Cattle evaluation device and cattle evaluation method

Abstract

To provide a cow evaluation apparatus and a cow evaluation method which can be applied to various sites of breeding.SOLUTION: A cow evaluation apparatus 100 acquires a two-dimensional photographed image 50 obtained by imaging a cow in a standing posture from substantially right behind, extracts a contour line 60 of the cow from the photographed image 50, decides a point 403a on a first curve part 63a that extends to the other crest part 61b side from an apex 62a being a point on a substantially center on the contour line 60 of one crest part 61a of the two crest parts 61a, 61b existing on left and right sides of an upper part of the contour line 60 and a point 404a on a second curve part 64a that extends to an opposite side to the first curve part 63a, specifies a point 406a where a straight line 424a that passes through a middle point 405a of a line segment 410a connecting the point 403a and the point 404a and is vertical to the line segment 410a intersects the crest part 61a, calculates an angle ω1 formed by a line segment 412a connecting the point 403a and a point 406a and a line segment 414a connecting the point 404a and the point 406a, and evaluates fleshiness of the cow from the calculated angle ω1.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present invention relates to a cattle evaluation device and a cattle evaluation method. [Background technology]

[0002] In order to evaluate the energy balance in the feeding management of cattle, the state of body fat (fleshiness) of cattle is evaluated. One index showing the state of body fat is the body condition score. Normally, the body condition score is judged by veterinarians or dairy experts, but because the judgement is made by humans, the judgment criteria become vague and the judgment varies. Meanwhile, there are known methods for evaluating a score indicating the body condition based on a three-dimensional image of an animal (e.g., Patent Document 1) and a method for evaluating a score indicating the body condition based on a two-dimensional image of an animal (e.g., Patent Document 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2012-510278 [Patent Document 2] European Patent No. 2027770 Summary of the Invention [Problem to be solved by the invention]

[0004] The evaluation method described in Patent Document 1 uses a three-dimensional image of the animal to calculate a score indicating the physical condition, so it is necessary to take images at a specific location where large-scale equipment is installed, and it is difficult to apply it to a variety of breeding sites. The evaluation method described in Patent Document 2 uses a two-dimensional image of the animal, but since it uses a two-dimensional image of the animal taken from above, it is necessary to take images at a specific location where equipment that can take images of the animal from above is installed, and like Patent Document 1, it is difficult to apply it to a variety of breeding sites.

[0005] The present invention has been made in consideration of the above problems, and has an object to provide a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites. [Means for solving the problem]

[0006] The cattle evaluation device of the present invention comprises an image acquisition unit that acquires a two-dimensional captured image of a cow in a standing position taken from approximately directly behind or approximately in front of the cow, an extraction unit that extracts the contour line of the cow from the captured image, a determination unit that determines a first point on a first curved portion extending from an approximately central point on the contour line of one of two peaks present on both the left and right sides of the upper part of the contour line to the other peak side and a second point on a second curved portion extending on the opposite side to the first curved portion, and a determination unit that connects the first point and the second point. a calculation unit that calculates at least one of the following: a length of a first line segment connecting a third point where a straight line passing through approximately the midpoint of the first line segment and approximately perpendicular to the first line segment intersects with one of the peaks, and the length of a second line segment connecting approximately the midpoint of the first line segment, and the ratio of the length of the first line segment to the length of the second line segment, and an angle formed by a third line segment connecting the first point and the third point, and a fourth line segment connecting the second point and the third point; and an evaluation unit that evaluates the meatiness of the cattle from the values ​​calculated by the calculation unit. Effect of the Invention

[0007] According to the present invention, it is possible to obtain a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram showing the configuration of a cattle evaluation device according to the first embodiment. [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of a control unit in the first embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of an image acquired by the image acquisition unit. [Figure 4] FIG. 4 is a diagram for explaining the process executed by the extraction unit. [Diagram 5]FIG. 5 is a diagram for explaining the process executed by the determination unit. [Figure 6] 6(a) and 6(b) are diagrams for explaining the process executed by the calculation unit in the first embodiment. [Figure 7] Figures 7(a) to 7(c) are images of cows with different body masses. [Figure 8] 8(a) to 8(c) are diagrams showing the relationship between the fleshiness of a cow and the angle ω1 calculated by the calculation unit. [Figure 9] FIG. 9 shows the results of an experiment investigating the correlation between the body condition score and the angles ω1, ω2, and the average values ​​of the angles ω1 and ω2 calculated by the calculation unit. [Figure 10] FIG. 10 is a block diagram showing the hardware configuration of the cow evaluation device according to the embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of a method for evaluating beef meatiness in the first embodiment. [Figure 12] 12(a) to 12(c) are diagrams showing other determination methods by the determination unit. [Figure 13] 13(a) and 13(b) are diagrams for explaining the process executed by the calculation unit in the second embodiment. [Figure 14] 14(a) to 14(c) are diagrams showing the relationship between the fleshiness of a cow and the lengths X1a and X2a calculated by the calculation unit. [Figure 15] FIG. 15 shows the results of an experiment investigating the correlation between the body condition score and the length X1a, the length X1b, and the average value of the lengths X1a and X1b calculated by the calculation unit. [Figure 16] FIG. 16 shows the results of an experiment investigating the correlation between the body condition score and the length X2a, the length X2b, and the average value of the length X2a and the length X2b calculated by the calculation unit. [Figure 17]FIG. 17 shows the results of an experiment investigating the correlation between the body condition score and the length ratio (X1a / X2a) of length X1 to length X2a, the length ratio (X1b / X2b) of length X1b to length X2b, and the average values ​​of the length ratios (X1a / X2a) and (X1b / X2b). [Figure 18] FIG. 18(a) is an image of a cow in an upright position captured from approximately directly behind, and FIG. 18(b) is an image of the cow in FIG. 18(a) captured from approximately the front. [Figure 19] FIGS. 19(a) and 19(b) are extracted images in which the contour lines of the cow are extracted from the captured images of FIGS. 18(a) and 18(b). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] First Embodiment A cow evaluation device 100 according to a first embodiment will be described below with reference to Figs. 1 to 12. Fig. 1 shows in a block diagram the configuration of the cow evaluation device 100 according to the first embodiment. Fig. 2 shows in a block diagram the functional configuration of a control unit 22. In this first embodiment, the evaluation device 100 is a portable information device carried and used by an operator. Examples of portable information devices include smartphones, tablet computers, PDAs (Personal Digital Assistants), and smart glasses. The evaluation device 100 has, for example, a telephone function, an email function, a communication function for connecting to the Internet, etc., and a data processing function for executing a program.

[0010] As shown in FIG. 1, the evaluation device 100 includes a display unit 12, an operation unit 14, a communication unit 16, an imaging unit 18, a storage unit 20, and a control unit 22.

[0011] The display unit 12 is a display device that displays images, various information, and operation input images such as touch operation buttons.

[0012] The operation unit 14 is a device such as a touch panel or a switch. The touch panel accepts information input in response to a worker's touch and transmits the accepted information to the control unit 22. The touch panel is incorporated in, for example, the display unit 12. Therefore, the touch panel accepts various information inputs in response to the worker's touch on the surface of the display unit 12. The switch is an operating member that accepts an operation on the evaluation device 100 from the worker and transmits the accepted information to the control unit 22.

[0013] The communication unit 16 is a communication interface that performs short-range wireless communication (e.g., NFC (Near Field Communication)) with other devices, and wireless communication (e.g., communication using a mobile phone line or a wireless LAN (Local Area Network)) with other devices connected to the network.

[0014] The imaging unit 18 is a device that captures images such as still images and videos. The imaging unit 18 captures images in response to an operator carrying the evaluation device 100 operating the operation unit 14. When evaluating the fleshiness of a cow, the operator uses the imaging unit 18 to capture an image of the cow in a standing position from approximately directly behind. Capturing an image from approximately directly behind means capturing an image in a range that captures the outline of the cow's left and right hip angles. Therefore, the operator captures an image from a position several meters (e.g., 1 m to 2 m) behind the cow so that the outline of the cow's left and right hip angles can be captured.

