, obtaining the spatial gradient histogram of the image to be detected according to the three-dimensional coordinates of the spatial point;

Step 14: Identify the target object in the image to be detected according to the spatial gradient histogram.

In this embodiment, the grayscale area of the image to be detected is obtained to avoid color interference during image feature extraction, and the pixels in each grayscale area are projected into the spatial coordinate system, and the three-dimensional coordinates of the spatial points are calculated, Processing the image in three-dimensional space ensures the invariance of image geometry and optical deformation, and has certain estimation and calculation for occluded objects; according to the three-dimensional coordinates, the spatial gradient histogram of the image to be detected is calculated, The feature extraction of the image to be detected is performed by using the space gradient histogram, which ensures the comprehensiveness of the feature extraction and improves the recognition rate and accuracy of the target object.

In an optional embodiment of the present invention, step 11 may include:

Step 111, acquiring the image to be detected;

Step 112, performing grayscale processing on the image to be detected to obtain a grayscale image of the image to be detected;

Step 113 , performing segmentation processing on the grayscale image to obtain multiple grayscale regions.

In this embodiment, grayscale processing is performed on the image to be detected to avoid color interference during feature extraction, and normalization processing is performed on the grayscale image after grayscale processing to adjust the contrast of the image to be detected and reduce the Influenced by information such as human body, background and light;

Preferably, the Gamma compression formula is used for processing, i.e. I(x, y, z)=I(x, y, z) ^gamma , wherein I is an image to be detected; The image is cut and processed, and each slice is extracted during feature extraction to ensure the comprehensiveness and accuracy of feature extraction.

In an optional embodiment of the present invention, step 113 may include:

Step 1131 , segment the grayscale image according to the first grayscale threshold to obtain multiple grayscale regions; the value range of the first grayscale threshold is [0, 255].

In this embodiment, the grayscale image is segmented within the first grayscale threshold range. Preferably, information entropy is used for segmentation. When the system is more chaotic and the uncertainty is greater, the information entropy is greater; when The more ordered the system, the higher the certainty, the smaller the information entropy;

Here, according to the formula: H=-Σp(x)logp(x), wherein P(x) represents the frequency of occurrence of the gray level x, and H represents information entropy.

In an optional embodiment of the present invention, step 1131 may include:

Step S1, using the grayscale area of the grayscale image whose grayscale value is lower than the first grayscale threshold as the background area, and the grayscale area higher than the first grayscale threshold as the target object area;

Step S2, calculating the ratio of each gray level in the background area and the target object area;

Step S3, calculating the information entropy of each gray level in the background area and the target object area according to the ratio;

Step S4, according to the sum of the information entropy of each gray level in the background area and the target object area, and a preset maximum information entropy, multiple gray area areas are obtained.

计算每个灰度在所述背景区域比例，其中P_B表示每个灰度在所述背景区域中的比例；In this embodiment, according to the formula:

Calculate the proportion of each grayscale in the background area, where P _B represents the proportion of each grayscale in the background area;

计算每个灰度在所述目标对象区域中的比例，其中，P_O表示每个灰度在所述目标对象区域中的比例，i表示一灰度，取值为正整数，P_T表示灰度值在灰度图像中出现的频率总和；According to the formula:

Calculate the ratio of each gray level in the target object area, wherein P _O represents the ratio of each gray level in the target object area, i represents a gray level, and the value is a positive integer, and P _T represents gray The sum of the frequencies of the grayscale values appearing in the grayscale image;

根据P_B、P_O的值以及信息熵计算公式，分别计算灰度i在所述背景区域和所述目标对象区域中的信息熵，即/>

并将两者信息熵相加，将得到的信息熵总和与最大信息熵对比；

According to the values of P _B , P _O and the information entropy calculation formula, respectively calculate the information entropy of the gray level i in the background area and the target object area, i.e.

Add the two information entropies together, and compare the obtained information entropy sum with the maximum information entropy;

If the sum of information entropy is greater than the maximum information entropy, assign the maximum information entropy to the maximum information entropy, set i as the threshold of binarization, if the information entropy sum is less than the maximum information entropy, then the maximum information entropy remains unchanged; optional, The initial value of the maximum information entropy here is set to -1.

