CN113344960B - Live cattle body ruler weight measuring method based on machine vision - Google Patents
Live cattle body ruler weight measuring method based on machine vision Download PDFInfo
- Publication number
- CN113344960B CN113344960B CN202110505378.7A CN202110505378A CN113344960B CN 113344960 B CN113344960 B CN 113344960B CN 202110505378 A CN202110505378 A CN 202110505378A CN 113344960 B CN113344960 B CN 113344960B
- Authority
- CN
- China
- Prior art keywords
- cattle
- weight
- pixel
- image
- cow
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1072—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring distances on the body, e.g. measuring length, height or thickness
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G17/00—Apparatus for or methods of weighing material of special form or property
- G01G17/08—Apparatus for or methods of weighing material of special form or property for weighing livestock
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/40—Animals
Abstract
The invention belongs to the technical field of live cattle body ruler and weight measurement, and particularly relates to a live cattle body ruler and weight measurement method based on machine vision. The method comprises the steps of synchronously taking side-view pictures and top-view pictures of a cow as a sample photo set for data processing; extracting the image of the cow from the background by using an image segmentation algorithm, and performing binarization processing; extracting the pixel length of each position body ruler of the cattle according to the body part characteristics in the binarized cattle image; reserving the head and the trunk from the binary image; slicing the image of the cow in a direction vertical to the axis of the trunk by taking pixels as units, and respectively acquiring two groups of slices for side view and overlooking; calculating the pixel volume of the single slice, and summing all slices to obtain the total pixel volume; and deducing coefficients of the body size and the pixel weight of the cattle according to the actually measured body size and the actually measured body weight of the cattle, thereby completing the measurement of the body size and the actually measured body weight of the cattle.
Description
Technical Field
The invention belongs to the technical field of live cattle body ruler and weight measurement, and particularly relates to a live cattle body ruler and weight measurement method based on machine vision.
Background
In the process of breeding beef cattle and dairy cows, monitoring the growth condition of the cattle is crucial to production, but because the individual size of the cattle is large, the body size and weight measurement of the cattle is difficult, and the following problems are specifically caused:
(1) Difficulty in driving: the method for measuring the weight and body size of the cattle needs to drive the cattle to a specified place, and the driving process and the process of limiting the cattle to a measurement area are time-consuming and labor-consuming;
(2) The stress response of cattle is large: in the measurement process, a measurer needs to contact the body of a cow, such as tube circumference measurement, the reaction of the cow is very sudden, and the measurer is easily injured by a little carelessness;
(3) The measurement error is large: after the measuring tool is used for a long time, the precision is reduced to cause tool errors, and the proficiency of an operator on the measuring method also influences the measuring result to cause human errors;
(4) The labor cost is high: the driving process of the cattle needs cooperation of multiple persons, the measurement also needs cooperation of the multiple persons, the measurement time is long, the working strength is high, the number of participators is large, and the labor cost is high.
Also currently, for the estimation of the body weight of live cattle, the formula is used conventionally, namely: cattle weight = (chest circumference square x body slant length) ÷ 10800, but the method ignores the difference of cattle varieties, and the comparison of the calculation result with the measured weight has large error, so that the calculation data loses the reference value.
Disclosure of Invention
Aiming at the defects and problems of high labor intensity, low working efficiency, low measurement precision and large data error in the existing estimation of the body size and the weight of the live cattle, the invention provides a live cattle body size and weight measurement method based on machine vision.
