CN116823802A - Method for detecting water level based on image processing - Google Patents
Method for detecting water level based on image processing Download PDFInfo
- Publication number
- CN116823802A CN116823802A CN202310890899.8A CN202310890899A CN116823802A CN 116823802 A CN116823802 A CN 116823802A CN 202310890899 A CN202310890899 A CN 202310890899A CN 116823802 A CN116823802 A CN 116823802A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- water level
- image processing
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a water level detection method based on image processing, which comprises the following steps: collecting a floating position image of a humidification tank of the breathing machine; converting the humidifying tank buoy position image into a humidifying tank buoy position gray level image, and acquiring gray level image parameters; and performing image processing on the gray level image, namely searching index values of gray level image data arranged in sequence according to gray level image parameters to obtain a float position, so as to realize automatic detection of the water level of the humidification tank. According to the method, the floating position image of the humidification tank is converted into the gray level image of the floating position of the humidification tank, gray level image parameters are obtained, the gray level image is subjected to image processing to detect the water level, the detection speed is high, the reliability is high, and the overall detection efficiency is improved.
Description
Technical Field
The invention belongs to the field of water level monitoring systems of respiratory humidification equipment, and particularly relates to a water level detection method based on image processing, which is applied to respiratory humidification equipment.
Background
The respiratory humidification equipment is usually matched with an air source for use, and provides heated and humidified respiratory air for patients so as to maintain the physiological conditions necessary for the normal clearance function of the airway surface mucociliary system and the normal comfort and dispersion characteristics of alveolar epithelium and reduce airway dryness and inflammatory symptoms. Among the prior art, the humidification device in the respiratory humidification type equipment includes the humidification jar, and in use heats the water in the humidification jar through the heating dish, makes the air current carry vapor to carry the patient end through heating respiratory line, and the in-process humidification jar has the possibility of dry combustion method, will not satisfy patient's respiratory tract temperature and humidity's physiological demand, can lead to respiratory tract and lung to excessively dry and amazing, causes physiological influence to the patient.
The existing respiratory humidification equipment water level monitoring method is to judge whether dry burning exists according to the power of a heating disc after acquiring the temperature of an air outlet of a humidification tank and the temperature of the heating disc. The method needs to obtain more parameters, wherein the temperature value fluctuation is larger due to the influence of the outside in the temperature obtaining process, so that the parameter accuracy is influenced, and the reliability is lower; in the method, the water level is indirectly estimated by measuring the temperature, the time required from parameter acquisition to final control of the heating disc power is long, the water storage condition in the humidifying tank cannot be timely detected, and the safety is low.
Disclosure of Invention
The invention aims to provide the method for automatically detecting the water level, which has high reliability, high accuracy and high detection efficiency by combining the camera with the image processing technology.
The technical scheme adopted by the invention for achieving the purpose is as follows: a water level detection method based on image processing comprises the following steps:
collecting a floating position image of a humidification tank of the breathing machine;
converting the humidifying tank buoy position image into a humidifying tank buoy position gray level image, and acquiring gray level image parameters;
and performing image processing on the gray level image, namely searching index values of gray level image data arranged in sequence according to gray level image parameters to obtain a float position, so as to realize automatic detection of the water level of the humidification tank.
The gray image parameters comprise maximum value, minimum value, average value, standard deviation value and peak-to-peak value of gray image data.
After the gray image parameters are obtained, judging whether the gray image meets the image processing requirements or not;
if the average value, the standard deviation value and the peak-to-peak value of the gray level image are all in the set range, the gray level image is considered to accord with the image processing requirement so as to perform image processing;
otherwise, the gray level image is enabled to meet the image processing requirement by adjusting the light supplementing lamp so as to process the image;
the adjusting light supplementing lamp comprises the following specific components:
when the gray value of the gray image is smaller than the threshold value M1, a light supplementing lamp is started;
when the gray value is larger than the threshold value M2, the light supplementing lamp is turned off; wherein M1< M2.