In an optional embodiment of the present invention, step 12 may include:

Step 121, obtaining the projection coordinates of the spatial point corresponding to the pixel point in the gray-scale area in each gray-scale area of the plurality of gray-scale areas;

Step 122, according to the homogeneous coordinates of the projection points of the spatial points in different directions in the gray-scale region and the homogeneous coordinates of the spatial points in the world coordinate system, obtain the coordinates of the spatial points corresponding to the pixel points 3D coordinates.

In this embodiment, the spatial coordinates of the pixel points are calculated according to the coordinates of the pixel points in the projected coordinate system. For irregular objects with a high degree of occlusion, the characteristics of each pixel point can be calculated more accurately from the spatial coordinate system, so that Improve the accuracy of target object recognition.

The above embodiments will be described below in conjunction with specific examples:

For the imaging position q of any point Q in the image on the image, q is the intersection point of the line OQ connecting the optical center O and point Q and the image plane, then the relationship is as follows:

Among them, (x, y) is the image coordinates of point q, (X _c , Y _c , Z _c ) is the coordinates of spatial point Q in the projected coordinate system, f is the length of the connection line OQ, through homogeneous coordinates and matrix The above relationship can be expressed as:

Substituting formula (12.1) and formula (12.2) into the above formula (12.3), the relationship between the coordinates of point Q and the coordinates (u, v) of point q can be obtained:

M是3行4列的投影矩阵，R是旋转矩阵，t是平移矩阵；in,

M is a projection matrix with 3 rows and 4 columns, R is a rotation matrix, and t is a translation matrix;

Assuming that the camera shoots point Q from left and right directions, their projection points are q ₁ and q ₂ respectively, the position of the camera is fixed, and their projection matrices are M ₁ and M ₂ respectively, so there are:

表示为M_k的第i行第j列元素，Z_c1、Z_c2表示非零比例项。消去比例项，可以得到关于X，Y，Z的线性方程如下：Among them, (u ₁ ,v ₁ ,1) and (u ₂ ,v ₂ ,1) represent the homogeneous coordinates of q ₁ and q ₂ in their respective images, and (X,Y,Z,1) represent Q in the world Homogeneous coordinates in the coordinate system,

Expressed as the i-th row and j-th column element of M _k , Z _c1 and Z _c2 represent non-zero proportional items. By eliminating the proportional term, the linear equations about X, Y, and Z can be obtained as follows:

In the above four equations, the values of X, Y, and Z can be obtained by the method of least squares, and (X, Y, Z) is the spatial coordinate of point Q.

In an optional embodiment of the present invention, step 13 may include:

Step 131, calculating the amount of change between the three-dimensional coordinates of the spatial point corresponding to the pixel point in the grayscale area and the three-dimensional coordinates of the spatial point corresponding to the adjacent pixel point;

Step 132, obtain the image gradient of the pixel point according to the variation of the three-dimensional coordinates;

Step 133, according to the image gradient of the pixel, obtain the spatial gradient histogram of the image to be detected.

In this embodiment, the image gradient refers to the rate of change in the three directions of x, y, and z compared with adjacent pixels at a certain point of the image. It is a three-dimensional vector consisting of 3 components. The change of the X axis, The change of the Y axis and the change of the Z axis; the change of the X axis refers to the pixel value on the right side of the current pixel (X plus 1) minus the pixel value on the left side of the current pixel (X minus 1), and the change of the Y axis refers to The pixel value in front of the current pixel (Y plus 1) minus the pixel value behind the current pixel (Y minus 1), the change of the Z axis refers to the pixel value below the current pixel (Z plus 1) minus the pixel value above the current pixel (Z minus 1) Pixel value. These three components are calculated to form a three-dimensional vector, thereby obtaining the image gradient of the pixel. The image gradient can include the gradient direction and the magnitude of the gradient. By calculating the pixel three-dimensional space gradient of the image, the contour information of the image can be captured, and the interference of illumination can be further weakened. Further, take the arc tangent arctan to get the gradient angle. The three-dimensional spatial gradient calculation method is used to identify image features. For irregular and highly occluded objects, the features of each pixel can be calculated more accurately from the spatial coordinate system, thereby improving the accuracy of recognition.