The technical scheme adopted by the invention for solving the technical problems is as follows: a live cow body size and weight measuring method based on machine vision comprises the following steps:
step one, image acquisition: selecting N sample cattle as a cattle sample set, and measuring the actual measurement weight and each position body ruler value of each cattle; respectively arranging image acquisition devices right in front of and right above each cow, and synchronously acquiring a side view and a top view of the cow as acquired images;
step two, image processing: marking the background and the foreground of the collected image by adopting an image segmentation algorithm, and segmenting the image of the cow from the background to be used as a basic image; respectively carrying out binarization processing on the basic images of the side view and the top view to obtain side view and top view sample images;
step three, body size calculation:
(1) Extracting pixel volume scale values L of each part of the cattle according to the characteristics of each part of the cattle body in the sample image pi ；
(2) The pixel volume scale value L of each part of the cattle pi And the measured body scale value L ri Calculating to obtain the body ruler coefficient C of each part of the cattle i ，
(3) According to the body size coefficient C of all the cattle parts in the sample set i Calculating the average coefficient of body size of each part of all the cows
In the formula: m = N-x × N × 2,m>0,N is the total number of samples, x is the ratio of the maximum value to the minimum value to be removed, and i is the body part;
(4) Pixel value L of each position body ruler obtained by measurement pi Average body-size coefficient with corresponding part
Calculating to obtain estimated value L of each position body ruler of the cattle i ，
Step four, calculating the weight:
(1) Elliptical slicing of a sample image of a cow in units of a single pixel in a direction perpendicular to a torso axis X-axis in a side view of the sample image;
(2) Respectively taking the length l1 of the long-axis pixel and the length l2 of the short-axis pixel of the slice at the same point on the X axis, and calculating the pixel area S of the complete slice k ，
Then the pixel volume V of a single slice is obtained by calculating the unit pixel thickness k ，V k ＝S k ×1；
(3) The total pixel volume Wp of the cattle is obtained by accumulating all the single slice pixel volumes j ，
In the formula: q is the total number of slices; k is a slice number; j is a cattle number;
(4) Obtaining the pixel volume according to the actually measured weight Wrj of each cattleWp j And the measured body weight Wr j Coefficient Cw of j ，
(5) Calculating the average weight coefficient according to the weight coefficients of all the cows in the sample set
Wherein h = N-y × N × 2, h >0, N is the total number of samples, and y is the ratio of the maximum value to the minimum value to be removed;
(6) Calculating a cattle weight estimation value W through the measured pixel volume and the average weight coefficient of each cattle j ，
The live cattle body ruler and weight measuring method based on machine vision is characterized in that the body ruler indexes comprise body height, chest width, abdomen height, abdomen width, ischium end width and body straight length.
According to the live cattle body ruler and weight measuring method based on machine vision, before weight measurement is carried out, the leg, tail and ox horn protrusions in the side view of the sample image are erased, only the head and the trunk of a cattle are reserved, and the protrusions are prevented from interfering area calculation.
The invention has the beneficial effects that: according to the invention, the body size and the weight of the cattle are automatically identified and calculated by taking the pictures of the cattle, so that the labor intensity can be reduced to the greatest extent. When the body size is measured, the coefficient between the pixel value and the measured value of the body size is obtained, the coefficient of each body size of the cattle is obtained by adopting a central tendency algorithm, the estimated value of each body size of the cattle is obtained by calculation, and the absolute value of the deviation is less than 5 percent, which shows that the method for estimating the body size of the live cattle has better accuracy and can be used for estimating the body size of the cattle.
When the weight is measured, the average weight coefficient of the cattle is obtained by obtaining the coefficient between the pixel volume and the actually measured weight through a concentration trend algorithm, the weight of the cattle can be estimated only by obtaining the pixel volume of the cattle, the calculation amount is greatly reduced, the deviation between the estimated weight value and the actually measured value of the cattle calculated by the method is less than 20kg, the weight estimation error requirement is met, the problem that the error of the existing formula method for the estimation of the weight of the cattle is large is solved, and the weight estimation method has reference value.
Drawings
FIG. 1 is a flow chart of the measurement of body size and weight of cattle according to the present invention.
Fig. 2 is a schematic layout diagram of a cow image acquisition channel device.
FIG. 3 is a diagram illustrating an automatic annotation method for image segmentation according to the present invention.
