Cattle evaluation device and cattle evaluation method

Abstract

To provide a cow evaluation device and a cow evaluation method which can be applied to various breeding sites.SOLUTION: A cow evaluation device 100 acquires a two-dimensional photographed image 50 obtained by imaging a cow in a standing position from substantially right behind or substantially the front, extracts a contour line 60 of the cow from the acquired photographed image 50, specifies at least one reference point of a reference point 70 located on a curved part 66a extending to one side and a reference point 72 located on a curved part 68a extending to the other side with a substantial center point 64a on the contour line 60 of at least one crest part 62a of two crest parts 62a, 62b existing on left and right sides on an upper part of the contour line 60 as a boundary, calculates an angle α between a line segment 80 connecting the reference point 70 and a point 74 on the contour line 60 located on the substantial center point 64a from the specified reference point and a line segment 82 connecting the reference point 70 and a point 76 located on a side opposite to the point 74 on the contour line 60 with the reference point 70 held therebetween, and evaluates fleshiness of the cow by using the calculated angle α.SELECTED DRAWING: Figure 8

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 it is judged by humans, the judgment criteria are vague and there is variation in the judgment. Meanwhile, a method is known for evaluating a score indicating the physical condition using images of the cattle (for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2012-510278 [Patent Document 2] International Publication No. 2004 / 012146 Summary of the Invention [Problem to be solved by the invention]

[0004] The evaluation methods described in Patent Documents 1 and 2 calculate a score indicating the physical condition of the cow using images taken from above and behind. This requires photography to be done in a specific location where equipment is installed that can image the cow from above and behind, making it difficult to apply to a variety of farming sites.

[0005] The present invention has been made in consideration of the above-mentioned 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 image of a standing cattle from approximately directly behind or approximately the front, an extraction unit that extracts the contour line of the cattle from the captured image, a reference point identification unit that identifies at least one of a first reference point located on a first curved portion extending to one side of a boundary at an approximately central point on the contour line of at least one of two peaks existing on both the left and right sides of the upper part of the contour line and a second reference point located on a second curved portion extending to the other side, an angle calculation unit that calculates the angle between a first line segment connecting a first point on the contour line located on the approximately central point side of the identified reference point and the reference point, and a second line segment connecting a second point on the contour line opposite the first point across the reference point and the reference point, and an evaluation unit that evaluates the fleshiness of the cattle using the angle calculated by the angle 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 functional configuration of a cow evaluation device according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of the control unit. [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 reference point identification unit. [Figure 6] FIG. 6 is a diagram (part 1) for explaining the process executed by the angle calculation unit. [Figure 7] FIG. 7 is a diagram (part 2) for explaining the process executed by the angle calculation unit. [Figure 8]FIG. 8 is a diagram (part 3) for explaining the process executed by the angle calculation unit. [Figure 9] 9(a) and 9(b) are diagrams (part 1) showing the relationship between the angle calculated by the angle calculation unit and the meatiness of the cow. [Figure 10] FIG. 10(a) and FIG. 10(b) are diagrams (part 2) showing the relationship between the angle calculated by the angle calculation unit and the meatiness of the cow. [Figure 11] 11(a) to 11(d) are graphs showing the results of Experiment 1. [Figure 12] 12(a) and 12(b) are graphs showing the results of Experiment 2. [Figure 13] FIG. 13 is a hardware configuration diagram of the cow evaluation device according to the embodiment. [Figure 14] FIG. 14 is a flowchart showing an example of a method for evaluating beef meatiness according to the embodiment. [Figure 15] FIG. 15 is a graph showing the results of Experiment 3. [Figure 16] FIG. 16 is a diagram showing a case where the points between the two reference points on the contour line used for calculating the angle are different points. [Figure 17] FIG. 17(a) is an image of a cow in an upright position captured from substantially directly behind, and FIG. 17(b) is an image of the cow in FIG. 17(a) captured from substantially the front. [Figure 18] FIGS. 18(a) and 18(b) are extracted images in which the contour lines of the cow are extracted from the captured images of FIGS. 17(a) and 17(b). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] <<Embodiment>> The cow evaluation device 100 according to the embodiment will be described below with reference to the drawings. FIG. 1 shows a block diagram of the functional configuration of the cow evaluation device 100 according to the embodiment. FIG. 2 shows a block diagram of the functional configuration of the control unit 20. In this 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, and a data processing function for executing a program.

[0010] As shown in FIG. 1, the evaluation device 100 includes a display unit 10, an input unit 12, a communication unit 14, an imaging unit 16, a storage unit 18, and a control unit 20.

[0011] The display unit 10 is a display device that displays images, various information, and images for operation input such as touch operation buttons.

[0012] The input unit 12 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 20. The touch panel is incorporated in the display unit 10, for example. Therefore, the touch panel accepts various information inputs in response to the worker's touch on the surface of the display unit 10. The switch is an input member that accepts input from the worker to the evaluation device 100 and transmits the accepted information to the control unit 20.

[0013] The communication unit 14 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 16 is a device that captures images such as still images and videos. The imaging unit 16 captures images in response to an operator carrying the evaluation device 100 operating the input unit 12. For example, when evaluating the fleshiness of a cow, the operator uses the imaging unit 16 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 contours of the cow's left and right hip angles. Therefore, when evaluating the fleshiness of a cow, the operator captures an image of the cow from a position several meters (e.g., 1 m to 2 m) behind the cow up to the cow's feet, so that the contours of the left and right hip angles are captured.

[0015] The memory unit 18 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 fleshiness.