The image processing of the gray image comprises the following steps:
taking the average value of gray image data of the floating position of the humidifying tank and the average value of the minimum value as a threshold T1;
all the gray image data of the tank buoy position larger than the threshold value T1 are assigned to be the threshold value T1;
sequentially searching a first index of the minimum gray image data of the float position of the humidifying tank according to the sampling time, and marking the first index as I1;
sequentially searching the last index of the minimum gray image data of the float position of the humidifying tank according to the sampling time, and marking the last index as I2;
searching forward with I1 as a start until a value with data of T1 is found, recording the current index as I3, wherein the data corresponding to the I3 is the upper edge position of the buoy;
and starting to search backwards by taking I2 as a start until a value with the data of T1 is found, and recording the current index of I4, wherein the data corresponding to the I4 is the position of the lower edge of the buoy.
When W1< K, the upper edge position of the float is I5=I1- (K-W1)/2, and if W1 is more than or equal to K, I5=I1;
when W1 is less than K, the lower edge position of the float is I6=I2+ (K-W1)/2, and if W1 is more than or equal to K, I6=I2;
k is a pixel width set value occupied by the float, and the minimum value includes a range w1=i2-I1.
Averaging operation is carried out on the upper edge position I5 or I3 of the buoy, and the method comprises the following steps:
water level position i7= (i5+i3)/2;
and (3) acquiring gray level images of the floating positions of the humidification tanks in the T time, calculating the water level position I7 obtained by each gray level image in the T time, and taking the average value W2 of the water level positions I7 obtained by all gray level images as an optimized water level value.
A water level detection device based on image processing, comprising:
the image acquisition module is used for acquiring images of the floating position of the humidification tank of the breathing machine;
the gray image parameter acquisition module is used for converting the humidifying tank floating position image into a humidifying tank floating position gray image and acquiring gray image parameters;
the image processing module is used for carrying out image processing on the gray level image, namely, according to gray level image parameters, acquiring a float position by searching index values of gray level image data which are sequentially arranged, and realizing automatic detection of the water level of the humidification tank.
A water level detection device based on image processing comprises a memory and a processor; the memory is used for storing a computer program; the processor is used for realizing the method for detecting the water level based on image processing when executing the computer program.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of detecting water level based on image processing.
The invention has the following beneficial effects and advantages:
1. according to the invention, the water level image is directly acquired, the water level data is acquired after the image is processed, the acquired data is less, the influence of the environment is less, and the reliability is higher.
2. According to the invention, the light supplementing lamp is additionally arranged at the same time of data acquisition, so that the requirement of image processing is met, and the detection accuracy is improved.
3. According to the method, the floating position image of the humidification tank is converted into the gray level image of the floating position of the humidification tank, gray level image parameters are obtained, the gray level image is subjected to image processing to detect the water level, the detection speed is high, and the overall detection efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a water level monitoring device according to the present invention;
FIG. 2 is a low water level gray scale plot of the present invention;
FIG. 3 is a water level map calculated by the low water level algorithm 1 of the present invention;
FIG. 4 is a water level map calculated by the low water level algorithm 2 of the present invention;
FIG. 5 is a graph showing the water level calculated by algorithm 1 and algorithm 2 of the present invention;
FIG. 6 is a mid-level gray scale plot of the present invention;
FIG. 7 is a water level map calculated by the mid-water level algorithm 1 of the present invention;
FIG. 8 is a water level map calculated by the mid-water level algorithm 2 of the present invention;
FIG. 9 is a graph showing the comparison of the water levels calculated by algorithm 1 and algorithm 2 of the present invention;
FIG. 10 is a flowchart of an exposure algorithm of the present invention;
fig. 11 is a program flow chart of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in fig. 1, the automatic device for detecting the water level in the humidification tank according to the invention is based on the camera shooting an image with a certain pixel and performing image processing, and comprises:
the humidifying tank is used for storing a certain amount of water and is used for humidifying.