Fig. 4 is a schematic image diagram of the binarization process.
FIG. 5 is a schematic view of the main parts of the body ruler.
Fig. 6 is a schematic image diagram of the binarization processing for the measurement of the weight of the cattle.
Fig. 7 is a schematic front and top view of a slice.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
Example 1: the present embodiment provides a method for measuring the body size and weight of a live cow, and the overall flow of the method is shown in fig. 1, which mainly includes the following steps.
Step one, obtaining an image
Selecting N sample cows as a cow sample set, arranging photographic devices at the side and above a passage through which the cows must pass, and as shown in figure 2, automatically triggering a camera to take a picture by a computer service program connected with the photographic devices when the cows pass, and synchronously acquiring a side view and a top view which are respectively used as acquired images for data processing.
Step two, image processing
For the side-view and top-view images of the cattle, an image segmentation algorithm Onecut is adopted to label the background and the foreground of the image, and as shown in fig. 3, the cattle image is separated from the side-view image and the top-view image through a matting algorithm;
the side view image and the top view image are respectively subjected to binarization processing (the gray value of a pixel point on the image is set to be 0 or 255 so that the whole image is black and white), a sample image calculated by the body size is generated, and as shown in fig. 4, the image after binarization processing has clearer outline and can better display the characteristics of each part of the body of the cow.
Step three, body ruler measurement
(1) Based on the features of each part of the body of the cow in the side view image and the top view image after binarization, as shown in fig. 5, the pixel lengths of the height, the chest width, the abdomen height, the abdomen width, the width of the ischium end and the body length of the cow are extracted.
(2) The pixel length L of each position body ruler of the cow pi And the measured body scale value L ri Calculating to obtain the body ruler coefficient C of each part of the cattle i ，
Wherein i represents a body ruler index.
(3) Using the sample data of all cattle body sizes in the sample set and the body size coefficient C of each part i Calculating the average body size coefficient of each part of the cattle according to the concentration trend
In the formula: m = N-x × N × 2,m>0,N is the total number of samples, x is the ratio of the maximum and minimum data to be removed, and i is the body part.
(4) Pixel value L of each position body ruler obtained by measurement pi Average body-size coefficient with corresponding part
Calculating to obtain estimated value L of each position body ruler of the cattle i ，
For example: pixel value L of body length of cattle p1 Length L of measured body r1 Calculating to obtain the coefficient C of the straight length of the cattle body 1 ，
Respectively obtaining corresponding body straight length coefficients by using body straight length pixel values and measured body straight length data of a large number of sample cows, and calculating a body straight length average coefficient of the cows according to a centralized trend;
and multiplying the measured body straight length pixel value of the test cattle by the body straight length average coefficient to obtain the body straight length estimated value of the test cattle.
Step four, measuring the body weight
The body weight measurement is carried out by regarding the body (including the head and the trunk) of the cattle as an approximately irregular elliptic cylinder, namely the cattle is formed by superposing N approximately elliptic slices along the axial direction of the trunk. The section of a 1-pixel slice vertical to the trunk is regarded as an approximate ellipse, and the estimated weight value of the cattle is obtained by calculating the volume of the irregular elliptic cylinder with the thickness of 1 pixel and multiplying the volume by a coefficient. The method comprises the following specific steps:
(1) The leg, tail and horn parts of the cow are wiped off from the side view of the sample image after the binarization processing, and only the head and the trunk of the cow are kept as shown in figure 6. This step avoids the overhang interfering with the calculation of the elliptical area by removing the overhang from the image beyond the head and torso.
(2) The sample image of the cow was elliptically sliced in units of single pixels in a direction perpendicular to the torso axis (x-axis), as shown in detail in fig. 7.
(3) Respectively taking the length l1 of the long-axis pixel and the length l2 of the short-axis pixel of the slice at the same point on the X axis, and calculating the pixel area S of the complete slice k ，
Then the pixel volume V of a single slice is calculated according to the unit pixel thickness k ，V k ＝S k ×1。
(4) The total pixel of the cattle is obtained by accumulating the pixel volumes of all the single slicesVolume Wp j ，
In the formula: q is the total number of slices; k is a slice number; j is a cattle number;
(5) Obtaining the pixel volume Wp of each cow according to the actually measured weight Wrj j And measured body weight Wr thereof j Coefficient Cw of j ，
(6) Calculating the average weight coefficient of all cattle in the sample set
Wherein h = N-y × N × 2,h>0,N is the total number of samples, and y is the ratio of the maximum and minimum data to be discarded.
(7) Calculating the weight estimated value W of the cattle by multiplying the measured pixel volume of each cattle by the average weight coefficient of the cattle j ，
Example 2: in this embodiment, the method of the present invention is used to measure the body scales of a cow, measure each body scale, compare the estimated value of the body scale with the measured value of the body weight of the cow, and calculate the deviation value between the estimated value and the measured value. Since the body size indexes are more, the body height value, the chest circumference and the abdominal circumference are used as the body size indexes to verify the effectiveness of the body size measuring method.
Selecting 15 cows as test cows, respectively measuring the body height, chest circumference and abdomen circumference of each cow, respectively calculating coefficients for the cows with the serial numbers of 1-10, and obtaining average coefficients, as shown in table 1.
TABLE 1 body ruler actual measurement data
Then, the body height, chest circumference and abdomen circumference of the cows of the serial numbers 11 to 15 were calculated from the average coefficient and the pixel value by using the average coefficient, and the deviation from the measured value was calculated as shown in table 2.
TABLE 2 body ruler estimate data
As can be seen from the table 2, the absolute values of the deviations between the estimated values of the body height, the chest circumference and the abdomen circumference obtained by the method and the corresponding measured values are all lower than 5%, which shows that the method of the invention has higher accuracy and meets the requirement of the body size estimation accuracy.
Example 3: in this embodiment, the method of the present invention is used to measure the body weight of a cow, and meanwhile, the body weight of the cow is estimated by using a formula method, and the estimated values of the body weight of the cow and the body weight of the cow are compared with the actual body weight value of the cow, so as to calculate the deviation value of the body weight of the cow and the body weight of the cow.
In addition, 15 cows were selected as test cows, the weight, body lean length and chest circumference of each cow were measured, and the body weight of the cow was estimated according to the formula = (square of chest circumference × body lean length) ÷ 10800, and the results are shown in table 3.
TABLE 3 results of body weight estimation of live cattle by formula method
As can be seen from Table 3, the deviation value of the cattle weight estimated by the formula method is different from the actually measured cattle weight, and the error is obviously larger. The deviation of the live cattle weight estimation within 20kg has reference value, so that the error is obviously larger from the result estimated by a formula method, and the reference value is lost.
In this embodiment, the weight of 15 cattle is estimated by using the weight measurement method of the present invention, the pixel volume of 10 cattle numbered 1-10 in table 3 is calculated, then the weight coefficient of each cattle is obtained, and the average weight coefficient of the cattle is calculated according to the concentration trend, and the result is shown in table 4.
TABLE 4 calculation of the weight average coefficient of live cattle according to the method of the present invention
Estimated body weight values for cattle nos. 11-15 in Table 3 were then calculated using the average body weight coefficients derived in Table 4, and the results are shown in Table 5.
TABLE 5 live cattle weight measurement results according to the method of the present invention
As can be seen from the table 5, the weight deviation values of the live cattle estimated by the method are within +/-20 kg, so that the method meets the requirement of weight estimation errors, can realize estimation and measurement of the weight of the live cattle, and has reference value.