[0016] The control unit 20 is a processing unit that controls each unit of the cow evaluation device 100. As shown in Fig. 2, the control unit 20 has an image acquisition unit 30, an extraction unit 32, a reference point identification unit 34, an angle calculation unit 36, and an evaluation unit 38.

[0017] FIG. 3 shows an example of an image acquired by the image acquisition unit 30. As shown in FIG. 3, for example, the image acquisition unit 30 acquires an image 50 of a cow in a standing 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 16, or an image captured by another device and received by the communication unit 14. The image 50 of the cow to be acquired may be an image selected by the operator using the input unit 12 from among those stored in the storage unit 18. The image acquisition unit 30 may display the acquired image 50 of the cow on the display unit 10. This allows the operator to visually recognize on the display unit 10 the cow to be evaluated for its fleshiness.

[0018] FIG. 4 is a diagram for explaining the process executed by the extraction unit 32. In FIG. 4, curved lines 66a, 66b, 68a, and 68b, which will be described later, are illustrated with thick lines for clarity. As shown in FIG. 4, the extraction unit 32 extracts a contour line 60 that traces the contour of the cow from the captured image 50 of the cow acquired by the image acquisition unit 30. The contour line 60 can be extracted using a generally known image processing technique. The extraction unit 32 may display an extracted image 52 that shows only the extracted contour line 60 of the cow on the display unit 10. This allows the operator to visually recognize on the display unit 10 the contour of the cow to be evaluated for fleshiness. The outer shape of the extracted image 52 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 52 and the captured image 50.

[0019] There are ridges 62a, 62b on both the left and right sides of the upper part of the contour line 60. The ridges 62a, 62b correspond to the hip angles. The ridge 62a has a curved portion 66a that extends toward the cow's back side, with a point 64a at the approximate center of the ridge 62a on the contour line 60 as the boundary, and a curved portion 68a that extends toward the cow's belly side. Similarly, the ridge 62b has a curved portion 66b that extends toward the cow's back side, with a point 64b at the approximate center of the ridge 62b on the contour line 60 as the boundary, and a curved portion 68b that extends toward the cow's belly side.

[0020] FIG. 5 is a diagram for explaining the process executed by the reference point identification unit 34. Note that 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 reference point identification unit 34 identifies at least one of the reference points 70 and 72 for at least one of the two peaks 62a and 62b. In this embodiment, a case where both the reference point 70 and the reference point 72 are identified for the peak 62a of the two peaks 62a and 62b will be described as an example.

[0021] The reference point identification unit 34 identifies a reference point 70 located on a curved portion 66a extending toward the upper side of the contour line 60 with respect to a point 64a at the approximate center of the contour line 60 of the peak 62a as a boundary, and a reference point 72 located on a curved portion 68a extending toward the side. For example, the reference point identification unit 34 moves a first straight line 90 extending generally in the left-right direction in the extracted image 52 from above toward the peak 62a, and identifies the point at which the first straight line 90 first touches the peak 62a as the reference point 70. The reference point identification unit 34 also moves a second straight line 92 extending generally in the up-down direction in the extracted image 52 from the side toward the peak 62a, and identifies the point at which the second straight line 92 first touches the peak 62a as the reference point 72.

[0022] The first straight line 90 may be a horizontal line in the extracted image 52, or may be a straight line tilted relative to the horizontal line. When the first straight line 90 is tilted relative to the horizontal line, it may be a straight line tilted diagonally downward from the center side in the left-right direction of the extracted image 52 toward the peak portion 62a. The tilt angle of the first straight line 90 relative to the horizontal line in the extracted image 52 is described in detail below, but is preferably 20° or less.

[0023] The second straight line 92 may be a perpendicular line in the extracted image 52, or may be a straight line inclined with respect to the perpendicular line. When the second straight line 92 is inclined with respect to the perpendicular line, it may be a straight line inclined from the peak portion 62a side toward the center of the upper side 54 of the extracted image 52. The inclination angle of the second straight line 92 with respect to the horizontal line in the extracted image 52 will be described in detail later, but it is preferable that it is 70° or more.

[0024] It should be noted that the reference point identification unit 34 may identify the reference points 70, 72 by a method other than the above. For example, the closest point on the contour 60 that has the shortest straight-line distance from the upper left corner point 56 of the extracted image 52 may be identified, and two points located on either side of this closest point may be set as the reference points 70, 72. The reference points 70, 72 may be separated from the closest point by approximately the same distance on a straight line or on the contour 60.

[0025] 6 to 8 are diagrams for explaining the process executed by the angle calculation unit 36. Note that FIG. 6 to FIG. 8 are diagrams in which the vicinity of the mountain portion 62a on the contour line 60 is enlarged, and are illustrated diagrammatically for clarity. As shown in FIG. 6, first, the angle calculation unit 36 ​​specifies, for example, a point 74 located between the reference point 70 and the reference point 72 on the contour line 60. For example, the angle calculation unit 36 ​​specifies a point 74 on the contour line 60 that is approximately equal in linear distance from the reference point 70 and the reference point 72, or a point 74 on the contour line 60 that is approximately equal in length along the contour line 60 between the reference point 70 and the reference point 72. For example, the angle calculation unit 36 ​​specifies the midpoint of the line segment connecting the reference point 70 and the reference point 72, and specifies as the point 74 the point at which a line segment that passes through the midpoint and is perpendicular to the line segment connecting the reference point 70 and the reference point 72 intersects with the contour line 60.