And the camera is used for acquiring images.
And when the external environment is darker, the image acquired by the camera cannot meet the requirement of image processing, and the light supplementing lamp is utilized to supplement light at the moment so as to meet the requirement of image processing.
MCU: the method is used for image processing and judging the water level. The MCU stores a program, and when the program is called, the steps of adjusting the brightness of the picture, collecting the image, processing the image and the like are executed.
As shown in fig. 10 and 11, a method for detecting a water level based on an image processing technology includes the following steps:
and configuring camera parameters and initializing a camera.
And collecting a frame of floating position image of the humidifying tank.
The humidifying tank buoy position image is converted into a humidifying tank buoy position gray level image, and the conversion formula is as follows: gray=r 0.299+g 0.587+b 0.114.
And calculating the gray average value of all pixel points of the gray image at the floating position of the humidification tank.
And judging whether the frame of image meets the image processing requirement or not, wherein the gray scale is more than 15 and less than 40.
And judging whether the frame image meets the image processing requirement. If the standard of the image processing is met, the image processing is carried out, and if the standard of the image processing is not met, the on-off of the light supplementing lamp and the exposure time of the camera are adjusted so as to meet the requirement of the image processing.
The light supplementing lamp is turned on when the gray value is less than 15, and is turned off when the gray value is greater than 30. The exposure time is adjusted by adjusting the exposure time register of the camera. The adjustment in the two ways is used to achieve the gray value of the image between 15 and 45, and the adjustment flow is shown in fig. 10.
And carrying out data compression and uploading the data to the main board MCU.
As shown in fig. 11, the main board MCU receives gray image data of a frame of floating position of the humidification tank, and performs the following steps:
and carrying out mean value filtering on gray image data of the floating position of the humidification tank.
And calculating the key data such as the maximum value, the minimum value, the average value, the standard deviation value, the peak value and the like of the gray image data of the float position of the humidification tank.
And judging whether the standard deviation value and the peak-to-peak value accord with the image processing standard.
And waiting for the next frame of image without meeting the image processing standard.
And (5) carrying out threshold calculation according with standard.
And taking the average value of gray image data of the floating position of the humidification tank and the average value of the minimum value as a threshold T1.
All the gray image data of the tank buoy positions larger than the threshold value T1 are assigned as the threshold value T1.
Searching a first index of the minimum value of gray image data of the float position of the humidification pot, and marking the first index as I1.
Searching the last index of the minimum value of gray image data of the float position of the humidification pot, and marking as I2.
The method comprises the steps of starting with I1, searching forward until a value with data of T1 is found, and recording the current index as I3.
The method comprises the steps of starting with I2, looking backwards until a value with data of T1 is found, and recording the current index as I4.
I3 is the cursory upper edge of such an algorithm.
I4 is the cursory trailing edge of such an algorithm.
The above steps are the float positions obtained by the algorithm 1, are used for conventionally calculating the float positions, the accuracy of the water level information collected under the general environment is higher, and the collected float width is too small due to the fact that the partial reflection of the light occurs under certain extreme environments, so that the accuracy is affected.
When the calculated float width of the algorithm 1 is too large or too small, the algorithm 2 is adopted to correct the error, and the method comprises the following steps:
obtaining I1, I2, I3 and I4 according to the algorithm 1;
the range included in the calculated minimum value is: I2-I1, designated W1.
A typical value (K value) of the pixel width occupied by the float was determined to be 60 by a certain number of experiments.
Calculating the cursory upper edge of such an algorithm: i1- (60-W1)/2 is denoted as I5.
Calculating the cursory lower edge of such an algorithm: i2+ (60-W1)/2 is designated I6.
The calculated water level data of gray level image data of the floating position of the frame humidifying tank is (I5+I3)/2 and is marked as I7.
And collecting gray image data of the floating position of the humidifying tank for 3 minutes, and calculating an average value W2 of I7 data in the three minutes, wherein the average value is the current water level value.