Specifically, the gradient representation of the pixel point (x, y, z) in the image:

Gx(x,y,z)=H(x+1,y,z)-H(x-1,y,z) formula (13.1)

Gy(x,y,z)=H(x,y+1,z)-H(x,y-1,z) formula (13.2)

Gz(x,y,z)=H(x,y,z+1)-H(x,y,z-1) formula (13.3)

Among them, Gx(x,y,z) represents the gradient of the pixel point (x,y,z) in the input image in the x-axis direction, Gy(x,y,z) represents the gradient in the y-axis direction, Gz(x,y, z) represents the gradient in the z-axis direction.

The magnitude of the gradient at the pixel point (x, y, z) is:

The gradient direction is:

In an optional embodiment of the present invention, step 14 may include:

Step 141, dividing the image to be detected into a plurality of cells;

Step 142, collect the directional gradient histogram features in the spatially connected intervals of the plurality of cells, and obtain the directional gradient histogram feature set of the image to be detected;

Step 143: Obtain at least one target object according to the directional gradient histogram feature vector in the directional gradient histogram feature set of the image to be detected.

In this embodiment, the image is divided into multiple "cells", which facilitates setting different codes for different regions of the image, and reduces the sensitivity of the algorithm to the shape and appearance of the human body in the image. Each of the plurality of cells includes a plurality of pixels, and the characteristic information of a cell is counted using a histogram of direction cells.

As shown in Figure 2 and Figure 3, the image is divided into countless "cells", each cell contains 6 × 6 pixels, and the histogram of 9 bins (directions) is used to count the feature information of a cell. Considering the positive and negative directions, divide the 360-degree gradient space direction of the cell into 9 parts, and every 20 degrees corresponds to a direction unit. All gradient directions are divided into a feature vector containing 9 dimensions, that is, the gradient corresponding to the cell is obtained. Orientation histogram.

Further, by normalizing the spatial gradient histogram, the influence of factors such as illumination in the image can be reduced; multiple cells are combined into intervals that are connected to each other in space, and the background brightness and contrast of the image are avoided. The problem of large differences between multiple cells caused by the impact; and HOG feature collection is performed on the interval, and the HOG feature of an interval is the combination of all cell feature vectors in the interval.

进行归一化处理，通过归一化处理；Preferably, through the L2-norm normalization function

Perform normalization processing, through normalization processing;

个数据组成的高维度向量，其中β表示每个单元格中方向(bin)单元的数目，/>

表示区间的个数，η表示一个区间中单元格的数目。Through the above process, a

A high-dimensional vector composed of data, where β represents the number of direction (bin) cells in each cell, />

Indicates the number of intervals, and η indicates the number of cells in an interval.

Finally, collect the histogram of orientation gradient HOG features in all overlapping intervals in the detection window, and obtain the histogram of orientation gradient feature set of the image to be detected;

Classifying and identifying the directional gradient histogram feature vectors in the directional gradient histogram feature set of the image to be detected to obtain at least one target object, for example, classifying the directional gradient histogram feature vectors that meet a preset condition into one category , determine a target object according to the eigenvector of the histogram of oriented gradients of this category.

In the above-mentioned embodiment of the present invention, the gradient calculation is performed on the image in a three-dimensional vector space, and the feature extraction of the target object in the image to be detected is performed while maintaining the invariance of the image geometry and optical deformation, which has good characteristics and can be more comprehensively extracted Image features, thereby improving the accuracy of image recognition.

FIG. 4 shows a schematic structural diagram of an image processing device 40 provided by an embodiment of the present invention. As shown in Figure 4, the device 40 includes:

An acquisition module 41, configured to acquire a plurality of grayscale regions of the image to be detected;

The processing module 42 is configured to obtain the three-dimensional coordinates of the spatial points corresponding to the pixel points according to the pixel points in each of the gray-scale regions; and obtain the three-dimensional coordinates of the spatial points according to the three-dimensional coordinates of the spatial points. The spatial gradient histogram of the image to be detected; according to the spatial gradient histogram, identify the target object in the image to be detected.

Optionally, the acquiring module 41 is specifically configured to: acquire an image to be detected, perform grayscale processing on the image to be detected to obtain a grayscale image of the image to be detected; perform segmentation processing on the grayscale image to obtain multiple grayscale area.

Optionally, the grayscale image is segmented to obtain multiple grayscale regions, including:

The grayscale image is segmented according to the first grayscale threshold to obtain multiple grayscale regions; the value range of the first grayscale threshold is [0, 255].

Optionally, according to the first grayscale threshold, the grayscale image is segmented to obtain multiple grayscale regions, including:

Using the grayscale region of the grayscale image whose grayscale value is lower than the first grayscale threshold as the background region, and the grayscale region higher than the first grayscale threshold as the target object region;

calculating the proportion of each gray level in the background area and the target object area;

Calculate the information entropy of each gray level in the background area and the target object area according to the ratio;

According to the sum of the information entropy of each gray level in the background area and the target object area and a preset maximum information entropy, multiple gray area areas are obtained.

Optionally, the processing module 42 is specifically configured to: obtain the projected coordinates of a spatial point corresponding to a pixel in each gray-scale area in the plurality of gray-scale areas;

According to the homogeneous coordinates of the projection points of the spatial points in different directions in the gray scale area and the homogeneous coordinates of the spatial points in the world coordinate system, the three-dimensional coordinates of the spatial points corresponding to the pixel points are obtained.

Optionally, the processing module 42 is specifically configured to: calculate the amount of change between the three-dimensional coordinates of the spatial point corresponding to the pixel point in the grayscale area and the three-dimensional coordinates of the spatial point corresponding to the adjacent pixel points;

Obtaining the image gradient of the pixel point according to the variation of the three-dimensional coordinates;

According to the image gradient of the pixel point, the spatial gradient histogram of the image to be detected is obtained.

Optionally, the processing module 42 is specifically configured to: divide the image to be detected into a plurality of cells; perform direction gradient histogram feature collection in intervals where the plurality of cells are connected to each other in space, and obtain the The directional gradient histogram feature set of the image to be detected; according to the directional gradient histogram feature vector in the directional gradient histogram feature set of the image to be detected, at least one target object is obtained.

It should be noted that the device 40 is a device corresponding to the above-mentioned method, and all the implementation modes in the above-mentioned method embodiments are applicable to the embodiments of the device, and can also achieve the same technical effect.

An embodiment of the present invention provides a computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the image processing method in any one of the above method embodiments.

FIG. 5 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in FIG. 5 , the computing device may include: a processor (processor), a communication interface (Communications Interface), a memory (memory), and a communication bus.

Wherein: the processor, the communication interface, and the memory complete the mutual communication through the communication bus. The communication interface is used to communicate with network elements of other devices such as clients or other servers. The processor is configured to execute a program, and specifically, may execute relevant steps in the above embodiments of the image processing method for a computing device.

Specifically, the program may include program code including computer operation instructions.

The processor may be a central processing unit CPU, or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be of the same type, such as one or more CPUs, or may be different types of processors, such as one or more CPUs and one or more ASICs.

Memory for storing programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program may specifically be used to cause the processor to execute the image processing method in any of the above method embodiments. For the specific implementation of each step in the program, refer to the corresponding descriptions in the corresponding steps and units in the above image processing method embodiment, and details are not repeated here. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the foregoing method embodiments, and details are not repeated here.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present invention are not directed to any particular programming language. It should be understood that various programming languages can be used to implement the contents of the embodiments of the present invention described herein, and the above description of specific languages is for disclosing the best implementation mode of the embodiments of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be understood that in the above description of the exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together in order to simplify the embodiments of the present invention and facilitate understanding of one or more of the various inventive aspects. in a single embodiment, figure, or description thereof. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that although some embodiments herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components according to the embodiments of the present invention. Embodiments of the present invention can also be implemented as a device or apparatus program (eg, computer program and computer program product) for performing a part or all of the methods described herein. Such a program implementing an embodiment of the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims (10)

1. An image processing method, the method comprising:

acquiring a plurality of gray areas of an image to be detected;

according to the pixel points in each gray scale area in the plurality of gray scale areas, three-dimensional coordinates of space points corresponding to the pixel points are obtained;

acquiring a spatial gradient histogram of the image to be detected according to the three-dimensional coordinates of the spatial points;

and identifying the target object in the image to be detected according to the spatial gradient histogram.

2. The image processing method according to claim 1, wherein acquiring a plurality of gradation areas of the image to be detected includes:

acquiring an image to be detected;

carrying out gray scale processing on the image to be detected to obtain a gray scale image of the image to be detected;

and carrying out segmentation processing on the gray level image to obtain a plurality of gray level areas.

3. The image processing method according to claim 2, wherein the dividing the gradation image to obtain a plurality of gradation regions includes:

dividing the gray level image according to a first gray level threshold value to obtain a plurality of gray level areas; the value range of the first gray threshold is [0, 255].

4. The image processing method according to claim 3, wherein the dividing the gray image according to the first gray threshold value to obtain a plurality of gray areas comprises:

taking a gray level region of the gray level image, the gray level value of which is lower than a first gray level threshold value, as a background region, and taking a gray level region of which is higher than the first gray level threshold value as a target region;

calculating the proportion of each gray value in the background area and the target object area;

calculating information entropy of each gray value in the background area and the target object area according to the proportion;

and obtaining a plurality of gray areas according to the sum of the information entropy of each gray value in the background area and the target object area and the preset maximum information entropy.

5. The image processing method according to claim 1, wherein acquiring three-dimensional coordinates of a spatial point corresponding to a pixel point in each of the plurality of gradation areas from the pixel point, comprises:

obtaining projection coordinates of space points corresponding to pixel points in each gray scale region in the plurality of gray scale regions;

and obtaining the three-dimensional coordinates of the space point corresponding to the pixel point according to the homogeneous coordinates of the projection points of the space point in different directions in the gray scale area and the homogeneous coordinates of the space point in a world coordinate system.

6. The image processing method according to claim 1, wherein acquiring the spatial gradient histogram of the image to be detected based on the three-dimensional coordinates of the spatial points includes:

calculating the change quantity of the three-dimensional coordinates of the space points corresponding to the pixel points in the gray scale area and the three-dimensional coordinates of the space points corresponding to the adjacent pixel points respectively;

obtaining the image gradient of the pixel point according to the variation of the three-dimensional coordinates;

and obtaining a spatial gradient histogram of the image to be detected according to the image gradient of the pixel point.

7. The image processing method according to claim 1, wherein identifying the target object in the image to be detected based on the spatial gradient histogram, comprises:

dividing the image to be detected into a plurality of cells;

performing directional gradient histogram feature collection in the interval where the cells are spatially communicated to obtain a directional gradient histogram feature set of the image to be detected;

and obtaining at least one target object according to the directional gradient histogram feature vector in the directional gradient histogram feature set of the image to be detected.

8. An image processing apparatus, characterized in that the apparatus comprises:

the method comprises the steps of obtaining a module speed, wherein the module speed is used for obtaining a plurality of gray areas of an image to be detected;

the processing module is used for acquiring the three-dimensional coordinates of the space point corresponding to the pixel point according to the pixel point in each gray scale area in the plurality of gray scale areas; acquiring a spatial gradient histogram of the image to be detected according to the three-dimensional coordinates of the spatial points; and identifying the target object in the image to be detected according to the spatial gradient histogram.

9. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform the operations corresponding to the image processing method according to any one of claims 1 to 7.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the image processing method of any one of claims 1-7.

Images