[0026] 7, the angle calculation unit 36 ​​identifies a point 76 located on the contour line 60 on the opposite side to the point 74 with respect to the reference point 70, and a point 78 located on the contour line 60 on the opposite side to the point 74 with respect to the reference point 72. For example, the angle calculation unit 36 ​​identifies a point 76 located on the contour line 60 on the opposite side to the point 74 with respect to the reference point 70, and separated from the reference point 70 on the line or on the contour line 60 by approximately the same length as the distance between the reference point 70 and the point 74 on the line or on the contour line 60. The angle calculation unit 36 ​​also identifies a point 78 located on the contour line 60 on the opposite side to the point 74 with respect to the reference point 72, and separated from the reference point 72 on the line or on the contour line 60 by approximately the same length as the distance between the reference point 72 and the point 74 on the line or on the contour line 60.

[0027] 8, the angle calculation unit 36 ​​identifies a line segment 80 connecting the reference point 70 and the point 74 and a line segment 82 connecting the reference point 70 and the point 76, and calculates an angle α between the line segments 80 and 82. Similarly, the angle calculation unit 36 ​​identifies a line segment 84 connecting the reference point 72 and the point 74, and a line segment 86 connecting the reference point 72 and the point 78, and calculates an angle β between the line segments 84 and 86.

[0028] 9(a), 9(b), 10(a) and 10(b) show the relationship between the angles α and β calculated by the angle calculation unit 36 ​​and the fleshiness of the cow. FIG. 9(a) shows the contour line 60 of a thin cow, FIG. 9(b) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 9(a), FIG. 10(a) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 9(b), and FIG. 10(b) shows the contour line 60 of a cow that is fatter (more fleshy) than the cow in FIG. 10(a). For example, FIG. 9(a) shows the upper part of the contour line 60 of a cow whose body condition score was evaluated by an expert as 2.00, and FIG. 9(b) shows the upper part of the contour line 60 of a cow whose body condition score was evaluated as 2.50. FIG. 10(a) shows the upper part of the contour line 60 of a cow whose body condition score was evaluated as 3.00, and FIG. 10(b) shows the upper part of the contour line 60 of a cow whose body condition score was evaluated as 3.50. The body condition score is an index showing the state of body fat deposition, and may be scored from 1.00 to 5.00, with the higher the value, the better the meatiness.

[0029] As shown in Figures 9(a) to 10(b), the higher the body condition score and the more fleshy the cow, the more rounded the peaks 62a, 62b, which correspond to the hip angle. For this reason, it is considered that the angles α and β are larger for beefier cows. Therefore, it is considered that it is possible to evaluate the fleshiness (body condition score) of a cow using at least one of the angles α and β.

[0030] [Experiment 1] Experiment 1 was conducted to investigate the correlation between the body condition score evaluated by experts and the sum of angles α and β (angle α + angle β). Figures 11(a) to 11(d) show the results of Experiment 1. The horizontal axis (x-axis) of Figures 11(a) to 11(d) is the body condition score evaluated by experts, and the vertical axis (y-axis) is the sum of angles α and β (angle α + angle β). The multiple black circles in Figures 11(a) to 11(d) represent each of the dairy cows experimented with, and the dotted straight lines represent approximate straight lines. The experiment was conducted on dairy cows (Holstein breed) (the same applies to Experiments 2 and 3 below).

[0031] 11(a) to 11(d) show experimental results when the inclination angles of the first straight line 90 and the second straight line 92 used to identify the reference points 70 and 72 are different. FIG. 11(a) shows the results when the first straight line 90 is a horizontal line in the extracted image 52 (i.e., the inclination angle with respect to the horizontal line is 0°) and the second straight line 92 is a perpendicular line in the extracted image 52 (i.e., the inclination angle with respect to the horizontal line is 90°). FIG. 11(b) shows the results when the inclination angle of the first straight line 90 with respect to the horizontal line in the extracted image 52 is 10° and the inclination angle of the second straight line 92 with respect to the horizontal line in the extracted image 52 is 80°. FIG. 11(c) shows the results when the inclination angle of the first straight line 90 with respect to the horizontal line in the extracted image 52 is 15° and the inclination angle of the second straight line 92 with respect to the horizontal line in the extracted image 52 is 75°. FIG. 11(d) shows the result when the angle of the first straight line 90 with respect to the horizontal line in the extracted image 52 is set to 20°, and the angle of the second straight line 92 with respect to the horizontal line in the extracted image 52 is set to 70°.

[0032] As shown in FIG. 11(a) to FIG. 11(d), it was confirmed that there is a strong correlation between the body condition score and the sum of the angles α and β (angle α + angle β). For example, as shown in FIG. 11(a), when the first line 90 is a horizontal line and the second line 92 is a perpendicular line, the approximate line is y = 35.174x + 199.16, and the correlation coefficient R is 0.88. As shown in FIG. 11(b), when the first line 90 is inclined 10° from the horizontal line and the second line 92 is inclined 80° from the horizontal line, the approximate line is y = 30.632x + 202.04, and the correlation coefficient R is 0.83. As shown in FIG. 11(c), when the first line 90 is inclined 15° from the horizontal line and the second line 92 is inclined 75° from the horizontal line, the approximate line is y = 20.625x + 231.22, and the correlation coefficient R is 0.89. As shown in FIG. 11(d), when the first line 90 is inclined at 20° from the horizontal line and the second line 92 is inclined at 70° from the horizontal line, the approximate line is y=10.555x+273.02, and the correlation coefficient R is 0.58.