[0015] The memory unit 20 stores various information such as captured images of the cow, extracted images of the cow's contour lines, and evaluation results of the cow's body fatness.

[0016] The control unit 22 is a processing unit that controls each unit of the cow evaluation device 100. As shown in Fig. 2, the control unit 22 has an image acquisition unit 30, an extraction unit 32, a determination unit 38, a calculation unit 34, and an evaluation unit 36.

[0017] FIG. 3 shows an example of an image acquired by the image acquisition unit 30. As shown in FIG. 3, the image acquisition unit 30 acquires an image 50 of, for example, a cow in an upright position, captured from approximately directly behind the cow. The image 50 of the cow to be acquired may be an image captured by the imaging unit 18, or an image captured by another device and received by the communication unit 16. The image 50 of the cow to be acquired may be an image selected by the operator using the operation unit 14 from among those stored in the storage unit 20. The image acquisition unit 30 may display the acquired image 50 of the cow on the display unit 12. This allows the operator to visually recognize on the display unit 12 the cow to be evaluated for fleshiness.

[0018] FIG. 4 is a diagram for explaining the process executed by the extraction unit 32. As shown in FIG. 4, the extraction unit 32 extracts a contour line 60 that traces the outline of the cow from the captured image 50 of the cow acquired by the image acquisition unit 30. A generally known image processing technique can be used for the extraction of the contour line 60. The extraction unit 32 may display an extracted image 51 that shows only the extracted contour line 60 of the cow on the display unit 12. This allows the operator to visually recognize on the display unit 12 the outline of the cow whose fleshiness is to be evaluated. The outer shape of the extracted image 51 is the same as that of the captured image 50, and the position of the cow relative to the frame of the image is the same in the extracted image 51 and the captured image 50.

[0019] There are peaks 61a and 61b on both the left and right sides of the upper part of the contour line 60. The peaks 61a and 61b correspond to the cow's hip angles. The peak 61a has a vertex 62a at the approximate center of the peak 61a on the contour line 60, a first curved portion 63a extending from the vertex 62a to the upper center of the contour line 60 (the cow's spine side), and a second curved portion 64a extending from the vertex 62a to the lower side of the contour line 60 (the cow's belly side). Similarly, the peak 61b has a vertex 62b at the approximate center of the peak 61b on the contour line 60, a first curved portion 63b extending from the vertex 62b to the upper center of the contour line 60 (the cow's spine side), and a second curved portion 64b extending from the vertex 62b to the lower side of the contour line 60 (the cow's belly side). The first curved portions 63a, 63b can be considered to be curved portions extending from approximately the center point (vertices 62a, 62b) on the contour line 60 of the peaks 61a, 61b to the other peak side (the cow's spine side). The second curved portions 64a, 64b can be considered to be curved portions extending from approximately the center point (vertices 62a, 62b) on the contour line 60 of the peaks 61a, 61b to the opposite side to the first curved portions 63a, 63b.

[0020] The apex 62a of the mountain 61a and the apex 62b of the mountain 61b can be specified by the following method. For example, an inclined straight line 55 inclined from the top to the bottom left in the extracted image 51 is moved from the upper left end point 52 of the extracted image 51 toward the contour line 60, and the point where the inclined straight line 55 first touches the contour line 60 can be specified as the apex 62a of the mountain 61a located on the left side. Similarly, an inclined straight line 56 inclined from the top to the bottom right in the extracted image 51 is moved from the upper right end point 54 of the extracted image 51 toward the contour line 60, and the point where the inclined straight line 56 first touches the contour line 60 can be specified as the apex 62b of the mountain 61b located on the right side. The inclined straight lines 55 and 56 are preferably inclined at an angle of, for example, 30° to 60° from the horizontal line in the extracted image 51, more preferably at an angle of 40° to 50°, and even more preferably at an angle of 45°.

[0021] The apex 62a of the mountain portion 61a and the apex 62b of the mountain portion 61b may be specified by other methods without being limited to the above-mentioned method. For example, in the extracted image 51, an inclined straight line 55a inclined at a first predetermined angle from the top to the bottom left is moved from the upper left end point 52 toward the contour line 60 to specify a first point where the inclined straight line 55a first touches the contour line 60, and an inclined straight line 55b inclined at a second predetermined angle is moved from the upper left end point 52 toward the contour line 60 to specify a second point where the inclined straight line 55b first touches the contour line 60, and a point on the contour line 60 that is approximately in the middle between the first point and the second point is specified as the apex 62a of the mountain portion 61a. Similarly, an inclined straight line 56a inclined at a third predetermined angle from top to bottom right in the extracted image 51 may be moved from the upper right end point 54 toward the contour line 60 to identify a third point where the straight line 56a first touches the contour line 60, and an inclined straight line 56b inclined at a fourth predetermined angle may be moved from the upper right end point 54 toward the contour line 60 to identify a fourth point where the straight line 56b first touches the contour line 60, and a point located approximately in the middle between the third point and the fourth point on the contour line 60 may be identified as the apex 62b of the mountain portion 61b. The first and third predetermined angles are preferably set to 15° to 30° from the horizontal line in the extracted image 51, and the second and fourth predetermined angles are preferably set to 60° to 75° from the horizontal line in the extracted image 51.

[0022] Also, for example, the extracted image 51 may be converted into an XY coordinate system, and the vertices 62a, 62b of the two peaks 61a, 61b may be identified from the X and Y coordinates of each pixel of the extracted image 51. For example, the point on the contour 60 that is the shortest distance from the upper left end point 52 of the extracted image 51 may be set as the vertex 62a of the peak 61a, and the point on the contour 60 that is the shortest distance from the upper right end point 54 of the extracted image 51 may be set as the vertex 62b of the peak 61b.

[0023] Alternatively, the apex of either the mountain portion 61a or the mountain portion 61b may be specified by any of the above methods, and the point where the horizontal line in the extracted image 51 passing through the specified apex intersects with the contour line 60 of the other mountain portion may be specified as the apex of the other mountain portion. Note that the apex 62a of the mountain portion 61a and the apex 62b of the mountain portion 61b may be specified by a method other than the above methods. Note that the ranges of the mountain portions 61a and 61b can be specified by various methods. For example, the range of the mountain portion 61a can be the range of the contour line 60 contained in a circle having a predetermined radius centered on the apex 62a of the mountain portion 61a. The predetermined radius can be, for example, a value obtained by multiplying the distance between the apex 62a of the mountain portion 61a and the uppermost point 91 located at the uppermost side of the contour line 60 by a predetermined value (for example, 0.5), but may be a value obtained by other methods. Note that the range of the mountain portion 61a may be a range of a predetermined length on both sides from the apex 62a of the mountain portion 61a. The predetermined length may be, for example, the length of the predetermined radius, or may be a length obtained by multiplying the entire length of the contour line 60 by a predetermined value. The same applies to the peak portion 61b. The range of the peak portions 61a and 61b may be determined by machine learning or the like.

[0024] FIG. 5 is a diagram for explaining the process executed by the determination unit 38. FIG. 5 is an enlarged view of the upper part of the contour line 60, and is illustrated diagrammatically for clarity (the same applies to the following similar figures). As shown in FIG. 5, the determination unit 38 determines a point 403a on a first curved portion 63a and a point 404a on a second curved portion 64a of one of the peaks 61a of the peaks 61a and 61b present on both the left and right sides of the upper part of the contour line 60. In the first embodiment, the determination unit 38 determines the point that first touches the peak 61a by moving a horizontal line 420 extending in the left-right direction (horizontal direction) in the extracted image 51 (captured image 50) from above the peak 61a toward the peak 61a as the point 403a on the first curved portion 63a. Furthermore, the determination unit 38 determines the point on the second curved portion 64a that first touches the peak portion 61a when the vertical line 422a extending in the up-down direction (vertical direction) in the extracted image 51 (captured image 50) approaches the peak portion 61a from the left side of the peak portion 61a toward the peak portion 61a as the point 404a. In this manner, in the first embodiment, the determination unit 38 determines the point on the first curved portion 63a that protrudes most upward as the point 403a, and determines the point on the second curved portion 64a that protrudes most laterally as the point 404a.