And comparing the value of W2 with a water level threshold value, and judging whether the current water level is too low.
The relative positions of the camera and the humidification tank are shown in figure 1.
Example 1:
an anhydrous humidification tank was placed in the humidifier.
A frame of data is collected and filtered, the graph is shown in fig. 2.
The data obtained after filtering are as follows:
42,41,40,39,38,37,37,37,38,37,37,38,40,42,43,45,45,46,46,46,46,45,45,45,45,46,45,45,
45,45,45,45,45,44,43,43,43,44,43,43,43,42,41,40,39,39,39,39,39,39,39,39,39,39,39,39,
39,39,39,39,39,39,39,39,39,39,39,39,39,38,38,38,38,38,38,38,38,38,38,38,38,38,39,39,
39,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,39,39,
39,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,40,39,39,39,39,40,40,40,39,39,39,
39,40,40,40,40,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,3938,38,38,
39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,38,38,38,38,39,39,39,39,39,39,
39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,38,38,38,38,38,38,
38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,38,37,37,37,37,37,37,37,37,
37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,37,
37,37,37,37,36,36,36,36,36,36,36,36,36,36,36,36,36,35,35,35,35,36,36,36,36,36,36,36,
36,36,36,36,36,36,36,36,36,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,
35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,35,
35,35,35,35,35,35,35,35,35,35,35,35,34,34,34,34,34,34,34,34,34,34,34,34,34,34,33,33,
33,33,33,32,32,32,32,32,32,32,32,31,31,31,31,31,31,32,32,32,32,31,31,31,31,31,30,30,
30,30,30,29,29,29,29,29,29,29,29,29,29,28,28,28,28,28,28,28,28,28,28,28,28,28,27,27,
27,27,27,26,26,26,27,27,27,26,26,26,25,25,24,23,23,22,21,21,20,19,19,18,18,17,17,17,
17,17,17,17,17,17,17,17,18,18,19,20,21,22,22,23,23,23,23,24,24,24,24,25,25,25,25,25,
25,25,24,24,24,24,24,24,24,24,24,24,24,24,24,24,24,24,24,24,23,23,23,24,24,24,24,24,
24,24,24,24,25,25,25,26,26,26,26,26,26,26,26,26,26,26,27,27,27,27,27,27,27,27,28,28,
28,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,30,29,29,29,29,29,28,
27,25,22,20,18,16,14,11,9,8,8,7,7,7,7,7,7,7,6,6,6,5,5,5,5,5,5,4,
4,4,4,4,4,4,4,4,4,3,3,3,3,3,3,3,3,3,3,3,4,7,7
the average value of the gray scale was calculated to be 31, the maximum value was 46, the minimum value was 3, the peak-to-peak value was 43, and the standard deviation was 7.
The algorithm 1 calculates as follows:
threshold t1= (31+3)/2=17.
The index I1 of the first data having the gradation of the minimum value 3 is 626.
The index I2 of the last data having the gradation of the minimum value 3 is 636.
The index is searched forward by taking I1 (626) as a starting index until the index data is found to be greater than or equal to a value of T1 (17), and the current index is recorded as I3 (593).
Looking back with I2 (636) as the starting index until a value of index data greater than or equal to T1 (17) is found, recording the current index as I4 (none, when index is not found as I4 value is 640).
Algorithm 1 results in a float top I3, i.e., 593, and a float width I3-I4, i.e., 640-593=47. As shown in fig. 3 and 4.
The algorithm 2 calculates as follows:
obtaining I1, I2, I3 and I4 according to the algorithm 1;
the range included in the calculated minimum value is: w1=i2-i1=636-626=10.
Calculating the cursory upper edge of such an algorithm: i5 =i1- (60-W1)/2=626- (60-10)/2=601.
Calculating the cursory lower edge of such an algorithm: i6 =i2+ (60-W1)/2=636+ (60-10)/2=661.