[0033] [Experiment 2] Experiment 2 was conducted to investigate the effect of the inclination angle of the first line 90 and the second line 92 on the correlation coefficient R between the body condition score and the sum of the angles α and β (angle α + angle β). In experiment 2, the inclination angle of the first line 90 from the horizontal line in the extracted image 52 was set to 0°, 10°, 15°, and 20°, and the inclination angle of the second line 92 was set to 70°, 75°, 80°, and 90°, and the correlation coefficient R between the body condition score and the sum of the angles α and β (angle α + angle β) was obtained for each combination.

[0034] Table 1 and Figures 12(a) and 12(b) show the results of Experiment 2. The horizontal axis (x-axis) of Figure 12(a) is the inclination angle of the second straight line 92 from the horizontal line in the extracted image 52, and the vertical axis (y-axis) is the correlation coefficient R. The horizontal axis (x-axis) of Figure 12(b) is the inclination angle of the first straight line 90 from the horizontal line in the extracted image 52, and the vertical axis (y-axis) is the correlation coefficient R. The curves shown in Figures 12(a) and 12(b) are approximation curves. [Table 1]

[0035] As shown in Table 1, FIG. 12(a) and FIG. 12(b), it was confirmed that a strong correlation was obtained between the body condition score and the sum of the angles α and β (angle α + angle β) by identifying the reference point 70 using the first straight line 90 having an inclination angle of 0° or more and 20° or less from the horizontal line in the extracted image 52, and identifying the reference point 72 using the second straight line 92 having an inclination angle of 70° or more and 90° or less from the horizontal line in the extracted image 52. It was confirmed that the inclination angle of the first straight line 90 from the horizontal line in the extracted image 52 is preferably 0° or more and 15° or less from the viewpoint of strengthening the correlation between the body condition score and the sum of the angles α and β (angle α + angle β). It was confirmed that the inclination angle of the second straight line 92 from the horizontal line in the extracted image 52 is preferably more than 70° and 80° or less, more preferably 72° or more and 78° or less, and even more preferably 74° or more and 76° or less.

[0036] 2, as shown in Experiments 1 and 2, there is a strong correlation between the body condition score and the sum of angles α and β (angle α + angle β), and therefore in this embodiment, evaluation unit 38 evaluates the fleshiness of the cow (body condition score) from the sum of angles α and β (angle α + angle β). For example, evaluation unit 38 uses score information stored in memory unit 18 that associates angles with body condition scores, and evaluates the body condition score from the sum of angles α and β (angle α + angle β) calculated by angle calculation unit 36.

[0037] Table 2 shows an example of score information stored in storage unit 18. As shown in Table 2, 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 1.00, and when the angle is equal to or greater than a° and less than b°, the body condition score is 1.50. Note that, although Table 2 shows an example in which the body condition score is in increments of 0.5, other increments are also acceptable. For example, increments of 0.25 are acceptable, or increments of 0.25 are acceptable between 2.00 and 4.00, and increments of 0.50 are acceptable elsewhere. [Table 2]

[0038] The score information stored in memory unit 18 may be score information other than that shown in Table 2, as long as it is information in which the angle and the body condition score are associated with each other. For example, a linear function (y=ax+b) corresponding to the approximated straight lines shown in Figures 11(a) to 11(d) may be stored in memory unit 18 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.

[0039] Fig. 13 is a hardware configuration diagram of the cow evaluation device 100. As shown in Fig. 13, the evaluation device 100 has a storage device 40, a memory 41, a processor 42, a communication interface 43, an input device 44, a display device 45, and an imaging device 46. These components are connected to each other by a bus 48.

[0040] The storage device 40 is a non-volatile semiconductor memory such as a flash memory, and stores a cow evaluation program 47 .

[0041] The memory 41 is hardware that temporarily stores data, such as a dynamic random access memory (DRAM), etc. The storage unit 18 in FIG.

[0042] The processor 42 is hardware such as a CPU (Central Processing Unit) that controls each part of the cow evaluation device 100. The processor 42 executes a cow evaluation program 47 in cooperation with the memory 41. In this way, each function of the control unit 20 in Fig. 2 is realized by the memory 41 and the processor 42 cooperating to execute the cow evaluation program 47.

[0043] The communication interface 43 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 43 realizes the communication unit 14 in FIG.

[0044] The input device 44 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 44 realizes the input section 12 in FIG.

[0045] The display device 45 is hardware for realizing the display unit 10 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 52, the evaluation results of the cow, etc.

[0046] The imaging device 46 is hardware for realizing the imaging unit 16 in FIG. 1, and includes a lens, an imaging element, and the like.

[0047] Next, an example of the method for evaluating beef meatiness according to the embodiment will be described with reference to the flowchart in Fig. 14. The process in Fig. 14 is executed by the control unit 20 of the evaluation device 100. It is assumed that the memory unit 18 stores score information such as that shown in Table 2, for example.

[0048] In the process of Fig. 14, first, in step S10, the image acquisition section 30 of the control section 20 waits until the cow evaluation program 47 is started. In this case, the process proceeds to step S12 when the control section 20 starts the cow evaluation program 47 in response to an operation by an operator (for example, an input operation to the input section 12 or a voice input to a microphone (not shown)).

[0049] 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, for example, an image of the cow in an upright position captured from approximately directly behind the cow. The image acquisition unit 30 acquires, for example, an image of the cow captured by the operator using the imaging unit 16, an image of the cow received from another device via the communication unit 14, or an image of the cow selected by the operator by operating the input unit 12 from among a plurality of images of the cow stored in the storage unit 18. Note that 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 16 after the cow evaluation program 47 is started. When the operator captures an image of the cow using the imaging unit 16, the captured image of the cow and a selection button asking whether or not to select this image may be displayed on the display unit 10.