[0025] The determination unit 38 may determine a point 403b on the first curved portion 63b and a point 404b on the second curved portion 64b of the peak portion 61b, instead of or in addition to determining the point 403a on the first curved portion 63a and the point 404a on the second curved portion 64a of the peak portion 61a. The determination unit 38 can determine the point at which the horizontal line 420 first touches the peak portion 61b when it approaches the peak portion 61b from above the peak portion 61b toward the peak portion 61b as the point 403b on the first curved portion 63b, and can determine the point at which the vertical line 422b extending in the up-down direction (vertical direction) in the extracted image 51 first touches the peak portion 61b when it approaches the peak portion 61b from the right side of the peak portion 61b toward the peak portion 61b as the point 404b on the second curved portion 64b.

[0026] 6(a) and 6(b) are diagrams for explaining the process executed by the calculation unit 34 in the first embodiment. As shown in FIG. 6(a), the calculation unit 34 identifies a point 406a at which a straight line 424a that passes through a midpoint 405a of a line segment 410a connecting the points 403a and 404a and is perpendicular to the line segment 410a intersects with the mountain portion 61a. The calculation unit 34 then calculates an angle ω1 between a line segment 412a connecting the points 403a and 406a and a line segment 414a connecting the points 404a and 406a. The angle ω1 calculated by the calculation unit 34 is one of the index values ​​indicating the degree of inclination of the mountain portion 61a.

[0027] The evaluation unit 36 ​​evaluates the fleshiness of the cattle captured in the captured image 50 from the angle ω1 calculated by the calculation unit 34. As the fleshiness, for example, the body condition score is evaluated.

[0028] 6(b), in the case where the determining unit 38 determines the point 403b on the first curved portion 63b and the point 404b on the second curved portion 64b of the mountain portion 61b, the calculating unit 34 identifies the point 406b where the straight line 424b, which passes through the midpoint 405b of the line segment 410b connecting the points 403b and 404b and is perpendicular to the line segment 410b, intersects with the mountain portion 61b. Then, the calculating unit 34 calculates the angle ω2 between the line segment 412b connecting the points 403b and 406b and the line segment 414b connecting the points 404b and 406b. The angle ω2 calculated by the calculating unit 34 is one of the index values ​​indicating the degree of inclination of the mountain portion 61b. In this case, the evaluating unit 36 ​​evaluates the beefiness of the cow captured in the captured image 50 from the angle ω2 calculated by the calculating unit 34.

[0029] Furthermore, in a case where the determination unit 38 determines point 403b on the first curved portion 63b and point 404b on the second curved portion 64b of the peak portion 61b in addition to point 403a on the first curved portion 63a and point 404a on the second curved portion 64a of the peak portion 61a, the calculation unit 34 may calculate both the angles ω1 and ω2 and calculate the average value of the angles ω1 and ω2. In this case, the evaluation unit 36 ​​may evaluate the fleshiness of the cow captured in the captured image 50 from the average values ​​of the angles ω1 and ω2 calculated by the calculation unit 34.

[0030] Here, the relationship between the angles ω1, ω2 calculated by calculation unit 34 and the body condition score will be described. The body condition score is an index showing the state of body fat and may be given a score of, for example, 1.00 to 5.00, with a higher value indicating better fleshiness.

[0031] 7(a) to 7(c) are images 50 of cows with different levels of fleshiness. FIG. 7(a) is an image 50 of a cow with poor fleshiness, FIG. 7(b) is an image 50 of a cow that is more fleshy than the cow in FIG. 7(a), and FIG. 7(c) is an image 50 of a cow that is even more fleshy. The cow in FIG. 7(a) was given a body condition score of 2.25 by an expert. The cow in FIG. 7(b) was given a score of 3.00, and the cow in FIG. 7(c) was given a score of 4.00. As shown in FIG. 7(a) to FIG. 7(c), it can be seen that the fleshiness around the hip angle changes due to differences in fleshiness (i.e., different body condition scores), and the shape of the hip angle when the cow is viewed from directly behind in a standing position is different.

[0032] 8(a) to 8(c) are diagrams showing the relationship between the meatiness of a cow and the angle ω1 calculated by the calculation unit 34. FIG. 8(a) shows the contour line 60 of a lean cow, FIG. 8(b) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 8(a), and FIG. 8(c) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 8(b). As shown in Figures 8(a) to 8(c), the more fleshy a cow is, the more rounded the peak 61a, which is the part that corresponds to the waist angle. For this reason, it was found that the more fleshy a cow is, the smaller the value of angle ω1. Although not shown in the figures, the same holds true for the relationship between the fleshiness of a cow and the angle ω2 calculated by the calculation unit 34. From these facts, it is considered that the fleshiness of a cow can be evaluated by calculating the angle ω1, the angle ω2, or the average value of angles ω1 and ω2, and using these.

[0033] [experiment] An experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the angles ω1, ω2, and the average value of the angles ω1 and ω2 calculated by the calculation unit 34. The experiment was conducted on dairy cows (Holstein breed).

[0034] FIG. 9 shows the results of an experiment investigating the correlation between the body condition score and the angles ω1, ω2, and the average values ​​of the angles ω1 and ω2 calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 9 is the body condition score evaluated by an expert, and the vertical axis is the angle. A plurality of black circles in FIG. 9 show the results of each dairy cow when the angle ω1 is used, and the dotted straight line shows the approximation line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the angle ω2 is used, and the dashed straight line shows the approximation line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average values ​​of the angles ω1 and ω2 are used, and the dashed straight line shows the approximation line (regression line) at that time. As shown in FIG. 9, the body condition score increases as the angle decreases, regardless of whether the angle ω1, the angle ω2, or the average values ​​of the angles ω1 and ω2 are used. The dotted approximation line using angle ω1 is calculated as y = -7.4724x + 162.85, and the coefficient of determination is R 2 was 0.6478. The approximate straight line of the dashed line using the angle ω2 was found to be y = -10.594x + 171.76, and the coefficient of determination R 2 was 0.7048. The approximate dashed line using the average values ​​of angles ω1 and ω2 was calculated as y = -9.0331x + 167.31, and the coefficient of determination R 2 This confirmed that there is a strong correlation between the body condition score and the angles ω1, ω2, and the average value of the angles ω1 and ω2 calculated by the calculation unit 34.

[0035] As described above, since there is a strong correlation between the body condition score and the angles ω1, ω2, and the average values ​​of angles ω1 and ω2 calculated by calculation unit 34, it can be seen that the beefiness of the cow can be evaluated with high accuracy by evaluation unit 36 ​​evaluating the beefiness from angles ω1, ω2, or the average values ​​of angles ω1 and ω2. Evaluation unit 36 ​​evaluates the body condition score using, for example, score information stored in memory unit 20 that associates angles with body condition scores.

[0036] Table 1 shows an example of score information stored in the storage unit 20. As shown in Table 1, in the score information, angles and body condition scores are associated with each other. For example, when the angle is less than a°, the body condition score is 5.00, and when the angle is equal to or greater than a° and less than b°, the body condition score is 4.50. In Table 1, the body condition score is in increments of 0.5, but other increments are also possible. For example, increments of 0.25 are also possible, or increments of 0.25 are possible between 2.00 and 4.00, and increments of 0.50 are also possible. As the score information as shown in Table 1, separate score information may be created for the angle ω1, the angle ω2, and the average value of the angle ω1 and the angle ω2, or score information may be created and shared for either the angle ω1, the angle ω2, or the average value of the angle ω1 and the angle ω2. When sharing score information, by sharing score information created from the average value of angles ω1 and ω2, the body condition score can be evaluated with high accuracy even when evaluating the body condition score from angles ω1 and ω2. [Table 1]

[0037] The score information stored in storage unit 20 may be other than the score information shown in Table 1, as long as it is information that associates angles with body condition scores. For example, a linear function (y=ax+b) such as the approximated straight line shown in Fig. 9 may be stored in storage unit 20 as score information. In this case, the body condition score may be evaluated by performing fractional processing such as rounding off, rounding up, or rounding down on the value of x obtained by substituting the angle for y.

[0038] Fig. 10 is a block diagram showing the hardware configuration of the cow evaluation device 100 according to the first embodiment. As shown in Fig. 10, the cow evaluation device 100 has a storage device 70, a memory 71, a processor 72, a communication interface 73, an input device 74, a display device 75, and an imaging device 76. These components are connected to each other by a bus 77.

[0039] The storage device 70 is a non-volatile semiconductor memory such as a flash memory, and stores a cow evaluation program 78 .

[0040] The memory 71 is hardware that temporarily stores data, such as a dynamic random access memory (DRAM), etc. The storage unit 20 in FIG.

[0041] The processor 72 is hardware such as a CPU (Central Processing Unit) that controls each part of the cow evaluation device 100. The processor 72 executes a cow evaluation program 78 in cooperation with the memory 71. In this way, the memory 71 and the processor 72 cooperate to execute the cow evaluation program 78, thereby realizing each function of the control unit 22 in Fig. 2.

[0042] The communication interface 73 is hardware for enabling the cow evaluation device 100 to perform short-range wireless communication or wireless communication via a network with other devices. The communication interface 73 realizes the communication unit 16 in FIG.

[0043] The input device 74 is an input device such as a touch panel or a switch that enables an operator to operate the cattle evaluation device 100. The input device 74 realizes the operation unit 14 in FIG.

[0044] The display device 75 is hardware for realizing the display unit 12 in FIG. 1, and is a display device such as a liquid crystal display for displaying the captured image 50 of the cow, the extracted image 51, the evaluation results of the beefiness of the cow, etc.

[0045] The imaging device 76 is hardware for realizing the imaging unit 18 in FIG. 1, and includes a lens, an imaging element, and the like.

[0046] Next, an example of the method for evaluating beef meatiness in the first embodiment will be described with reference to the flowchart in Fig. 11. The process in Fig. 11 is executed by the control unit 22 of the evaluation device 100. It is assumed that the storage unit 20 stores score information such as that shown in Table 1, for example.

[0047] 11, first, in step S10, the image acquisition section 30 of the control section 22 waits until the start of the cow evaluation program 78. In this case, the process proceeds to step S12 when the control section 22 starts the cow evaluation program 78 in response to an operation by an operator (for example, an input operation to the operation section 14 or a voice input to a microphone (not shown)).

[0048] When the process proceeds to step S12, the image acquisition unit 30 acquires an image 50 of the cow to be evaluated for meatiness (see FIG. 3). The image 50 of the cow is an image of the cow in an upright position captured from almost directly behind. The image acquisition unit 30 acquires, for example, an image of the cow captured by the operator using the imaging unit 18. The image acquisition unit 30 may acquire an image of the cow received from another device via the communication unit 16, or an image of the cow selected by the operator by operating the operation unit 14 from among a plurality of images of the cow stored in the storage unit 20. The image acquisition unit 30 may start a camera function so that the operator can capture an image of the cow using the imaging unit 18 after the cow evaluation program 78 is started. When the operator captures an image of the cow using the imaging unit 18, the image of the captured cow and a selection button asking whether or not to select this captured image may be displayed on the display unit 12, and if the operator chooses not to select the image, the camera function may be started again.

[0049] In step S14, the extraction unit 32 of the control unit 22 extracts a contour line 60 that traces the outline of the cow from the captured image 50 of the cow acquired in step S12 (see FIG. 4). This generates an extracted image 51 showing the cow's contour line 60. When extracting the contour line 60, the extraction unit 32 may perform a process of removing background other than the cow in the captured image 50 in order to extract the contour line 60 with good accuracy.

[0050] Next, in step S16, in the first embodiment, the determination unit 38 of the control unit 22 determines a point 403a on the first curved portion 63a of the peak portion 61a and a point 404a on the second curved portion 64a. The determination unit 38 determines the point at which the horizontal line 420 first touches the peak portion 61a when it approaches the peak portion 61a from above the peak portion 61a as the point 403a on the first curved portion 63a, and determines the point at which the vertical line 422a first touches the peak portion 61a when it approaches the peak portion 61a from the left side of the peak portion 61a as the point 404a on the second curved portion 64a (see FIG. 5).

[0051] Next, in step S18, the calculation unit 34 of the control unit 22 first identifies a point 406a where a straight line 424a that passes through a midpoint 405a of a line segment 410a connecting the points 403a and 404a and is perpendicular to the line segment 410a intersects with the mountain portion 61a. Then, the calculation unit 34 calculates an angle ω1 between a line segment 412a connecting the points 403a and 406a and a line segment 414a connecting the points 404a and 406a (see FIG. 6(a)).

[0052] Next, in step S20, the evaluation unit 36 ​​of the control unit 22 evaluates the body condition score of the cow captured in the captured image 50 based on the angle ω1 calculated in step S18 and score information such as Table 1 stored in the memory unit 20.

[0053] Next, in step S22, the evaluation unit 36 ​​displays the body condition score evaluated in step S20 on the display unit 12 and stores it in the memory unit 20. For example, the evaluation unit 36 ​​may display the body condition score on the display unit 12 together with the captured image 50 of the cow. The evaluation unit 36 ​​may also store in the memory unit 20 individual identification information, such as the individual identification number of the cow, input by the worker operating the operation unit 14, in association with the evaluated body condition score. Note that the evaluation unit 36 ​​is not limited to acquiring individual identification information input by the worker operating the operation unit 14, but may also acquire individual identification information from an image captured by the imaging unit 18 of an image of an identification tag attached to the body of the cow, or may acquire individual identification information by using RFID (Radio Frequency Identification) technology and having the communication unit 16 receive the individual identification information from an RF tag attached to the body of the cow. Alternatively, cameras and communication devices may be installed in the passages inside and outside the cowshed so that the cows passing through the passages can be detected by sensors, and images of the cows passing through the passages captured by the cameras may be acquired by the communication unit 16, and the individual identification information may be acquired from the images of the identification tags captured in the images. Alternatively, the communication device may receive the individual identification information from RF tags attached to the cows passing through the passages, and the communication unit 16 may receive the individual identification information from the communication device. Furthermore, the evaluation unit 36 ​​may store in the memory unit 20 the individual identification number of the cow whose body condition score has been evaluated, the image 50 of the cow, the image date, and the body condition score of the cow as a single piece of associated information.

[0054] As described above, according to the first embodiment, the image acquisition unit 30 acquires a two-dimensional captured image 50 in which a cow in a standing position is captured from almost directly behind (see FIG. 3). The extraction unit 32 extracts a contour line 60 of the cow from the captured image 50 (see FIG. 4). The determination unit 38 determines a point 403a (first point) on a first curved portion 63a of the peak portion 61a of the two peak portions 61a, 61b present on both the left and right sides of the upper part of the contour line 60, and a point 404a (second point) on a second curved portion 64a (see FIG. 5). The calculation unit 34 specifies a point 406a (third point) at which a straight line 424a that passes through a midpoint 405a of a line segment 410a (first line segment) connecting the points 403a and 404a and is perpendicular to the line segment 410a intersects the peak portion 61a. Then, the calculation unit 34 calculates the angle ω1 between the line segment 412a (third line segment) connecting the point 403a and the point 406a and the line segment 414a (fourth line segment) connecting the point 404a and the point 406a (see FIG. 6(a)). The evaluation unit 36 ​​evaluates the beefiness of the cow captured in the captured image 50 from the angle ω1 calculated by the calculation unit 34. In this way, in the first embodiment, the beefiness of the cow is evaluated using the two-dimensional captured image 50 in which the cow in an upright position is captured from substantially behind, so that it is possible to apply the present invention to various breeding sites without requiring special equipment for capturing images of the cow in three dimensions or special equipment for capturing images of the cow from above. In addition, the angle ω1 does not change whether the cow is captured large or small in the captured image 50, which is a two-dimensional image. Therefore, by evaluating the beefiness of the cow using the angle ω1, the beefiness of the cow can be favorably evaluated without performing processing such as normalization. Furthermore, when a person evaluates the fleshiness of a cow, the evaluation criteria become vague and the evaluation varies, but in this first embodiment, the control unit 22 judges the fleshiness of the cow, so the variation in evaluation can be suppressed. Furthermore, since the fleshiness of the cow is evaluated using a two-dimensional captured image 50 captured from almost directly behind a cow in an upright position, the evaluation device 100, which is highly portable and versatile, such as a smartphone, can be used.

[0055] In the first embodiment, the determiner 38 determines the most upwardly protruding point of the first curved portion 63a of the peak 61a as a point 403a on the first curved portion 63a, as shown in FIG. 5. The determiner 38 determines the most outwardly protruding point of the second curved portion 64a of the peak 61a as a point 404a on the second curved portion 64a. The angle ω1 calculated using such points 403a and 404a has a high correlation with the body condition score, as shown in FIG. 9. Therefore, by evaluating the beefiness of the cow using the angle ω1, the beefiness of the cow can be evaluated with high accuracy.

[0056] In the first embodiment, the determination unit 38 determines the first point of contact when the horizontal line 420 approaches the peak 61a from above the peak 61a as point 403a on the first curved portion 63a, as shown in Fig. 5. The determination unit 38 also determines the first point of contact when the vertical line 422a approaches the peak 61a from the side of the peak 61a as point 404a on the second curved portion 64a. This makes it possible to determine the point of the first curved portion 63a that protrudes most upward as point 403a, and the point of the second curved portion 64a that protrudes most outward as point 404a, by simple processing.

[0057] Furthermore, as described above, the determination unit 38 may determine a point 403b (first point) on the first curved portion 63b of the mountain portion 61b of the two mountain portions 61a, 61b present on both the left and right sides of the upper part of the contour line 60, and a point 404b (second point) on the second curved portion 64b (see FIG. 5). The calculation unit 34 may specify a point 406b (third point) at which a straight line 424b passing through a midpoint 405b of a line segment 410b (first line segment) connecting the points 403b and 404b and perpendicular to the line segment 410b intersects with the mountain portion 61b, and calculate an angle ω2 between a line segment 412b (third line segment) connecting the points 403b and 406b and a line segment 414b (fourth line segment) connecting the points 404b and 406b (see FIG. 6(b)). The evaluation unit 36 ​​may then evaluate the fleshiness of the cow captured in the captured image 50 from the angle ω2 calculated by the calculation unit 34. Even in this case, the same effect as in the case of evaluating the fleshiness of the cow from the angle ω1 can be obtained.

[0058] Furthermore, as described above, the determination unit 38 may determine points 403a, 403b (first points) on the first curved portions 63a, 63b and points 404a, 404b (second points) on the second curved portions 64a, 64b for both of the two peaks 61a, 61b present on both the left and right sides of the upper part of the contour line 60 (see FIG. 5). The calculation unit 34 may calculate the average value of the angle ω1 between the line segment 412a and the line segment 414a in the peak 61a and the angle ω2 between the line segment 412b and the line segment 414b in the peak 61b. The evaluation unit 36 ​​may evaluate the fleshiness of the cow captured in the captured image 50 from the average value of the angles ω1 and ω2 calculated by the calculation unit 34. The average value of the angles ω1 and ω2 is used as a coefficient of determination R, which indicates a correlation with the body condition score, as described in FIG. 9. 2 Therefore, the meatiness of the cow can be evaluated with high accuracy. In addition, by using the average value of the angles ω1 and ω2, the effect of the shooting angle when the cow is imaged from almost directly behind is reduced.

[0059] In the first embodiment, the evaluation unit 36 ​​may determine the body condition score from at least two of the angle ω1, the angle ω2, and the average value of the angles ω1 and ω2, and evaluate the average value of the determined body condition scores.

[0060] In addition, when evaluating the fleshiness of a cow, the user can appropriately select whether to use the angle ω1, the angle ω2, or the average value of the angles ω1 and ω2.

[0061] [Another determination method by the determination unit 38] 12(a) to 12(c) are diagrams showing another determination method by the determination unit 38. As shown in Fig. 12(a), there are cases where a part of the second curved portion 64a of the mountain portion 61a is parallel to the vertical line 422a, and the point where the vertical line 422a first touches the second curved portion 64a is not a point but a range 426. In this case, the determination unit 38 determines the central point of the range 426 to be point 404a. The same applies to points 403a, 403b, and 404b.

[0062] 12(b), there is a case where the first curved portion 63a of the mountain portion 61a continues to rise from the apex 62a toward the uppermost point 91 without forming a depression. In this case, the determining unit 38 determines the inflection point on the apex 62a side of the contour line 60, which is the point of the first curved portion 63a located closest to the cow's spine, as point 403a. The same applies to point 403b.

[0063] As shown in Fig. 12(c), there is a case where the second curved portion 64a of the mountain portion 61a continues to descend from the apex 62a downward without forming a depression. In this case, the determination unit 38 determines the boundary point between the waist angle and the abdomen, which is the point located most abdominally on the second curved portion 64a, as point 404a. The same applies to point 404b.

[0064] 12(a) to 12(c), the determination unit 38 determines the point of the first curved portion 63a that protrudes most upward as point 403a, and determines the point of the second curved portion 64a that protrudes most laterally as point 404a. Therefore, like the first embodiment, the beefiness of the cow can be evaluated with high accuracy.

[0065] Second Embodiment The functional configuration and hardware configuration of the cattle evaluation device according to the second embodiment are the same as those of the first embodiment shown in Fig. 1 and Fig. 10. The functional configuration of the control unit 22 in the second embodiment is the same as that of the first embodiment shown in Fig. 2, but the processing executed by the calculation unit 34 differs from that in the first embodiment. The following description will focus on the processing executed by the calculation unit 34.

[0066] 13(a) and 13(b) are diagrams for explaining the process executed by the calculation unit 34 in the second embodiment. As shown in FIG. 13(a), when the determination unit 38 determines the point 403a on the first curved portion 63a of the mountain portion 61a and the point 404a on the second curved portion 64a, the calculation unit 34 calculates the length X1a of the line segment 410a connecting the points 403a and 404a, the length X2a of the line segment 416a connecting the midpoint 405a and the point 406a, or the length ratio (X1a / X2a) of the length X1a to the length X2a. The length X1a, the length X2a, and the length ratio (X1a / X2a) calculated by the calculation unit 34 are one of the index values ​​indicating the degree of inclination of the mountain portion 61a.

[0067] The evaluation unit 36 ​​evaluates the fleshiness of the cow captured in the captured image 50 from the length X1a, the length X2a, or the length ratio (X1a / X2a) calculated by the calculation unit 34.

[0068] 13(b), in the case where the determination unit 38 determines a point 403b on the first curved portion 63b of the peak portion 61b and a point 404b on the second curved portion 64b, the calculation unit 34 calculates the length X1b of a line segment 410b connecting the points 403b and 404b, the length X2b of a line segment 416b connecting the midpoint 405b and the point 406b, or the length ratio (X1b / X2b) of the length X1b to the length X2b. The length X1b, the length X2b, and the length ratio (X1b / X2b) calculated by the calculation unit 34 are one of the index values ​​indicating the degree of inclination of the peak portion 61b.

[0069] The evaluation unit 36 ​​evaluates the fleshiness of the cow captured in the captured image 50 from the length X1b, the length X2b, or the length ratio (X1b / X2b) calculated by the calculation unit 34.

[0070] In addition, when the determination unit 38 has determined all of the point 403a on the first curved portion 63a of the peak portion 61a, the point 404a on the second curved portion 64a, and the point 403b on the first curved portion 63b of the peak portion 61b, and the point 404b on the second curved portion 64b, the calculation unit 34 may calculate the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b). In this case, the evaluation unit 36 ​​may evaluate the fleshiness of the cow captured in the captured image 50 from the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) calculated by the calculation unit 34.

[0071] 14(a) to 14(c) are diagrams showing the relationship between the fatness of a cow and the lengths X1a and X2a calculated by the calculation unit 34. FIG. 14(a) shows the contour line 60 of a lean cow, FIG. 14(b) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 14(a), and FIG. 14(c) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 14(b). As shown in Figures 14(a) to 14(c), it was found that the length X1a of the line segment 410a connecting the points 403a and 404a, and the length X2a of the line segment 416a connecting the midpoint 405a and the point 406a, become larger as the beefiness increases. It was also found that the length ratio (X1a / X2a) of the length X1a to the length X2a becomes smaller as the beefiness increases. From these facts, it is considered that the beefiness of a cow can be evaluated by determining the length X1a, the length X2a, or the length ratio (X1a / X2a). Although not shown in the figures, the same relationship is also true for the beefiness of a cow and the length X1b, the length X2b, and the length ratio (X1b / X2b) calculated by the calculation unit 34.

[0072] [experiment] An experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the value calculated by the calculation unit 34. The experiment was conducted on dairy cows (Holstein breed).

[0073] FIG. 15 shows the results of an experiment investigating the correlation between the body condition score and the length X1a, length X1b, and the average value of the length X1a and length X1b calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 15 is the body condition score evaluated by an expert, and the vertical axis is the length. A plurality of black circles in FIG. 15 show the results of each dairy cow when the length X1a was used, and the dotted straight line shows the approximation straight line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the length X1b was used, and the dashed straight line shows the approximation straight line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average value of the length X1a and the length X1b was used, and the dashed straight line shows the approximation straight line (regression line) at that time. As shown in FIG. 15, the body condition score increases as the length increases, regardless of whether the length X1a, the length X1b, or the average value of the length X1a and the length X1b is used. The approximate dotted line using the length X1a is calculated as y = 5.8314x + 3.8135, and the coefficient of determination is R 2 was 0.6037. The approximate straight line of the dashed line using the length X1b was found to be y = 5.9771x + 2.7028, and the coefficient of determination R 2 was 0.6084. The approximate dashed line using the average values ​​of length X1a and length X1b was calculated as y = 5.9042x + 3.2582, and the coefficient of determination R 2 This confirmed that there is a strong correlation between the body condition score and the length X1a, length X1b, and the average value of length X1a and length X1b calculated by calculation unit 34.

[0074] In this way, since there is a strong correlation between the body condition score and the length X1a, length X1b, and the average value of length X1a and length X1b calculated by the calculation unit 34, the evaluation unit 36 ​​evaluates the fleshiness of the cow using the length X1a, length X1b, or the average value of length X1a and length X1b. For example, the fleshiness of the cow is evaluated using score information similar to that shown in Table 1, which associates the length X1a, length X1b, or the average value of length X1a and length X1b with the body condition score. This allows the fleshiness of the cow to be evaluated with high accuracy.

[0075] FIG. 16 shows the results of an experiment investigating the correlation between the body condition score and the length X2a, length X2b, and the average value of the length X2a and length X2b calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 16 is the body condition score evaluated by an expert, and the vertical axis is the length. A plurality of black circles in FIG. 16 show the results of each dairy cow when the length X2a was used, and the dotted straight line shows the approximation straight line (regression line) at that time. A plurality of black squares show the results of each dairy cow when the length X2b was used, and the dashed straight line shows the approximation straight line (regression line) at that time. A plurality of black triangles show the results of each dairy cow when the average value of the length X2a and the length X2b was used, and the dashed straight line shows the approximation straight line (regression line) at that time. As shown in FIG. 16, whether the length X2a, the length X2b, or the average value of the length X2a and the length X2b was used, the body condition score increased as the length increased. The approximate dotted line using the length X2a is calculated as y = 2.0388x - 2.2042, and the coefficient of determination is R 2 was 0.7707. The approximate straight line of the dashed line using the length X2b was found to be y = 2.5939x - 3.9392, and the coefficient of determination R 2 was 0.7297. The approximate dashed line using the average values ​​of length X2a and length X2b was calculated as y = 2.3164x - 3.0717, and the coefficient of determination R 2 This confirmed that there is a strong correlation between the body condition score and the length X2a, the length X2b, and the average value of the lengths X2a and X2b calculated by the calculation unit 34.

[0076] In this way, since there is a strong correlation between the body condition score and the length X2a, length X2b, and the average value of length X2a and length X2b calculated by the calculation unit 34, the evaluation unit 36 ​​evaluates the fleshiness of the cow using length X2a, length X2b, or the average value of length X2a and length X2b. For example, the fleshiness of the cow is evaluated using score information similar to that shown in Table 1, which associates length X2a, length X2b, or the average value of length X2a and length X2b with the body condition score. This allows the fleshiness of the cow to be evaluated with high accuracy.

[0077] FIG. 17 shows the results of an experiment investigating the correlation between the body condition score and the length ratio (X1a / X2a) of the length X1a to the length X2a, the length ratio (X1b / X2b) of the length X1b to the length X2b, and the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b), all calculated by the calculation unit 34. The horizontal axis (x-axis) of FIG. 17 is the body condition score evaluated by an expert, and the vertical axis is the length ratio. A number of black circles in FIG. 17 show the results for each dairy cow when the length ratio (X1a / X2a) is used, and the dotted straight line shows the approximation straight line (regression line) at that time. A number of black squares show the results for each dairy cow when the length ratio (X1b / X2b) is used, and the dashed straight line shows the approximation straight line (regression line) at that time. The multiple black triangles show the results for each dairy cow when the average length ratio ((X1a / X2a)+(X1b / X2b)) / 2) is used, and the dashed straight line shows the approximation line (regression line) at that time. As shown in Figure 17, whether the length ratio (X1a / X2a), the length ratio (X1b / X2b), or the average of the length ratios (X1a / X2a) and (X1b / X2b) is used, the body condition score increases as the length ratio decreases. The dotted approximation line using the length ratio (X1a / X2a) was found to be y=-1.0967x+9.0164, and the coefficient of determination R 2 was 0.5676. The approximate straight line of the dashed line using the length ratio (X1b / X2b) was found to be y = -1.5338x + 10.441, and the coefficient of determination R 2was 0.5985. The approximate dashed line using the average values ​​of the length ratios (X1a / X2a) and (X1b / X2b) was calculated as y = -1.3152x + 9.7286, and the coefficient of determination R 2 This confirmed that there is a strong correlation between the body condition score and the length ratio (X1a / X2a), length ratio (X1b / X2b), and the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) calculated by the calculation unit 34.

[0078] In this way, since there is a strong correlation between the body condition score and the length ratio (X1a / X2a), the length ratio (X1b / X2b), and the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) calculated by the calculation unit 34, the evaluation unit 36 ​​evaluates the beefiness of the cattle using the length ratio (X1a / X2a), the length ratio (X1b / X2b), or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b). For example, the beefiness of the cattle is evaluated using score information in which the length ratio (X1a / X2a), the length ratio (X1b / X2b), or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) is associated with the body condition score, as in Table 1. This allows the beefiness of the cattle to be evaluated with high accuracy.