Float position i7= (i3+i5)/2= (593+601)/2=597
I7 =597, the calculated float position at this time, as shown in fig. 5.
Example 2:
a full water humidification tank was placed in the humidifier.
A frame of data is collected and filtered as shown in fig. 6.
32,31,31,29,28,27,27,27,27,27,27,28,29,32,36,39,41,41,40,39,39,39,38,37,38,38,38,38,
37,38,40,40,38,36,34,35,35,36,36,35,35,33,32,30,29,28,28,28,29,29,29,29,29,29,29,29,
29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,28,28,28,28,29,29,29,
29,29,30,30,30,30,30,30,30,30,30,30,30,30,30,30,29,29,29,29,29,30,30,30,30,30,29,29,
29,29,30,30,30,30,30,29,29,29,29,29,29,29,30,29,29,29,29,29,29,29,29,29,29,29,29,29,
29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,
28,28,28,29,28,28,28,28,28,29,29,29,29,29,29,29,29,29,29,29,29,29,28,28,28,29,28,28,
28,28,28,28,28,28,28,28,28,28,28,28,28,28,28,27,27,27,27,28,28,27,27,27,28,28,28,27,
27,27,27,27,27,27,27,28,28,28,27,27,27,27,27,27,27,27,27,27,27,27,27,27,27,27,26,26,
26,27,27,27,27,27,27,26,26,26,27,27,27,27,27,27,27,27,27,27,27,26,26,26,26,26,26,26,
26,26,26,26,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,
25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,25,24,24,24,24,24,24,24,24,24,24,24,24,
24,24,24,24,24,24,24,24,24,24,24,24,25,25,24,24,24,25,25,25,25,25,24,24,24,24,24,24,
24,24,24,24,24,24,24,24,24,24,24,24,23,23,23,23,23,23,23,23,22,22,22,22,22,22,22,22,
22,22,22,22,22,22,21,21,21,22,22,21,21,21,21,21,20,20,20,20,20,20,20,19,19,19,18,18,
18,18,18,18,18,18,17,17,17,17,17,16,16,16,16,15,15,15,15,14,14,14,14,14,14,14,14,14,
14,14,15,15,15,15,15,15,16,16,16,16,16,16,15,15,14,14,13,13,12,12,12,11,11,10,10,9,
9,9,9,9,8,8,8,9,9,9,9,8,8,7,7,6,6,5,5,5,5,5,5,5,5,5,5,4,
4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,3,3,3,3,3,
3,3,4,4,4,4,4,5,5,5,6,7,7,8,8,9,9,
10,10,10,11,11,11,11,12,12,12,12,12,12,13,13,13,13,13,13,13,13,13,13,13,14,14,14,14,
14,14,14,15,15,15,15,15,15,16,15,15,15,16,16,16,16,16,16,16,16,17,17,17,17,17,17,17,
17,17,17,17,18,18,18,18,17,17,17,18,18,18,18,18,18,18,18,18,18,17,17,17,17,18,18,18,
18,18,17,17,16,16,16
The average value of the gray scale is calculated to be 22, the maximum value is 41, the minimum value is 3, the peak-to-peak value is 38, and the standard deviation is 7.
The algorithm 1 calculates as follows:
threshold t1= (22+3)/2=12.
The index I1 of the first data having the gradation of the minimum value 3 is 527.
The index I2 of the last data having the gradation of the minimum value 3 is 533.
The index is searched forward with I1 (527) as a starting index until the index data is found to be greater than or equal to a value of T1 (12), and the current index is recorded as I3 (470).
Looking back with I2 (533) as the starting index until the index data is found to be greater than or equal to the value of T1 (12), recording the current index as I4 (556).
Algorithm 1 results in a float top I3, 470, and a float width I3-I4, 556-470=86, algorithm 2 calculated as follows:
obtaining I1, I2, I3 and I4 according to the algorithm 1;
the range included in the calculated minimum value is: w1=i2-i1=533-527=6.