[0050] In step S14, the extraction unit 32 of the control unit 20 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 52 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 from the captured image 50 in order to extract the contour line 60 with good accuracy.

[0051] Next, in step S16, the reference point identification unit 34 of the control unit 20 identifies a reference point 70 located on a curved portion 66a extending to the upper side of the contour line 60 and a reference point 72 located on a curved portion 68a extending to the side of the contour line 60 with respect to a point 64a at the approximate center of at least one of the two peaks 62a, 62b present on both the left and right sides of the upper part of the contour line 60 (see FIG. 5). For example, the reference point identification unit 34 approaches a first straight line 90 extending generally in the left-right direction in the extracted image 52 from above toward the peak 62a, and identifies the point where the first straight line 90 first hits the peak 62a as the reference point 70. The reference point identification unit 34 also approaches a second straight line 92 extending generally in the up-down direction in the extracted image 52 from the side of the peak 62a toward the peak 62a, and identifies the point where the second straight line 92 first hits the peak 62a as the reference point 72.

[0052] Next, in step S18, the angle calculation unit 36 ​​of the control unit 20 identifies a point 74 located between the reference points 70 and 72 on the contour line 60 (see FIG. 6). For example, the angle calculation unit 36 ​​identifies one point 74 that is located between the reference points 70 and 72 on the contour line 60 and whose distances from the reference points 70 and 72 are approximately the same.

[0053] Next, in step S20, the angle calculation unit 36 ​​identifies a point 76 located on the contour line 60 opposite the point 74 with respect to the reference point 70, and a point 78 located on the contour line 60 opposite the point 74 with respect to the reference point 72 (see FIG. 7). For example, the angle calculation unit 36 ​​identifies the point 76 that is separated from the reference point 70 by a length substantially equal to the distance between the reference point 70 and the point 74. The angle calculation unit 36 ​​also identifies the point 78 that is separated from the reference point 72 by a length substantially equal to the distance between the reference point 72 and the point 74.

[0054] Next, in step S22, the angle calculation unit 36 ​​calculates an angle α between a line segment 80 connecting the reference point 70 and the point 74, and a line segment 82 connecting the reference point 70 and the point 76 (see FIG. 8). The angle calculation unit 36 ​​also calculates an angle β between a line segment 84 connecting the reference point 72 and the point 74, and a line segment 86 connecting the reference point 72 and the point 78 (see FIG. 8).

[0055] Next, in step S24, the evaluation unit 38 of the control unit 20 evaluates the body condition score of the cow captured in the captured image 50 based on the sum of the angles α and β (angle α + angle β) calculated in step S22 and the score information such as Table 2 stored in the memory unit 18.

[0056] Next, in step S26, the evaluation unit 38 displays the body condition score evaluated in step S24 on the display unit 10 and stores it in the memory unit 18. For example, the evaluation unit 38 may display the body condition score on the display unit 10 together with the captured image 50 of the cow. The evaluation unit 38 may store in the memory unit 18 individual identification information, such as the individual identification number of the cow, input by the operator operating the input unit 12, and the evaluated body condition score in association with each other. The input of the individual identification information by the input unit 12 may be performed before step S12 in FIG. 14. Note that the evaluation unit 38 is not limited to acquiring the individual identification information input by the operator operating the input unit 12, but may also acquire the individual identification information from an image captured by the imaging unit 16 of an image of an identification tag attached to the body of the cow, or may acquire the individual identification information by using RFID (Radio Frequency Identification) technology and receiving the individual identification information from an RF tag attached to the body of the cow by the communication unit 14. 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 camera may be acquired by the communication unit 14, and the individual identification information may be acquired from the image of the identification tag shown in the captured image, or the communication device may receive the individual identification information from an RF tag attached to the cow passing through the passage, and the communication unit 14 may receive the individual identification information from the communication device. Also, the evaluation unit 38 may store in the memory unit 18 information correlating the individual identification information of the cow whose body condition score has been evaluated, the captured image 50 of the cow, the image capture date, and the body condition score of the cow.

[0057] As described above, according to this embodiment, the image acquisition unit 30 acquires a two-dimensional captured image 50 obtained by capturing an image of a cow in a standing position from approximately directly behind. The extraction unit 32 extracts a contour line 60 of the cow from the captured image 50. The reference point identification unit 34 identifies a reference point 70 (first reference point) located on a curved portion 66a (first curved portion) extending to one side and a reference point 72 (second reference point) located on a curved portion 68a (second curved portion) extending to the other side, with respect to a point 64a that is approximately in the center of the contour line 60 of one of two peaks 62a, 62b present on both the left and right sides of the upper part of the contour line 60. The angle calculation unit 36 ​​calculates an angle α between a line segment 80 (first line segment) connecting the reference point 70 and a point 74 (first point) on the contour line 60 located on the approximately central point 64a side from the reference point 70, and a line segment 82 (second line segment) connecting the reference point 70 and a point 76 (second point) located on the contour line 60 opposite the point 74 across the reference point 70. The angle calculation unit 36 ​​also calculates an angle β between a line segment 84 (first line segment) connecting the reference point 72 and a point 74 (first point) on the contour line 60 located on the approximately central point 64a side from the reference point 72, and a line segment 86 (second line segment) connecting the reference point 72 and a point 78 (second point) located on the contour line 60 opposite the point 74 across the reference point 72. The evaluation unit 38 evaluates the beefiness of the cow captured in the captured image 50 using the sum of the angles α and β (angle α + angle β) calculated by the angle calculation unit 36. In this way, in this 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 approximately behind, so that special equipment for capturing images of the cow from above is not required and the method can be applied to various breeding sites. In addition, since the beefiness of the cow is evaluated from the angle, which is information having similarity on a two-dimensional image, the evaluation result is less affected by the size of the cow itself or the size of the cow captured in the captured image 50, and the beefiness of the cow can be evaluated without processing such as normalization. Furthermore, when a person evaluates the beefiness of a cow, the judgment criteria become vague and the evaluation varies, but in this embodiment, the control unit 20 evaluates the beefiness of the cow using the captured image 50, so the evaluation variation can be suppressed. Furthermore, since the beefiness of the cow is evaluated using a two-dimensional image 50 captured from approximately directly behind a cow in an upright position, the evaluation device 100 can be a portable information device such as a smartphone, which is highly portable and versatile.

[0058] Furthermore, in this embodiment, the reference point identification unit 34 identifies both the reference points 70, 72, and the angle calculation unit 36 ​​calculates both the angles α and β of the reference points 70, 72. The evaluation unit 38 evaluates the beefiness of the cow using the sum of the angles α and β (angle α + angle β). Since the shape of the cow's hip angle is well represented by both the angles α and β, the beefiness of the cow can be evaluated with high accuracy by evaluating the beefiness of the cow using the sum of the angles α and β (angle α + angle β).

[0059] In the above embodiment, the reference point identification unit 34 identifies both the reference points 70 and 72, the angle calculation unit 36 ​​calculates both the angles α and β, and the evaluation unit 38 evaluates the beefiness of the cow using the sum of the angles α and β (angle α + angle β), but this is not limited to the above. The evaluation unit 38 may evaluate the beefiness of the cow using the product of the angles α and β (angle α × angle β), or may evaluate the beefiness of the cow using a value obtained from the angles α and β other than the sum and product of the angles α and β. Furthermore, the reference point identification unit 34 may identify only one of the reference points 70 and 72, the angle calculation unit 36 ​​calculates the angle at the reference point identified by the reference point identification unit 34, and the evaluation unit 38 may evaluate the beefiness of the cow using the angle calculated by the angle calculation unit 36.

[0060] [Experiment 3] Experiment 3 was conducted to investigate the correlation coefficient R when evaluating the body condition score using the sum of angles α and angle β (angle α + angle β), the product of angles α and angle β (angle α × angle β), angle α, and angle β. In experiment 3, the inclination angles of the first straight line 90 and the second straight line 92 from the horizontal line in the extracted image 52 were changed in various ways, and the correlation coefficient R between the sum of angles α and angle β (angle α + angle β), the product of angles α and angle β (angle α × angle β), angle α, and angle β, and the body condition score was found.

[0061] Table 3 and Fig. 15 show the results of Experiment 3. The horizontal axis (x-axis) of Fig. 15 is the inclination angle of second straight line 92 from the horizontal line in extracted image 52, and the vertical axis (y-axis) is the correlation coefficient R. The correlation coefficient R when the body condition score is evaluated using the sum of angle α and angle β (angle α + angle β) is shown by ◇, the correlation coefficient R when the body condition score is evaluated using the product of angle α and angle β (angle α × angle β) is shown by □, the correlation coefficient R when the body condition score is evaluated using angle α is shown by ◯, and the correlation coefficient R when the body condition score is evaluated using angle β is shown by ×. [Table 3]

[0062] As shown in Table 3 and Figure 15, it was confirmed that there was a strong correlation with body condition score when the sum of angle α and angle β (angle α + angle β), the product of angle α and angle β (angle α × angle β), angle α, and angle β were all used. In particular, it was confirmed that when the sum or product of angle α and angle β was used, the correlation with body condition score was strong over a wide range of the inclination angle of the first line 90 and the second line 92, and when angle α and angle β were used, the correlation with body condition score was strong when the inclination angle of the first line 90 and the second line 92 was a certain predetermined value.

[0063] From the results of Experiment 3, the evaluation unit 38 may evaluate the fleshiness of the cow using the angle α or the angle β, or may evaluate the fleshiness of the cow using the sum or product of the angle α and the angle β. By the evaluation unit 38 evaluating the fleshiness of the cow using the sum or product of the angle α and the angle β, the correlation with the body condition score becomes strong over a wide range of the inclination angles of the first straight line 90 and the second straight line 92, so that the fleshiness of the cow can be evaluated with high accuracy even when the positions and shapes of the peaks 62a, 62b on the contour line 60 in the extracted image 52 vary.

[0064] In this embodiment, as shown in FIG. 6, a point 74 is located between the reference point 70 (first reference point) and the reference point 72 (second reference point) on the contour line 60, and the point used to calculate the angle α (the first point corresponding to the first reference point) and the point used to calculate the angle β (the first point corresponding to the second reference point) are the same point 74. The point 74 is located approximately equidistant from the reference points 70 and 72. The line segments 80, 82, 84, and 86 connecting the intermediate point 74, the reference points 70 and 72, and the points 76 and 78 located on the opposite side of the reference points 70 and 72 from the point 74 reflect the shape of the hip angle of the cow well. Therefore, the beefiness of the cow can be evaluated with high accuracy by evaluating the beefiness of the cow using the angle α and / or the angle β. "Approximately equal distances" means that deviations from exactly the same length are acceptable as long as the beefiness of the cattle can be evaluated with high accuracy. For example, the difference between the distance from reference point 70 to point 74 and the distance from reference point 72 to point 74 is within ±10%, and may be within ±5%.

[0065] Note that the point between the reference point 70 and the reference point 72 on the contour line 60 used to calculate the angle α and the point between the reference point 70 and the reference point 72 on the contour line 60 used to calculate the angle β may be different points. FIG. 16 is a diagram showing a case where the points between the reference point 70 and the reference point 72 on the contour line 60 used to calculate the angles α and β are different points. As shown in FIG. 16, the point 74a (first point corresponding to the first reference point) between the reference point 70 and the reference point 72 on the contour line 60 used to calculate the angle α and the point 74b (first point corresponding to the second reference point) between the reference point 70 and the reference point 72 on the contour line 60 used to calculate the angle β may be different points located at different positions. Even in this case, the beefiness of the cow can be evaluated with high accuracy by evaluating the beefiness using the angle α and / or the angle β.

[0066] 7, the angle calculation unit 36 ​​identifies a point 76 located on the opposite side of the reference point 70 from the point 74 and approximately equidistant to the reference point 70 and the point 74, and identifies a point 78 located on the opposite side of the reference point 72 from the point 74 and approximately equidistant to the reference point 72 and the point 74. In this case, the angle α identified by the line segments 80 and 82 connecting the reference point 70 to the points 74 and 76, and the angle β identified by the line segments 84 and 86 connecting the reference point 72 to the points 74 and 78, adequately represent the shape of the cow's hip angle. Therefore, by evaluating the beefiness of the cow using the angle α and / or the angle β, the beefiness of the cow can be evaluated with high accuracy. "Approximately equal distances" means that deviations from the exact same length are acceptable as long as the beefiness of the cattle can be evaluated with high accuracy, and for example, the difference between the distance from reference point 70 to point 74 and the distance from reference point 70 to point 76 with respect to the distance from reference point 70 to point 74 is ±10% or less, and may be ±5% or less. Similarly, the difference between the distance from reference point 72 to point 74 and the distance from reference point 72 to point 78 with respect to the distance from reference point 72 to point 74 is ±10% or less, and may be ±5% or less.

[0067] The distance between the reference point 70 and the point 74 and the distance between the reference point 70 and the point 76 may not be approximately equidistant. Similarly, the distance between the reference point 72 and the point 74 and the distance between the reference point 72 and the point 78 may not be approximately equidistant. Even if the points 74a and 74b are present between the reference point 70 and the reference point 72 as shown in FIG. 16, the distance between the reference point 70 and the point 74a and the distance between the reference point 70 and the point 76 may not be approximately equidistant. The distance between the reference point 72 and the point 74b and the distance between the reference point 72 and the point 78 may not be approximately equidistant. Even in these cases, the beefiness of the cattle can be evaluated by evaluating the beefiness of the cattle using the angle α and / or the angle β.

[0068] In this embodiment, as shown in FIG. 5, the reference point identification unit 34 moves a first straight line 90 extending generally in the left-right direction in the extracted image 52 from above the peak 62a toward the peak 62a, and identifies the point where the first straight line 90 first touches the peak 62a as the reference point 70. The reference point identification unit 34 also moves a second straight line 92 extending generally in the up-down direction in the extracted image 52 from the side of the peak 62a toward the peak 62a, and identifies the point where the second straight line 92 first touches the peak 62a as the reference point 72. Points 74, 76, and 78 are identified based on the reference points 70 and 72 thus identified, and the angles α and β obtained from the line segments 80, 82, 84, and 86 connecting these points well represent the shape of the cow's hip angle. Therefore, by evaluating the beefiness of the cow using the angle α and / or the angle β, the beefiness of the cow can be evaluated with high accuracy.

[0069] As shown in the results of Experiment 2 described above, the first straight line 90 is preferably a straight line that forms an angle between 0° and 20° with respect to the horizontal line or the horizontal line in the extracted image 52, and that inclines diagonally downward from the center in the left-right direction of the extracted image 52 toward the peak 62a. The second straight line 92 is preferably a straight line that forms an angle between 70° and less than 90° with respect to the vertical line or the horizontal line in the extracted image 52, and that inclines from the peak 62a toward the center of the upper side 54 of the extracted image 52. The first straight line 90 and the second straight line 92 are used to identify points 74, 76, and 78, and the line segments 80, 82, 84, and 86 connecting these points are used to identify the points 74, 76, and 78, and the beefiness of the beef can be evaluated with high accuracy.

[0070] In the above embodiment, the reference points 70, 72 are specified in one of the two peaks 62a, 62b present on both the left and right sides of the upper part of the contour line 60, that is, the peak 62a. However, the reference points 70, 72 may be specified in both the peaks 62a, 62b. In this case, the beefiness of the cow may be determined as an average of the beefiness evaluated using the angles α, β at the reference points 70, 72 of the peak 62a and the beefiness evaluated using the angles α, β at the reference points 70, 72 of the peak 62b. Alternatively, the beefiness of the cow may be evaluated using an average value of the angles α, β at the reference points 70, 72 of the peak 62a and the angles α, β at the reference points 70, 72 of the peak 62b.

[0071] In the above embodiment, the image acquisition unit 30 acquires an image 50 of a cow in a standing position from approximately directly behind, but the image may be acquired from approximately the front of the cow in a standing position. Fig. 17(a) is an image 50 of a cow in a standing position from approximately directly behind, and Fig. 17(b) is an image 50a of the cow in Fig. 17(a) from approximately the front. As shown in Fig. 17(a), the image is not limited to an image of a cow in a standing position from approximately directly behind, and even if the image of a cow in a standing position is captured from approximately the front, as shown in Fig. 17(b), the image can be captured so that the contours around the left and right hip angles of the cow are visible.

[0072] FIG. 18(a) and FIG. 18(b) are extracted images 52 in which the contour line 60 of the cow is extracted from the captured images 50 and 50a of FIG. 17(a) and FIG. 17(b). As shown in FIG. 18(a), even when the image of the cow in a standing position is taken from almost directly behind, as shown in FIG. 18(b), even when the image of the cow in a standing position is taken from almost directly in front, the ridges 62a and 62b 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 evaluation device 100 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 100.

[0073] In the above embodiment, the evaluation device for evaluating the beefiness of cattle is a portable information device equipped with an image capturing unit 16 that is carried by an operator, but other cases are also possible. For example, it may be a stationary information device such as a server that can communicate with other devices connected to a network. 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.

[0074] In the above embodiment, the body condition score is evaluated as the amount of meat in the cow, but other indices that indicate the amount of meat in the cow may be evaluated. Also, although experiments 1 to 3 were performed on dairy cows, it is considered that beef cows having a similar skeletal structure would have similar results. Therefore, the above embodiment can be applied not only to dairy cows but also to beef cows.

[0075] 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]

[0076] 10 Display 12 Input section 14 Communications Department 16 Imaging unit 18 Memory section 20 Control section 30 Image acquisition unit 32 Extraction part 34 Reference point identification part 36 Angle calculation unit 38 Evaluation Section 40 Storage device 41 Memory 42 processors 43 Communication Interface 44 Input Devices 45 Display device 46 Imaging Device 47 Cattle Evaluation Program 48 Bus 50, 50a Image capture 52 Extracted images 54 Top 56 Upper left end point 60 Contour 62a, 62b Mountain 64a, 64b Near center point 66a, 66b, 68a, 68b curved section 70, 72 reference point 74, 74a, 74b, 76, 78 points 80, 82, 84, 86 lines 90 1st straight line 92 Second straight line 100 Cow Evaluation Device

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 reference point specifying unit that specifies at least one of a first reference point located on a first curved portion extending to one side of the contour line and a second reference point located on a second curved portion extending to the other side of the contour line, the first reference point being located on a first curved portion extending to the other side of the contour line, the second reference point being located on a second curved portion extending to the other side of the contour line, the second reference point being located on a second curved portion extending to the other side of the contour line, the second reference point being located on a second curved portion extending to the other side of the contour line, and an angle calculation unit that calculates an angle between a first line segment that connects the reference point and a first point on the contour line that is located on the substantially central point side of the specified reference point, and a second line segment that connects the reference point and a second point that is located on the opposite side of the reference point to the first point on the contour line; and an evaluation unit that evaluates the fleshiness of the cow using the angle calculated by the angle calculation unit.

2. The reference point identification unit identifies both the first reference point and the second reference point, the angle calculation unit calculates the angle at each of the first reference point and the second reference point; The cattle evaluation device according to claim 1 , wherein the evaluation unit evaluates the fleshiness of the cattle using the sum or product of the angles at the first reference point and the second reference point.

3. The reference point identification unit identifies both the first reference point and the second reference point, 3. The cow evaluation device of claim 1, wherein the angle calculation unit identifies a point on the contour line located between the first reference point and the second reference point as the first point corresponding to the first reference point, and identifies a point on the contour line located between the first reference point and the second reference point as the first point corresponding to the second reference point.

4. A cow evaluation device as described in claim 3, wherein the first point corresponding to the first reference point and the first point corresponding to the second reference point are the same point and are located approximately equidistant from the first reference point and the second reference point.

5. 5. The cow evaluation device of claim 3, wherein the angle calculation unit identifies, as the second point corresponding to the first reference point, a point that is approximately equidistant to the distance between the first reference point and the first point corresponding to the first reference point, and identifies, as the second point corresponding to the second reference point, a point that is approximately equidistant to the distance between the second reference point and the first point corresponding to the second reference point.

6. 6. The cattle evaluation device according to claim 1, wherein, when identifying the first reference point, the reference point identification unit approaches a first straight line extending generally in a left-right direction in the extracted image from which the contour line has been extracted from an upper side of the at least one mountain portion toward the at least one mountain portion, and identifies the point where the first straight line first touches the at least one mountain portion, and when identifying the second reference point, the reference point identification unit approaches a second straight line extending generally in a up-down direction in the extracted image from a side of the at least one mountain portion toward the at least one mountain portion, and identifies the point where the second straight line first touches the at least one mountain portion.

7. the first straight line is a horizontal line in the extracted image or a straight line that has an angle with respect to the horizontal line in the extracted image that is greater than 0° and is equal to or smaller than 20° and that slopes obliquely downward from a center side in a left-right direction of the extracted image toward at least one of the mountain portions, The cow evaluation device described in claim 6, wherein the second straight line is a straight line inclined from at least one of the peaks toward the center of the upper side of the extracted image, at an angle of 70° or more and less than 90° with respect to a perpendicular line in the extracted image or a horizontal line in the extracted image.

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

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

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

11. 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; Identifying at least one of a first reference point located on a first curved portion extending to one side of a boundary at a substantially central point on the contour of at least one of two peaks present on both the left and right sides of an upper portion of the contour, and a second reference point located on a second curved portion extending to the other side of the boundary; calculating an angle between a first line segment connecting the reference point and a first point on the contour line located on the substantially central point side of the specified reference point, and a second line segment connecting the reference point and a second point located on the contour line on the opposite side of the reference point to the first point; Using the calculated angle, evaluate the beefiness of the cattle. A method for evaluating cattle, characterized in that processing is carried out by a computer.

Images