[0079] As described above, according to the second embodiment, the calculation unit 34 calculates the length X1a of the line segment 410a connecting the point 403a and the point 404a, the length X2a of the line segment 416a (second line segment) connecting the midpoint 405a and the point 406a, or the length ratio (X1a / X2a) of the length X1a to the length X2a (see FIG. 13(a)). The evaluation unit 36 ​​evaluates the beefiness of the cow captured in the captured image 50 from the length X1a, the length X2a, or the length ratio (X1a / X2a) calculated by the calculation unit 34. In this case, too, as in the first embodiment, the beefiness of the cow is evaluated using a two-dimensional captured image 50 in which a cow in an upright position is captured from substantially behind, so that the present invention can be applied to various breeding sites. In addition, when the beefiness of the cow is evaluated using the length ratio (X1a / X2a), the beefiness of the cow can be favorably evaluated without performing processing such as normalization, as in the first embodiment. Furthermore, since the control unit 22 judges the beefiness of the cow, it is possible to reduce variation in the judgment. Furthermore, since the beefiness of the cow is evaluated using two-dimensional captured image 50 captured from almost directly behind the cow in an upright position, it is possible to use an evaluation device such as a smartphone that is highly portable and versatile.

[0080] In addition, when the determination unit 38 determines the point 403b (first point) on the first curved portion 63b of the mountain portion 61b and the point 404b (second point) on the second curved portion 64b, the calculation unit 34 calculates the length X1b of the line segment 410b (first line segment) connecting the point 403b and the point 404b, the length X2b of the line segment 416b (second line segment) connecting the midpoint 405b and the point 406b, or the length ratio (X1b / X2b) of the length X1b to the length X2b (see FIG. 13(b)). The evaluation unit 36 ​​evaluates the beefiness of the cow captured in the captured image 50 from the length X1b, the length X2b, or the length ratio (X1b / X2b) calculated by the calculation unit 34. Even in this case, the same effect as that of evaluating the beefiness of the cow from the length X1a, the length X2a, or the length ratio (X1a / X2a) can be obtained.

[0081] In addition, when the determination unit 38 determines the points 403a, 403b (first points) on the first curved portions 63a, 63b and the points 404a, 404b (second points) on the second curved portions 64a, 64b for both of the peaks 61a, 61b, the calculation unit 34 may calculate the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b). The evaluation unit 36 ​​may evaluate the fleshiness of the cow captured in the captured image 50 from the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) calculated by the calculation unit 34. As explained in Figures 15 to 17, the average values ​​of length X1a and length X1b, the average values ​​of length X2a and length X2b, and the average values ​​of length ratio (X1a / X2a) and length ratio (X1b / X2b) are used to calculate the coefficient of determination R 2 Therefore, the meatiness of the cow can be evaluated with high accuracy. In addition, by using the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, and the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b), the evaluation is less susceptible to the influence of the shooting angle when the cow is imaged from almost directly behind.

[0082] When evaluating the fleshiness of a cow using length X1a, length X1b, length X2a, length X2b, the average value of lengths X1a and X1b, and the average value of lengths X2a and X2b, it is preferable that when photographing the cow from approximately directly behind, a reference object that serves as a standard for length is also photographed at the same distance and at the same magnification.

[0083] In addition, when evaluating the fleshiness of a cow, the user can appropriately select which of the length X1a, the length X1b, the length X2a, the length X2b, the length ratio (X1a / X2a), the length ratio (X1b / X2b), the average value of the lengths X1a and X1b, the average value of the lengths X2a and X2b, or the average value of the length ratio (X1a / X2a) and the length ratio (X1b / X2b) to use.

[0084] In the first and second embodiments, the calculation unit 34 may calculate two or more of the angle ω1, the length X1a, the length X2a, and the length ratio (X1a / X2a) for the peak 61a. The evaluation unit 36 ​​may evaluate the beefiness of the cow based on the maximum, minimum, or average body condition score obtained from each of the two or more values ​​of the angle ω1, the length X1a, the length X2a, and the length ratio (X1a / X2a). Similarly, the calculation unit 34 may calculate two or more of the angle ω2, the length X1b, the length X2b, and the length ratio (X1b / X2b) for the peak 61b. The evaluation unit 36 ​​may evaluate the beefiness of the cow based on the maximum, minimum, or average body condition score obtained from each of the two or more values ​​of the angle ω2, the length X1b, the length X2b, and the length ratio (X1b / X2b). In addition, the evaluation unit 36 ​​may evaluate the fleshiness of the cow based on the maximum, minimum, or average body condition score obtained from two or more of the average values ​​of the angles ω1 and ω2, the average values ​​of the lengths X1a and X1b, the average values ​​of the lengths X2a and X2b, and the average values ​​of the length ratios (X1a / X2a) and (X1b / X2b).

[0085] In the above first and second embodiments, the midpoints 405a and 405b of the line segments 410a and 410b are used, but approximate midpoints located within a range of 1 / 50 or less of the length of the line segments 410a and 410b from the midpoints of the line segments 410a and 410b may be used. The straight lines 424a and 424b and the line segments 416a and 416b are perpendicular to the line segments 410a and 410b, but they may be approximate perpendicular lines inclined within a range of ±5° from the perpendicular to the line segments 410a and 410b.

[0086] In the first and second embodiments, the determination unit 38 may convert the extracted image 51 into an XY coordinate system, and determine the points of the first curved portions 63a, 63b that protrude most upwardly from the X and Y coordinates of each pixel of the extracted image 51 as points 403a, 403b, and determine the points of the second curved portions 64a, 64b that protrude most laterally as points 404a, 404b.

[0087] [Allowable angles of horizontal line 420 and vertical lines 422a, 422b] In the above first and second embodiments, a case has been shown in which points 403a, 403b on first curved portions 63a, 63b are determined using horizontal line 420 in extracted image 51. A case has been shown in which points 404a, 404b on second curved portions 64a, 64b are determined using vertical lines 422a, 422b in extracted image 51. Here, an investigation was conducted to determine to what extent an inclination angle is permissible when a slightly inclined approximately horizontal line is used instead of horizontal line 420, and when a slightly inclined approximately vertical line is used instead of vertical lines 422a, 422b.

[0088] [experiment] Points 403a and 403b on the first curved portions 63a and 63b were determined using approximately horizontal lines with inclination angles of -20°, -10°, 0°, 10°, and 20° from the horizontal line in the extracted image 51. The inclination angle when the approximately horizontal line extends from the lower left to the upper right was determined as positive, and the inclination angle when the approximately horizontal line extends from the lower right to the upper left was determined as negative. Furthermore, points 404a and 404b on the second curved portions 64a and 64b were determined using approximately vertical lines with inclination angles of 80°, 90°, and 100° from the horizontal line in the extracted image 51. When the inclination angle is 80°, the approximately vertical line extends from the lower left to the upper right, and when the inclination angle is 100°, the approximately vertical line extends from the lower right to the upper left.

[0089] Using the determined points, as in the first embodiment, the coefficient of determination R between the average value of the angle ω1 and the angle ω2 and the body condition score is calculated. 2 Using the determined points, the coefficient of determination R between the average value of the lengths X1a and X1b and the body condition score was calculated as in the second embodiment. 2 , the coefficient of determination R between the average value of length X2a and length X2b and the body condition score 2 The coefficient of determination R between the average length ratio of length X1a to length X2a (X1a / X2a) and the average length ratio of length X1b to length X2b (X1b / X2b) and the body condition score 2 The experimental results are shown in Table 2.

[0090] [Table 2]

[0091] As shown in Table 2, when the average values ​​of the angles ω1 and ω2 are used, the coefficient of determination R is large when a nearly horizontal line with an inclination angle of -10° to 20° is used and a nearly vertical line with an inclination angle of 80° to 90° is used. 2 When the average value of the length X1a and the length X1b was used, the coefficient of determination R was large when a nearly horizontal line with an inclination angle of -20° to 20° was used and when a nearly vertical line with an inclination angle of 90° was used. 2 When the average value of the length X2a and the length X2b was used, the coefficient of determination R was large when a nearly horizontal line with an inclination angle of -10° to 20° was used and a nearly vertical line with an inclination angle of 80° to 90° was used. 2 When the average value of the length ratio was used, the coefficient of determination R was large when a nearly horizontal line with an inclination angle of -10° to 20° was used and when a nearly vertical line with an inclination angle of 90° was used. 2 From these results, points 403a, 403b on the first curved portions 63a, 63b are determined using an approximately horizontal line with an inclination angle of -10° to 20° from the horizontal direction (left-right direction) in the extracted image 51. Points 404a, 404b on the second curved portions 64a, 64b are determined using an approximately vertical line with an inclination angle of 80° to 90° from the horizontal direction (left-right direction) in the extracted image 51. This allows the beefiness of the cow to be evaluated with high accuracy. From the viewpoint of evaluating the beefiness of the cow with high accuracy, the inclination of the approximately horizontal line is more preferably -5° to 10°, and even more preferably -5° to 5°, and the inclination of the approximately vertical line is more preferably 85° to 90°.

[0092] In the above first and second embodiments, the image acquisition unit 30 acquires an image of a cow in a standing position from approximately directly behind, but may also acquire an image of a cow in a standing position from approximately the front. Fig. 18(a) is an image 50 of a cow in a standing position from approximately directly behind, and Fig. 18(b) is an image 50a of the cow in Fig. 18(a) from approximately the front. As shown in Fig. 18(a), the image is not limited to an image of a cow in a standing position from approximately directly behind, and even if an image of a cow in a standing position is captured from approximately the front, as shown in Fig. 18(b), the image of the cow can be captured so that the contours around the left and right hip angles of the cow are visible.

[0093] 19(a) and 19(b) are extracted images 51 in which the contour line 60 of the cow is extracted from the captured images 50 and 50a of FIG. 18(a) and FIG. 18(b). As shown in FIG. 19(a), even when the image of the cow in a standing position is taken from almost directly behind, as shown in FIG. 19(b), even when the image of the cow in a standing position is taken from almost directly in front, the ridges 61a and 61b corresponding to the waist angle can be present on both the left and right sides of the upper part of the contour line 60. Therefore, even when the captured image 50a in which the cow in a standing position is taken from almost directly in front is used, the beefiness of the cow can be evaluated by the same method as when the captured image 50 taken from almost directly behind is used. In addition, even when the two-dimensional captured image 50a in which the cow in a standing position is taken from almost directly in front is used, as in the case of using the captured image 50 taken from almost directly behind, no special equipment is required to take an image of the cow from above, and the image can be applied to various breeding sites, and a portable information device such as a smartphone, which is highly portable and versatile, can be used as the evaluation device.

[0094] In the above first and second embodiments, the evaluation device for evaluating the beefiness of cattle is a portable information device equipped with an image capturing unit 18 that is carried by an operator and used as an example. However, other cases are also possible. For example, a stationary information device such as a server that can communicate with other devices connected to a network may be used. In this case, the operator transmits an image of the cattle captured using a portable information device such as a smartphone to a stationary information device such as a server via the network. The stationary information device performs the same process as the evaluation device 100 to evaluate the beefiness of the cattle. The stationary information device then transmits the evaluation result of the beefiness of the cattle to a portable information device carried by the operator via the network. This reduces the load on the smartphone. Also, a camera may be installed in the cattle shed so as to be fixed or movable, and the portable information device such as a smartphone and the stationary information device such as a server may acquire an image of the cattle standing upright, captured by the camera installed in the cattle shed, from approximately directly behind or approximately in front of the cattle.

[0095] In the above first and second embodiments, the body condition score is evaluated as the fatness of the cow, but other indices for evaluating the fatness of the cow may be evaluated. In addition, each experiment was performed on dairy cows, but it is considered that beef cows having a similar skeletal structure would have similar results. Therefore, each of the above embodiments can be applied not only to dairy cows but also to beef cows.

[0096] Although the embodiment of the present invention has been described in detail above, the present invention is not limited to such specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention described in the claims. [Explanation of symbols]

[0097] 12 Display section 14 Control section 16 Communications Department 18 Imaging section 20 Memory section 22 Control section 30 Image acquisition unit 32 Extraction part 34 Calculation section 36 Evaluation Section 38 Decision Section 50, 50a Image capture 51 Extracted Images 52 Upper left end point 54 Upper right end point 55, 55a, 55b, 56, 56a, 56b Slant straight line 60 Contour 61a, 61b Yamabe 62a, 62b Vertex 63a, 63b 1st curve section 64a, 64b 2nd curve section 91 Top Point 100 Evaluation Device 403a, 403b points 404a, 404b points 405a, 405b midpoint 406a, 406b points 410a, 410b line segments 412a, 412b line segments 414a, 414b line segments 416a, 416b line segments 420 horizontal line 422a, 422b vertical line 424a, 424b straight line 426 Range

Claims

1. an image acquisition unit for acquiring a two-dimensional image of a cow in a standing position from approximately directly behind or approximately directly in front of the cow; an extraction unit that extracts a contour line of the cow from the captured image; a determination unit that determines a first point on a first curved portion extending from a substantially central point on the contour line of one of two peak portions present on both the left and right sides of an upper portion of the contour line toward the other peak portion, and a second point on a second curved portion extending to an opposite side to the first curved portion; a calculation unit that calculates at least one of a length of a first line segment connecting the first point and the second point, a length of a second line segment connecting a third point at which a straight line passing through an approximate midpoint of the first line segment and approximately perpendicular to the first line segment intersects with the one mountain portion and approximately the midpoint of the first line segment, a ratio of a length of the first line segment to a length of the second line segment, and an angle formed by a third line segment connecting the first point and the third point and a fourth line segment connecting the second point and the third point; A cattle evaluation device comprising: an evaluation unit that evaluates the fleshiness of the cattle from the value calculated by the calculation unit.

2. 2. The cow evaluation device of claim 1, wherein the determination unit determines the point of the first curved portion that protrudes most upward as the first point, and determines the point of the second curved portion that protrudes most laterally as the second point.

3. 3. The cow evaluation device of claim 1 or 2, wherein the determination unit determines as the first point a point where a first line extending in an approximately left-right direction in the captured image first touches one of the peaks when it approaches the one of the peaks from above the one of the peaks, and determines as the second point a point where a second line extending in an approximately up-down direction in the captured image first touches one of the peaks when it approaches the one of the peaks from the side of the one of the peaks.

4. the determination unit determines the first point on the first curved portion and the second point on the second curved portion for the other of the two peak portions; 4. The cattle evaluation device according to claim 1, wherein the calculation unit calculates at least one of the length of the first line segment, the length of the second line segment, the ratio of the length of the first line segment to the length of the second line segment, and the angle formed between the third line segment and the fourth line segment for the other ridge portion, and calculates at least one of the average length of the first line segment for each of the two ridge portions, the average length of the second line segment for each of the two ridge portions, the average ratio of the length of the first line segment to the length of the second line segment for each of the two ridge portions, and the average angle formed between the third line segment and the fourth line segment for each of the two ridge portions.

5. 5. The cattle evaluation device according to claim 1, wherein the two peaks correspond to the hip angles of the cattle.

6. The cattle evaluation device according to claim 1 , wherein the evaluation unit evaluates a body condition score as an evaluation of the beefiness of the cattle.

7. The cattle evaluation device according to claim 1 , further comprising an imaging unit that images the cattle.

8. A contour line of a cow is extracted from a two-dimensional captured image of the cow in a standing position taken from approximately directly behind or approximately directly in front of the cow; determining a first point on a first curved portion extending from a substantially central point on the contour line of one of two peaks present on both the left and right sides of an upper portion of the extracted contour line toward the other peak, and a second point on a second curved portion extending to an opposite side to the first curved portion; calculating at least one of the following: a length of a first line segment connecting the determined first point and the second point; a length of a second line segment connecting a third point at which a straight line passing through the approximate midpoint of the first line segment and approximately perpendicular to the first line segment intersects with the one mountain portion and the approximate midpoint of the first line segment; a ratio of the length of the first line segment to the length of the second line segment; and an angle formed by a third line segment connecting the first point and the third point and a fourth line segment connecting the second point and the third point; The meatiness of the cattle is evaluated from the calculated value. A method for evaluating cattle, characterized in that processing is carried out by a computer.

Images