Calculating the cursory upper edge of such an algorithm: i5 =i1- (60-W1)/2=527- (60-6)/2=500. Calculating the cursory lower edge of such an algorithm: i6 =i2+ (60-W1)/2=i2+ (60-W1)/2=560 float positions i7= (i3+i5)/2= (500+470)/2=485; as shown in fig. 7 and 8.
I7 =485, the calculated float position at this time, as shown in fig. 9.
Claims (9)
1. The method for detecting the water level based on the image processing is characterized by comprising the following steps of:
collecting a floating position image of a humidification tank of the breathing machine;
converting the humidifying tank buoy position image into a humidifying tank buoy position gray level image, and acquiring gray level image parameters;
and performing image processing on the gray level image, namely searching index values of gray level image data arranged in sequence according to gray level image parameters to obtain a float position, so as to realize automatic detection of the water level of the humidification tank.
2. The image processing-based water level detection method according to claim 1, wherein the gray image parameters include maximum value, minimum value, average value, standard deviation value, peak-to-peak value of gray image data.
3. The method for detecting water level based on image processing according to claim 1, wherein after the gray image parameters are obtained, judging whether the gray image meets the image processing requirement;
if the average value, the standard deviation value and the peak-to-peak value of the gray level image are all in the set range, the gray level image is considered to accord with the image processing requirement so as to perform image processing;
otherwise, the gray level image is enabled to meet the image processing requirement by adjusting the light supplementing lamp so as to process the image;
the adjusting light supplementing lamp comprises the following specific components:
when the gray value of the gray image is smaller than the threshold value M1, a light supplementing lamp is started;
when the gray value is larger than the threshold value M2, the light supplementing lamp is turned off; wherein M1< M2.
4. The method for detecting water level based on image processing according to claim 1, wherein the image processing of the gray scale image comprises the steps of:
taking the average value of gray image data of the floating position of the humidifying tank and the average value of the minimum value as a threshold T1;
all the gray image data of the tank buoy position larger than the threshold value T1 are assigned to be the threshold value T1;
sequentially searching a first index of the minimum gray image data of the float position of the humidifying tank according to the sampling time, and marking the first index as I1;
sequentially searching the last index of the minimum gray image data of the float position of the humidifying tank according to the sampling time, and marking the last index as I2;
searching forward with I1 as a start until a value with data of T1 is found, recording the current index as I3, wherein the data corresponding to the I3 is the upper edge position of the buoy;
and starting to search backwards by taking I2 as a start until a value with the data of T1 is found, and recording the current index of I4, wherein the data corresponding to the I4 is the position of the lower edge of the buoy.
5. The method for detecting water level based on image processing according to claim 4, wherein when W1< K, the upper edge position i5=i1- (K-W1)/2 of the float, if W1 is not less than K, i5=i1;
when W1 is less than K, the lower edge position of the float is I6=I2+ (K-W1)/2, and if W1 is more than or equal to K, I6=I2;
k is a pixel width set value occupied by the float, and the minimum value includes a range w1=i2-I1.
6. A method of detecting a water level based on image processing according to claim 4 or 5, wherein the averaging operation is performed on the upper edge position I5 or I3 of the float, comprising the steps of:
water level position i7= (i5+i3)/2;
and (3) acquiring gray level images of the floating positions of the humidification tanks in the T time, calculating the water level position I7 obtained by each gray level image in the T time, and taking the average value W2 of the water level positions I7 obtained by all gray level images as an optimized water level value.
7. A water level detection device based on image processing, comprising:
the image acquisition module is used for acquiring images of the floating position of the humidification tank of the breathing machine;
the gray image parameter acquisition module is used for converting the humidifying tank floating position image into a humidifying tank floating position gray image and acquiring gray image parameters;
the image processing module is used for carrying out image processing on the gray level image, namely, according to gray level image parameters, acquiring a float position by searching index values of gray level image data which are sequentially arranged, and realizing automatic detection of the water level of the humidification tank.
8. The water level detection device based on image processing is characterized by comprising a memory and a processor; the memory is used for storing a computer program; the processor is configured to implement an image processing based water level detection method according to any one of claims 1-5 when executing the computer program.
9. A computer readable storage medium, wherein a computer program is stored on the storage medium, which, when being executed by a processor, implements a method for detecting a water level based on image processing as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310890899.8A CN116823802A (en) | 2023-07-20 | 2023-07-20 | Method for detecting water level based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310890899.8A CN116823802A (en) | 2023-07-20 | 2023-07-20 | Method for detecting water level based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116823802A true CN116823802A (en) | 2023-09-29 |
Family
ID=88120336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310890899.8A Pending CN116823802A (en) | 2023-07-20 | 2023-07-20 | Method for detecting water level based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823802A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118052820A (en) * | 2024-04-16 | 2024-05-17 | 沈阳迈思医疗科技有限公司 | Water level detection method, device, equipment, storage medium and system |
-
2023
- 2023-07-20 CN CN202310890899.8A patent/CN116823802A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118052820A (en) * | 2024-04-16 | 2024-05-17 | 沈阳迈思医疗科技有限公司 | Water level detection method, device, equipment, storage medium and system |
| US12392653B1 (en) | 2024-04-16 | 2025-08-19 | Shenyang Rms Medical Tech Co., Ltd | Water level detection method, device, equipment, storage medium and system |
| WO2025218695A1 (en) * | 2024-04-16 | 2025-10-23 | 沈阳迈思医疗科技有限公司 | Water level detection method and apparatus, device, storage medium, and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116823802A (en) | Method for detecting water level based on image processing | |
| CN110986258B (en) | Air conditioner temperature sensor control method, computer readable storage medium and air conditioner | |
| CN108245759A (en) | Breathe humidification instrument humiture output control system and method | |
| CN116207312A (en) | Tail row control method and tail row control device for fuel cell system | |
| CN113989258B (en) | Photovoltaic panel hot spot positioning method based on drone and thermal imaging | |
| CN116147159A (en) | An automatic exhaust and ventilation type office space air circulation system | |
| US12392653B1 (en) | Water level detection method, device, equipment, storage medium and system | |
| CN112626437B (en) | Hot galvanizing humidifying system and method based on visual recognition | |
| CN118838188A (en) | Power consumption management regulation and control system and method based on edge computing gateway | |
| CN116576553B (en) | Data optimization acquisition method and system for air conditioner | |
| CN115325664B (en) | Intelligent control method, device, equipment and medium for humidification and sterilization of air conditioner | |
| CN113203185B (en) | Defrosting control method and device, computer readable storage medium and air conditioner | |
| CN114173850B (en) | Calibration methods for oxygen sensors, medical ventilation systems, anesthesia machines, ventilators | |
| US11764370B2 (en) | System and method for controlling operation of fuel cell system | |
| CN117390379B (en) | On-line signal measuring device and confidence measuring device for signal characteristics | |
| CN118195068A (en) | A carbon emission early warning system with automatic identification and early warning | |
| CN114288516B (en) | Dry combustion early warning method and early warning device for humidifier of sleep breathing machine | |
| CN111156655A (en) | Air conditioner main control board fault self-detection method and air conditioner | |
| CN118327951A (en) | Aging detection method and system for electric vehicle air conditioning compressor | |
| US7523651B2 (en) | Method for monitoring the state of turbines based on their coasting time | |
| CN114417057A (en) | Physiological space-time big data processing method based on image recognition and Internet of things | |
| CN104515247A (en) | Composite temperature control system and control method thereof | |
| CN112902396A (en) | Energy-saving and control method based on transition season by using all fresh air | |
| CN117870088B (en) | Air conditioner control method using sensor | |
| CN111457629A (en) | A modular air source heat pump unit group defrosting control system and method based on image recognition frost detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |