Animal body condition scoring system and method

Through depth image acquisition and image information processing, the body condition score value of dairy cows is automatically calculated, which solves the problem of great influence of human subjective factors in the prior art, and achieves efficient and accurate body condition scores of dairy cows.

CN114821400BActive Publication Date: 2024-11-15YINCHUAN AOTOSO INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210361831.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-07
Publication Date
2024-11-15
Estimated Expiration
2042-04-07

AI Technical Summary

Technical Problem

The existing cow body condition scoring methods are greatly affected by human subjective factors, resulting in large scoring errors and excessive time.

Method used

The depth image acquisition module is used to obtain the depth image from the back of the cow. By extracting image information of key parts and reference parts, the reference cube and actual volume values ​​are constructed, and the body condition score values ​​are calculated using formulas to reduce manual intervention.

Benefits of technology

It realizes automation of cow body condition scores, reduces manual errors, and improves scoring efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114821400B_ABST
    Figure CN114821400B_ABST
Patent Text Reader

Abstract

An animal body condition scoring system includes a depth image acquisition module and a body condition scoring module; the depth image acquisition module is used to acquire a back depth image reflecting the back contour of the animal from above the animal to be tested, and provide the back depth image to the body condition scoring module; the body condition scoring module is used to extract image information of key parts reflecting the fatness and thinness of the animal and image information of reference parts from the acquired back depth image; the reference fat and thin volume value is calculated and the actual fat and thin volume value is integrated according to the extracted image information of the key parts and the image information of the reference parts; the reference fat and thin volume value and the actual fat and thin volume value are multiplied by a coefficient after being ratioed to obtain the animal's body condition score value BCS. The present invention also provides an animal body condition scoring method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field:

[0001] The present invention relates to the technical field of animal health monitoring, and in particular to an animal body condition scoring system and method. Background technology:

[0002] The body condition scoring of animals is also called fatness assessment, which basically reflects the amount of fat deposited in the animal's body, and thus reflects whether the animal meets the requirements for feeding over a period of time, so as to adjust the feeding method. For example, for dairy cows, feeding practice and scientific experiments have proved that the body condition of cows will affect potential or acute postpartum complications, milk production during lactation, and reproductive efficiency. In the process of dairy cow feeding, appropriate body condition scoring at different stages can help breeders better understand the nutritional status and physical condition of dairy cows and the problems encountered in the feeding and management process, so as to take relevant measures to solve the problems in a timely manner and better improve the feeding level of dairy cows.

[0003] Body condition scoring is a special method for evaluating the amount of fat deposited in dairy cows. This method has now become an important indicator for evaluating the production capacity of the herd, inspecting and evaluating the feeding level of the cattle farm, and has now become an indispensable part of cattle farm feeding management. The body condition of dairy cows refers to the fat content or energy reserve level of dairy cows. The purpose of body condition scoring is to keep dairy cows in a good weight state, to identify the problems of dairy cows at different growth and production stages, and the factors that may affect dairy cows due to fluctuations in body condition.

[0004] At present, most of the body condition scores of dairy cows are given by professionally trained scorers with relevant scoring experience by observing and analyzing the relevant parts of the dairy cows. The scores are given on a 5-point scale, with low scores indicating thinness and high scores indicating obesity, with 0.25 as the scoring unit. The traditional method is too time-consuming and is more affected by the subjective factors of the scorers, resulting in large errors. Summary of the invention:

[0005] In view of this, it is necessary to provide an animal body condition scoring system that can avoid scoring errors caused by human subjective factors.

[0006] It is also necessary to provide an animal body condition scoring method that can avoid scoring errors caused by human subjective factors.

[0007] An animal body condition scoring system comprises a depth image acquisition module and a body condition scoring module; the depth image acquisition module is used to acquire a back depth image reflecting the back contour of the animal from above the animal to be tested, and provide the back depth image to the body condition scoring module;

[0008] The body condition scoring module is used to extract image information of key parts reflecting the fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and the reference parts, and three-dimensional coordinate points corresponding to each pixel information; according to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing a plane is obtained according to a first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information; according to the extracted image information of the reference part, a height reference feature point information is obtained according to a second extraction rule, and the height reference feature point information includes pixel information corresponding to the height reference feature point and three-dimensional coordinate points corresponding to the pixel information; according to the height reference feature point information, the plane feature point information and a preset height value, a reference cube reflecting the fatness and thinness of the animal's back is constructed, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite, and the height reference feature point is located in the upper surface of the reference cube; the volume of the reference cube is calculated according to the plane feature point and the preset height value, and the calculated volume value is used as the reference fatness and thinness volume value V whole ; According to the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube, the relative height value from each pixel in the target image area to the lower surface of the reference cube is calculated; the volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal reality ; Substitute the baseline fat-lean volume value and the actual fat-lean volume value into formula 1 to calculate and obtain the animal's body condition score (BCS);

[0009]

[0010] Wherein, δ in Formula 1 is the correction coefficient.

[0011] A method for scoring animal body condition, comprising the following steps:

[0012] A back depth image reflecting the back contour of the animal is obtained from above the animal to be tested using a depth camera;

[0013] Extracting image information of key parts reflecting fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and reference parts, and three-dimensional coordinate points corresponding to each pixel information;

[0014] According to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing the plane is obtained according to the first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information;

[0015] According to the extracted image information of the reference part, a height reference feature point information is obtained according to the second extraction rule, the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information;

[0016] According to the height reference feature point information, the plane feature point information and the preset height value, a reference cube reflecting the fatness of the animal's back is constructed, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite to each other, and the height reference feature point is located in the upper surface of the reference cube;

[0017] The volume of the reference cube is calculated according to the plane feature points and the preset height value, and the calculated volume value is used as the reference fat-thin volume value V whole ;

[0018] Calculate the relative height value of each pixel in the target image area to the lower surface of the reference cube based on the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube;

[0019] The volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal. reality ;

[0020] Substitute the baseline fat-lean volume value and the actual fat-lean volume value into Formula 1 to calculate and obtain the animal's body condition score (BCS);

[0021]

[0022] Wherein, δ in Formula 1 is the correction coefficient.

[0023] In the above-mentioned animal body condition scoring system and method, a back depth image reflecting the back contour of the animal to be tested is obtained from above, image information of key parts reflecting the fatness and thinness of the animal and image information of reference parts are extracted from the back depth image, a predetermined number of plane feature point information for constructing a plane is obtained based on the extracted image information of the key parts, a height reference feature point information is obtained based on the extracted image information of the reference part, and a reference cube reflecting the fatness and thinness of the animal's back is constructed based on the height reference feature point information, the plane feature point information and the preset height value, and the volume of the reference cube is calculated; according to the target enclosed by the plane feature points The pixel information in the image area and the three-dimensional coordinate points corresponding to the pixel information and the three-dimensional coordinate points of the lower surface of the reference cube are used to calculate the relative height value from each pixel in the target image area to the lower surface of the reference cube, and the volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and lean volume reflecting the fatness and thinness of the animal. The actual fat and lean volume value is ratioed with the benchmark fat and lean volume value and then multiplied by the correction coefficient to obtain the animal's body condition score BCS, thereby realizing the animal's body condition scoring without manual observation and analysis. Description of the drawings:

[0024] Figure 1 Schematic diagram of the functional modules of a cattle body condition scoring system according to a preferred embodiment.

[0025] Figure 2 for Figure 1 Schematic diagram of the functional modules of the body condition scoring module.

[0026] Figure 3 The diagram is a schematic diagram for determining points 1 to 7 of the depth image of the cow's back.

[0027] Figure 4 This is a volume diagram on the left side showing the key fat and lean parts of a dairy cow.

[0028] Figure 5 This is a volume diagram on the right side of the key parts of the cow's fat and thin.

[0029] Figure 6 The present invention is a flow chart of a method for scoring animal body condition in a preferred embodiment.

[0030] In the figure: an animal body condition scoring system 10, a depth image acquisition module 20, a body condition scoring module 30, an image information extraction unit 31, a first extraction unit 32, a second extraction unit 33, a reference fat and thin volume calculation unit 34, an actual fat and thin volume calculation unit 35, a body condition score calculation unit 36, a lookup information table generation unit 37, a body condition score value output unit 38, an animal identification device 40, and animal body condition scoring method steps S300 to S314. Specific implementation method:

[0031] The animal body condition scoring system provided by the present invention obtains an ideal baseline fat and lean volume value of the animal's back and an actual back volume value by analyzing the depth image of the animal's back, and obtains the animal's body condition score by multiplying the actual fat and lean volume value by a coefficient to achieve animal body condition scoring.

[0032] Please also see Figure 1 The animal body condition scoring system 10 includes a depth image acquisition module 20 and a body condition scoring module 30; the depth image acquisition module 20 is used to acquire a back depth image reflecting the back contour of the animal from above the animal to be tested, and provide the back depth image to the body condition scoring module 30. Among them, the depth image acquisition module 20 can be a depth camera. The depth image can accurately know the spatial distance of each pixel in the image, so that the three-dimensional spatial coordinates of each point in the image can be obtained by adding the (x, y) coordinates of each pixel in the two-dimensional image.

[0033] The body condition scoring module 30 is used to extract the image information of the key parts reflecting the fatness and thinness of the animal and the image information of the reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and the reference parts, and the three-dimensional coordinate points corresponding to each pixel information; according to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing a plane is obtained according to the first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and the three-dimensional coordinate points corresponding to the pixel information; according to the extracted image information of the reference part, a height reference feature point information is obtained according to the second extraction rule, and the height reference feature point information includes pixel information corresponding to the height reference feature point and the three-dimensional coordinate points corresponding to the pixel information; according to the height reference feature point information, the plane feature point information and the preset height value, a reference cube reflecting the fatness and thinness of the animal's back is constructed, wherein the upper surface of the reference cube has the same shape and size as the lower surface, and the upper surface is parallel to the lower surface and directly faces, and the height reference feature point is located in the upper surface of the reference cube; for example, the animal is a dairy cow, please also check Figures 3 to 5The key parts are the hip angle, tail root and hip bone of the animal. In the hip angle image information, the two hip angle edges are marked as point 4 and point 6, and the endpoint pixel information of point 4 and point 6 are obtained from the hip angle image information according to the marked points 4 and 6; in the tail root image information, the tail root edge is marked as point 5, and the endpoint pixel information of point 5 is obtained from the tail root image information according to the marked point 5; point 1 and point 3 are marked in the two opposite edges in the hip bone image information, the distance between point 1 and point 3 is the longest, and the endpoint pixel information of point 1 and point 3 are obtained from the hip bone image information according to the marked points 1 and 3, and the endpoint pixel information of point 1 and point 3 are determined in the back depth image according to the length between the endpoint pixel information of point 1 and the endpoint pixel information of point 3 according to the requirements of an equilateral triangle, and the endpoint pixel information of point 2 is far away from the endpoint pixel information of point 5; the above endpoint pixel information of points 1 to 6 is used as the plane feature point information. The reference part is the hip tubercle, point 7 is marked in the hip tubercle image information, and the endpoint pixel information of point 7 is obtained from the hip tubercle image information based on the marked point 7, wherein point 7 is the point highest from the ground in the back depth image, and the endpoint pixel information of point 7 is used as the height reference feature point information; with the height reference feature point information as the height reference point, the first plane (plane ABCDFE) is determined according to the plane feature point information and a preset height value (the preset height value is determined according to different animals, for example, in this embodiment, the animal is a cow, and the preset height value is set to 20 cm), and the first plane has a lower mapping feature point corresponding to the plane feature point; the second plane is determined according to the plane feature point information and the height reference feature point information, the second plane has an upper mapping feature point corresponding to the plane feature point, and the height reference feature point is located in the second plane, the first plane is parallel to the second plane, and the distance between the first plane and the second plane is the preset height value.

[0034] The body condition scoring module 30 calculates the volume of the reference cube according to the plane feature points and the preset height value, and uses the calculated volume value as the reference fat-lean volume value V whole ; According to the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube, the relative height value from each pixel in the target image area to the lower surface of the reference cube is calculated; the volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal reality , put the baseline fat-lean volume value and the actual fat-lean volume value into formula 1 to calculate and obtain the animal's body condition score (BCS);

[0035]

[0036] Among them, δ in Formula 1 is the correction coefficient, and δ is an empirical value determined by the staff in actual production based on actual production experience.

[0037] Furthermore, the animal body condition scoring system 10 also includes an animal identification device 40,

[0038] The animal identification device 40 is used to obtain the identification information carried by the animal and provide the identification information to the body condition scoring module; the body condition scoring module 30 is also used to establish a corresponding relationship based on the identification information and the back depth image to form a search information table; the body condition scoring module 30 is also used to display the obtained animal's body condition score value BCS and the corresponding identification information based on the search information table.

[0039] The body condition scoring module 30 may be a single chip microcomputer or a microcomputer running a set of computer applications, wherein the computer applications are used to complete the body condition scoring function of the animal. After the body condition scoring module runs the computer application, the following functional modules are generated. Please also refer to Figure 2 :

[0040] The body condition scoring module 30 includes an image information extraction unit 31, a first extraction unit 32, a second extraction unit 33, a reference fat and thin volume calculation unit 34, an actual fat and thin volume calculation unit 35, a body condition score calculation unit 36, a lookup information table generation unit 37 and a body condition score value output unit 38;

[0041] The image information extraction unit 31 is used to extract the image information of the key parts reflecting the fatness and thinness of the animal and the image information of the reference parts from the acquired back depth image; wherein the image information includes the pixel information reflecting the key parts and the reference parts, and the three-dimensional coordinate points corresponding to the pixel information;

[0042] The first extraction unit 32 is used to obtain a predetermined number of plane feature point information for constructing a plane according to the first extraction rule based on the image information of the extracted key parts, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information;

[0043] The second extraction unit 33 is used to obtain a height reference feature point information according to the extracted image information of the reference part according to the second extraction rule, and the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information;

[0044] The reference fat-thin volume calculation unit 34 is used to construct a reference cube reflecting the fatness of the animal's back according to the height reference feature point information, the plane feature point information and the preset height value, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite to each other, and the height reference feature point is located in the upper surface of the reference cube; the volume of the reference cube is calculated according to the plane feature point and the preset height value, and the calculated volume value is used as the reference fat-thin volume value V whole ;For example, Figure 4 , map 20cm downward in the z-axis direction where points 2, 3, 4, and 5 are located, and get the corresponding points A, B, C, and D. In this way, an irregular cube on the left side of the cow can be constructed, and the volume is defined as V1; points ABCD form the lower base S1 of V1, so V1=S1*20; Figure 5 It is the right side spatial map of the key points of the depth image of the cow's back. According to the key points 1, 2, 5, and 6, the irregular cube of the right side of the cow is constructed in the same way as above, and the volume is defined as V2. The four points of AEFD form the lower bottom surface S2 of V2, and V2 = S2*20; according to the key points 1, 2, 3, 4, 5, and 6, the irregular cube of the cow's back is constructed in the same way as above, and the volume is defined as V whole =V1+V2.

[0045] The actual fat-lean volume calculation unit 35 is used to calculate the relative height value of each pixel in the target image area to the lower surface of the reference cube based on the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube; calculate the volume value corresponding to each pixel in the target image area according to the relative height value, and integrate the volume of each pixel in the target image area to obtain the actual fat-lean volume value V reflecting the fatness and thinness of the animal. reality For example, the depth camera takes a depth image of the cow's back, obtains the RGBD data of the target pixel point, knows the three-dimensional spatial coordinates of each point, restores the real fat condition of the cow's back, and converts the actual fat condition of the cow's back into the actual fat and lean volume value V reality To reflect, the actual fat and lean volume value V reality The corresponding cow back is divided into the left volume and the right volume, defined as V left and V right , and using the idea of ​​calculus, V left , V rightThe volume is assumed to be composed of n small cuboids. By obtaining the RGBD data of the target pixel point and knowing the three-dimensional spatial coordinates of each point, the length Ln, width Wn, and height Hn of the small cuboid can be obtained, and the volume Vn = Ln*Wn*Hn can be calculated. Then, the left and right volumes are calculated using formula 2, and the sum of the left and right volumes is obtained to obtain the actual fat and thin volume value V reality ,

[0046]

[0047] The body condition score calculation unit 36 ​​is used to bring the reference fat-lean volume value and the actual fat-lean volume value into the pre-stored formula 1 for calculation to obtain the body condition score value BCS of the animal;

[0048]

[0049] Among them, δ in Formula 1 is the correction coefficient, and δ is an empirical value determined by the staff in actual production based on actual production experience.

[0050] The lookup information table generating unit 37 is used to establish a corresponding relationship according to the identification information and the back depth image to form a lookup information table.

[0051] The body condition score value output unit 38 is used to display or provide the obtained animal's body condition score value BCS and corresponding identification information to a third-party application software according to the search information table, so as to be displayed using the third-party application software. For example, the body condition score value output unit 38 can provide the animal's body condition score value BCS and corresponding identification information to a cloud platform or a mobile phone APP.

[0052] In other implementations, the above functional modules generated by the body condition scoring module may also be implemented through hardware logic circuits and embedded codes.

[0053] Furthermore, the present invention also provides a method for scoring animal body condition, see Figure 6 , the animal body condition scoring method comprises the following steps:

[0054] Step S300: using a depth camera to obtain a back depth image reflecting the back contour of the animal from above the animal to be tested.

[0055] Step S302, extracting image information of key parts reflecting fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and reference parts, and three-dimensional coordinate points corresponding to each pixel information;

[0056] Step S304, according to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing the plane is obtained according to the first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information. The first extraction rule is: determine the endpoint pixel information of each key part according to the edge of each key part, and record each endpoint pixel information as plane feature point information.

[0057] Step S306, based on the extracted image information of the reference part, obtain a height reference feature point information according to the second extraction rule, the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information; wherein the second extraction rule is: select the highest pixel information from the pixel information of the reference part from the ground, and use the selected highest pixel information as the height reference feature point information.

[0058] Step S308, constructing a reference cube reflecting the fatness of the animal's back based on the height reference feature point information, the plane feature point information and the preset height value, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite to each other, and the height reference feature point is located on the upper surface of the reference cube.

[0059] Step S310, calculating the volume of the reference cube according to the plane feature points and the preset height value, and using the calculated volume value as the reference fat-thin volume value V whole .

[0060] Step S312, based on the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube, calculate the relative height value of each pixel in the target image area to the lower surface of the reference cube, calculate the volume value corresponding to each pixel in the target image area based on the relative height value, and integrate the volume of each pixel in the target image area to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal reality .

[0061] Step S314, the reference fat-lean volume value and the actual fat-lean volume value are put into formula 1 to calculate to obtain the body condition score value BCS of the animal;

[0062]

[0063] Among them, δ in Formula 1 is the correction coefficient, and δ is an empirical value determined by the staff in actual production based on actual production experience.

[0064] Among them, step S304 is specifically as follows: the key parts are the hip angle, tail root, and hip bone of the animal. In the hip angle image information, the two hip angle edges are marked as point 4 and point 6, and the endpoint pixel information of point 4 and point 6 are obtained from the hip angle image information according to the marked points 4 and 6; in the tail root image information, the tail root edge is marked as point 5, and the endpoint pixel information of point 5 is obtained from the tail root image information according to the marked point 5; point 1 and point 3 are marked in the two opposite edges in the hip bone image information, the distance between point 1 and point 3 is the longest, and the endpoint pixel information of point 1 and point 3 are obtained from the hip bone image information according to the marked points 1 and 3, and the endpoint pixel information of point 2 and point 3 are determined in the back depth image according to the length between the endpoint pixel information 1 and the endpoint pixel information 3 according to the requirements of an equilateral triangle, and the endpoint pixel information of point 2 is far away from the endpoint pixel information of point 5; the above-mentioned endpoint pixel information of points 1 to 6 is used as the plane feature point information.

[0065] Among them, step S306 is specifically as follows: the reference part is the hip nodule, point 7 is marked in the hip nodule image information, and the endpoint pixel information of point 7 is obtained from the hip nodule image information based on the marked point 7, wherein point 7 is the highest point from the ground in the back depth image, and the endpoint pixel information of point 7 is used as the height reference feature point information.

[0066] Among them, step S312 is specifically as follows: using the height reference feature point information as the height reference point, determining the first plane according to the plane feature point information and the preset height value, and the first plane has a lower mapping feature point corresponding to the plane feature point; determining the second plane according to the plane feature point information and the height reference feature point information, the second plane has an upper mapping feature point corresponding to the plane feature point, and the height reference feature point is located in the second plane, the first plane is parallel to the second plane, and the distance between the first plane and the second plane is the preset height value.

[0067] Furthermore, the above-mentioned animal body condition scoring method further comprises the following steps: obtaining identification information carried by the animal;

[0068] Establishing a correspondence between the identification information and the back depth image;

[0069] A corresponding relationship is established based on the identification information and the back depth image, and the obtained animal body condition score BCS and the corresponding identification information are displayed.

[0070] In the above-mentioned animal body condition scoring system 10 and method, a back depth image reflecting the back contour of the animal to be tested is obtained from above, image information of key parts reflecting the fatness and thinness of the animal and image information of reference parts are extracted from the back depth image, a predetermined number of plane feature point information for constructing a plane is obtained based on the extracted image information of the key parts, a height reference feature point information is obtained based on the extracted image information of the reference parts, and a reference cube reflecting the fatness and thinness of the animal's back is constructed based on the height reference feature point information, the plane feature point information and the preset height value, and the volume of the reference cube is calculated; the target cube enclosed by the plane feature points is calculated. The pixel information in the target image area and the three-dimensional coordinate points corresponding to the pixel information and the three-dimensional coordinate points of the lower surface of the reference cube are calculated, and the relative height value from each pixel in the target image area to the lower surface of the reference cube is calculated, and the volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and lean volume reflecting the fatness and thinness of the animal, and the actual fat and lean volume value is multiplied by the correction coefficient δ after being ratioed with the reference fat and lean volume value to obtain the animal's body condition score value BCS, so that the animal's body condition score can be achieved without manual observation and analysis. δ is an empirical value determined by the staff in actual production based on actual production experience, for example, δ is equal to 5 points mentioned in the background technology of this application, and in other embodiments, δ can also be equal to 5 points multiplied by a conventional coefficient. Animal body condition scoring is to evaluate the fatness of the animal, which can reflect the basic situation of fat deposited in the animal. By understanding the body condition scores of groups and individuals, the feeding effect of this period can be studied and evaluated, providing an important basis for the feeding measures in the next stage, adjusting the recent daily diet formula and feeding amount. In addition, body condition scoring is also an auxiliary means of animal health examination.

Claims

1. An animal body condition scoring system, Features: Including depth image acquisition module and body condition scoring module; The depth image acquisition module is used to acquire a back depth image reflecting the back contour of the animal from above the animal to be tested, and provide the back depth image to the body condition scoring module; The body condition scoring module is used to extract image information of key parts reflecting the fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and the reference parts, and three-dimensional coordinate points corresponding to each pixel information; according to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing a plane is obtained according to a first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information; according to the extracted image information of the reference part, a height reference feature point information is obtained according to a second extraction rule, and the height reference feature point information includes pixel information corresponding to the height reference feature point and three-dimensional coordinate points corresponding to the pixel information; according to the height reference feature point information, the plane feature point information and a preset height value, a reference cube reflecting the fatness and thinness of the animal's back is constructed, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite, and the height reference feature point is located in the upper surface of the reference cube; the volume of the reference cube is calculated according to the plane feature point and the preset height value, and the calculated volume value is used as the reference fatness and thinness volume value V whole ; According to the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube, the relative height value from each pixel in the target image area to the lower surface of the reference cube is calculated; the volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal reality ; Substitute the baseline fat-lean volume value and the actual fat-lean volume value into formula 1 to obtain the animal's body condition score (BCS); Wherein, δ in Formula 1 is the correction coefficient.

2. The animal body condition scoring system according to claim 1, Features: The body condition scoring module includes an image information extraction unit, a first extraction unit, a second extraction unit, a reference fat and thin volume calculation unit, an actual fat and thin volume calculation unit and a body condition score calculation unit; An image information extraction unit is used to extract image information of key parts reflecting fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and reference parts, and three-dimensional coordinate points corresponding to the pixel information; A first extraction unit is used to obtain a predetermined number of plane feature point information for constructing a plane according to the extracted image information of the key parts and a first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and a three-dimensional coordinate point corresponding to the pixel information; A second extraction unit is used to obtain a height reference feature point information according to the extracted image information of the reference part and a second extraction rule, wherein the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information; The reference fat-thin volume calculation unit is used to construct a reference cube reflecting the fatness of the animal's back according to the height reference feature point information, the plane feature point information and the preset height value, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite to each other, and the height reference feature point is located in the upper surface of the reference cube; the volume of the reference cube is calculated according to the plane feature point and the preset height value, and the calculated volume value is used as the reference fat-thin volume value V whole ; The actual fat-lean volume calculation unit is used to calculate the relative height value of each pixel in the target image area to the lower surface of the reference cube according to the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube; calculate the volume value corresponding to each pixel in the target image area according to the relative height value, and integrate the volume of each pixel in the target image area to obtain the actual fat-lean volume value V reflecting the fatness and thinness of the animal reality ; A body condition score calculation unit is used to bring the reference fat-lean volume value and the actual fat-lean volume value into a pre-stored formula 1 for calculation to obtain the animal's body condition score value BCS; Wherein, δ in Formula 1 is the correction coefficient.

3. The animal body condition scoring system according to claim 1 or 2, Features: The animal body condition scoring system also includes an animal identification device, The animal identification device is used to obtain identification information carried by the animal and provide the identification information to the body condition scoring module; The body condition scoring module is also used to establish a corresponding relationship according to the identification information and the back depth image to form a search information table; the body condition scoring module is also used to display the obtained animal body condition score value BCS and the corresponding identification information according to the search information table.

4. The animal body condition scoring system according to claim 3, Features: The first extraction rule is: determine the endpoint pixel information of each key part according to the edge of each key part, and record each endpoint pixel information as plane feature point information; the second extraction rule is: select the highest pixel information from the ground from the pixel information of the reference part, and use the selected highest pixel information as the height reference feature point information.

5. A method for scoring animal body condition, The following steps are involved: Using a depth camera to obtain a back depth image reflecting the back contour of the animal from above the animal to be tested; Extracting image information of key parts reflecting fatness and thinness of the animal and image information of reference parts from the acquired back depth image; wherein the image information includes pixel information reflecting the key parts and reference parts, and three-dimensional coordinate points corresponding to each pixel information; According to the extracted image information of the key parts, a predetermined number of plane feature point information for constructing the plane is obtained according to the first extraction rule, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information; According to the extracted image information of the reference part, a height reference feature point information is obtained according to the second extraction rule, the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information; According to the height reference feature point information, the plane feature point information and the preset height value, a reference cube reflecting the fatness of the animal's back is constructed, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface and the lower surface are parallel and opposite to each other, and the height reference feature point is located in the upper surface of the reference cube; The volume of the reference cube is calculated according to the plane feature points and the preset height value, and the calculated volume value is used as the reference fat-thin volume value V whole ; Calculate the relative height value of each pixel in the target image area to the lower surface of the reference cube based on the pixel information in the target image area surrounded by the plane feature points, the three-dimensional coordinate points corresponding to the pixel information, and the three-dimensional coordinate points of the lower surface of the reference cube; The volume value corresponding to each pixel in the target image area is calculated according to the relative height value, and the volume of each pixel in the target image area is integrated to obtain the actual fat and thin volume value V reflecting the fatness and thinness of the animal. reality ; Substitute the baseline fat-lean volume value and the actual fat-lean volume value into Formula 1 to calculate and obtain the animal's body condition score (BCS); Wherein, δ in Formula 1 is the correction coefficient.

6. The animal body condition scoring method according to claim 5, It is characterized in that The first extraction rule is: determine the endpoint pixel information of each key part according to the edge of each key part, and record each endpoint pixel information as plane feature point information; the second extraction rule is: select the highest pixel information from the ground from the pixel information of the reference part, and use the selected highest pixel information as the height reference feature point information.

7. The animal body condition scoring method according to claim 6, It is characterized in that The step of "acquiring a predetermined number of plane feature point information for constructing a plane according to the first extraction rule based on the extracted image information of the key parts, wherein the plane feature point information includes pixel information corresponding to the plane feature point and three-dimensional coordinate points corresponding to the pixel information" is specifically: The key parts are the hip angle, tail root and hip bone of the animal. In the hip angle image information, the two hip angle edges are marked as point 4 and point 6, and the endpoint pixel information of point 4 and the endpoint pixel information of point 6 are obtained from the hip angle image information according to the marked point 4 and point 6; In the tail root image information, the edge of the tail root is marked as point 5, and the endpoint pixel information of point 5 is obtained from the tail root image information according to the marked point 5; Point 1 and point 3 are marked on two opposite edges in the hip bone image information, and the distance between point 1 and point 3 is the longest. The endpoint pixel information of point 1 and point 3 are obtained from the hip bone image information based on the marked points 1 and 3. The endpoint pixel information of point 1 and point 3 are determined in the back depth image based on the length between the endpoint pixel information of point 1 and the endpoint pixel information of point 3 and in accordance with the requirement of an equilateral triangle. The endpoint pixel information of point 2 is far away from the endpoint pixel information of point 5. The above endpoint pixel information of points 1 to 6 is used as plane feature point information.

8. The animal body condition scoring method according to claim 6 or 5, It is characterized in that The specific step of "according to the extracted image information of the reference part, a height reference feature point information is obtained according to the second extraction rule, the height reference feature point information includes pixel information corresponding to the height reference feature point and a three-dimensional coordinate point corresponding to the pixel information" is as follows: the reference part is the hip tubercle, point 7 is marked in the hip tubercle image information, and the endpoint pixel information of point 7 is obtained from the hip tubercle image information based on the marked point 7, wherein point 7 is the highest point from the ground in the back depth image, and the endpoint pixel information of point 7 is used as the height reference feature point information.

9. The animal body condition scoring method according to claim 8, It is characterized in that The specific step of "constructing a reference cube reflecting the fatness of the animal's back based on the height reference feature point information, the plane feature point information and the preset height value, wherein the upper surface and the lower surface of the reference cube have the same shape and size, and the upper surface is parallel to the lower surface and is opposite to each other, and the height reference feature point is located in the upper surface of the reference cube" is as follows: using the height reference feature point information as the height reference point, determining a first plane based on the plane feature point information and the preset height value, the first plane having a lower mapping feature point corresponding to the plane feature point; determining a second plane based on the plane feature point information and the height reference feature point information, the second plane having an upper mapping feature point corresponding to the plane feature point, and the height reference feature point is located in the second plane, the first plane is parallel to the second plane, and the distance between the first plane and the second plane is the preset height value.

10. The animal body condition scoring method according to claim 9, It is characterized in that The steps are also included: obtaining identification information carried by the animal; Establishing a correspondence between the identification information and the back depth image; A corresponding relationship is established based on the identification information and the back depth image, and the obtained animal body condition score BCS and the corresponding identification information are displayed.