Claims (3)
1. A live cattle body ruler weight measuring method based on machine vision is characterized in that: the method comprises the following steps:
1. image acquisition: selecting N sample cows as a cow sample set, and measuring the actual measurement weight and each position body ruler value of each cow; respectively arranging image acquisition devices right in front of and right above each cow, and synchronously acquiring a side view and a top view of the cow as acquired images;
2. image processing: marking the background and the foreground of the collected image by adopting an image segmentation algorithm, and segmenting the image of the cow from the background to be used as a basic image; respectively carrying out binarization processing on the basic images of the side view and the top view to obtain side view and top view sample images;
3. and (3) calculating the body size:
(1) Root of herbaceous plantsExtracting the pixel volume scale value L of each part of the cattle according to the characteristics of each part of the cattle body in the sample image pi ；
(2) The pixel volume scale value L of each part of the cattle pi And the measured body scale value L ri Calculating to obtain the body ruler coefficient C of each part of the cattle i ，
(3) According to the body size coefficient C of all the cattle parts in the sample set i Calculating the average coefficient of body size of each part of all the cows
In the formula: m = N-x × N × 2,m>0,N is the total number of samples, x is the data ratio of the maximum value to the minimum value to be removed, and i is the body part;
(4) Pixel value L of each position body ruler obtained by measurement pi Average body-size coefficient with corresponding part
Calculating to obtain estimated value L of each position body ruler of the cattle i ，
4. Calculating the weight:
(1) Elliptical slicing of a sample image of a cow in units of a single pixel in a direction perpendicular to a torso axis X-axis in a side view of the sample image;
(2) Respectively taking the length l1 of the long-axis pixel and the length l2 of the short-axis pixel of the slice at the same point on the X axis, and calculating the pixel area S of the complete slice k ，
Then the pixel volume V of a single slice is calculated according to the unit pixel thickness k ，V k ＝S k ×1；
(3) Accumulating all single slice imagesCalculating the pixel volume to obtain the total pixel volume Wp of the cattle j ，
In the formula: q is the total number of slices, k is the slice number, and j is the cattle number;
(4) According to the actual measurement weight W of each cow rj Obtaining the pixel volume Wp j And the measured body weight Wr j Coefficient Cw of j ，
(5) Calculating the average weight coefficient according to the weight coefficients of all the cows in the sample set
Wherein h = N-y × N × 2,h>0,N is the total number of samples, and y is the ratio of the maximum value to the minimum value to be removed;
(6) Calculating a cattle weight estimation value W through the measured pixel volume and the average weight coefficient of each cattle j ，
2. The live bovine body ruler weight measurement method based on machine vision according to claim 1, wherein: the body ruler indexes include body height, chest width, abdomen height, abdomen width, ischium width and body length.
3. The live bovine body ruler weight measurement method based on machine vision according to claim 1, wherein: before the weight measurement was performed, the leg, tail and horn protrusions in the side view of the sample image were erased, leaving only the head and torso of the cow, avoiding protrusions interfering with the area calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505378.7A CN113344960B (en) | 2021-05-10 | 2021-05-10 | Live cattle body ruler weight measuring method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110505378.7A CN113344960B (en) | 2021-05-10 | 2021-05-10 | Live cattle body ruler weight measuring method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344960A CN113344960A (en) | 2021-09-03 |
| CN113344960B true CN113344960B (en) | 2022-11-15 |
Family
ID=77470393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110505378.7A Active CN113344960B (en) | 2021-05-10 | 2021-05-10 | Live cattle body ruler weight measuring method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344960B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115396576B (en) * | 2022-08-24 | 2023-08-08 | 南京农业大学 | Device and method for automatically measuring sheep body ruler from side view and overlook double-view images |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110426112A (en) * | 2019-07-04 | 2019-11-08 | 平安科技（深圳）有限公司 | Live pig weight measuring method and device |
| CN110728259A (en) * | 2019-10-23 | 2020-01-24 | 南京农业大学 | Chicken group weight monitoring system based on depth image |
| CN112417378A (en) * | 2020-12-10 | 2021-02-26 | 常州大学 | Eriocheir sinensis quality estimation method based on unmanned aerial vehicle image processing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7399220B2 (en) * | 2002-08-02 | 2008-07-15 | Kriesel Marshall S | Apparatus and methods for the volumetric and dimensional measurement of livestock |
-
2021
- 2021-05-10 CN CN202110505378.7A patent/CN113344960B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110426112A (en) * | 2019-07-04 | 2019-11-08 | 平安科技（深圳）有限公司 | Live pig weight measuring method and device |
| CN110728259A (en) * | 2019-10-23 | 2020-01-24 | 南京农业大学 | Chicken group weight monitoring system based on depth image |
| CN112417378A (en) * | 2020-12-10 | 2021-02-26 | 常州大学 | Eriocheir sinensis quality estimation method based on unmanned aerial vehicle image processing |
Non-Patent Citations (4)
| Title |
|---|
| A novel automated system to acquire biometric and morphological measurements and predict body weight of pigs via 3D computer vision;Arthur F A Fernandes;《Journal of Animal Science》;20190131;第97卷(第1期);全文 * |
| 基于双目视觉及Mask RCNN的牛体尺无接触测量;李琦等;《黑龙江畜牧兽医》;20200620(第12期);全文 * |
| 基于图像的肉羊生长参数实时无接触监测方法;张丽娜等;《农业工程学报》;20171223(第24期);全文 * |
| 种猪体重三维预估模型的研究;付为森等;《农业工程学报》;20061230;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344960A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shuai et al. | Research on 3D surface reconstruction and body size measurement of pigs based on multi-view RGB-D cameras | |
| EP3261581B1 (en) | Improved method and relevant apparatus for the determination of the body condition score, body weight and state of fertility | |
| US9311556B2 (en) | Image analysis for making animal measurements including 3-D image analysis | |
| US20130064432A1 (en) | Image analysis for making animal measurements | |
| CA2723452C (en) | Systems, methods and devices for use in assessing carcass grading | |
| CN113344960B (en) | Live cattle body ruler weight measuring method based on machine vision | |
| US20160203604A1 (en) | Method for automatic detection of anatomical landmarks in volumetric data | |
| CN109636779B (en) | Method, apparatus and storage medium for recognizing integrated ruler of poultry body | |
| JP7062277B2 (en) | Cow body condition score evaluation device, evaluation method and evaluation program | |
| EP3127088B1 (en) | An arrangement and method to determine a body condition score of an animal | |
| CN112258651B (en) | Three-dimensional reconstruction method for dairy cow body surface point cloud under shielding condition | |
| CN111374712B (en) | Ultrasonic imaging method and ultrasonic imaging equipment | |
| CN109754401B (en) | Online measuring device and method for burrs at edge of lithium battery pole piece | |
| US8135179B2 (en) | Systems, methods and devices for use in assessing fat and muscle depth | |
| AU2016327051A1 (en) | Image analysis for making animal measurements including 3-D image analysis | |
| Yu et al. | Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera | |
| Imamura et al. | Automatic evaluation of cow's body-condition-score using 3D camera | |
| CN112288793A (en) | Livestock individual backfat detection method and device, electronic equipment and storage medium | |
| CN101052306A (en) | Data acquisition for sorting and qualitative and quantitive measurement to body of lovestock slaughtered | |
| Lynn et al. | Estimating body condition score of cows from images with the newly developed approach | |
| CN110415246B (en) | Analysis method of abdomen fat component | |
| Bercovich et al. | Automatic cow's body condition scoring | |
| CN110728708B (en) | Machine vision-based cattle body ruler measurement method | |
| WO2023133929A1 (en) | Ultrasound-based human tissue symmetry detection and analysis method | |
| US8472675B2 (en) | Systems, methods and devices for use in filter-based assessment of carcass grading |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |