JP7705145B2 - Cattle evaluation device and cattle evaluation method - Google Patents

Description

The present invention relates to a cow evaluation device and a cow evaluation method.

To evaluate the energy balance in cattle feeding management, 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, methods are known that evaluate a score indicating the body condition of an animal based on a three-dimensional image (e.g., Patent Document 1) and a method that evaluates a score indicating the body condition of an animal based on a two-dimensional image captured of the animal (e.g., Patent Document 2).

Special Publication No. 2012-510278 European Patent No. 2027770

The evaluation method described in Patent Document 1 uses three-dimensional images of the animals to calculate a score indicating the physical condition of the animals, so it is necessary to take images at a specific location where large-scale equipment is installed, making it difficult to apply to a variety of breeding sites. The evaluation method described in Patent Document 2 uses two-dimensional images of the animals, but because it uses two-dimensional images taken from above, it is necessary to take images at a specific location where equipment capable of taking images from above is installed, and like Patent Document 1, it is difficult to apply to a variety of breeding sites.

The present invention has been made in consideration of the above problems, and aims to provide a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites.

The cow evaluation device of the present invention comprises an image acquisition unit that acquires a two-dimensional image of a cow in an upright position taken from behind or from the front, an extraction unit that extracts the contour line of the cow from the captured image, a calculation unit that calculates an index value indicating, as an angle, the degree of inclination of at least one of two peaks on the contour line corresponding to one and the other hip angles of the cow, respectively , and an evaluation unit that evaluates the fleshiness of the cow from the index value calculated by the calculation unit, wherein the peak has a first curved portion extending to one side from a vertex of the peak identified on the contour line, and a second curved portion extending to the other side from the vertex, and the calculation unit identifies a plurality of angles made by a first tangent drawn from a point on the first curved portion and a second tangent drawn from a point on the second curved portion, with the points being different positions, and calculates a value obtained from the multiple identified angles as the index value .
The cow evaluation device of the present invention comprises an image acquisition unit that acquires a two-dimensional image of a cow in an upright position taken from behind or from the front, an extraction unit that extracts the contour line of the cow from the captured image, a calculation unit that calculates an index value indicating, as an angle, the degree of inclination of at least one of two peaks on the contour line that correspond to one and the other hip angles of the cow, respectively, and an evaluation unit that evaluates the fleshiness of the cow from the index value calculated by the calculation unit, wherein the peak has a first curved portion extending to one side from a vertex of the peak identified on the contour line, and a second curved portion extending to the other side from the vertex, and the calculation unit identifies a plurality of angles, with different radii of circles, made up of a first line segment connecting the vertex to a first point where a circle centered on the vertex intersects with the first curved portion, and a second line segment connecting the vertex to a second point where the circle intersects with the second curved portion, and calculates a value obtained from the plurality of identified angles as the index value.

The present invention provides a cattle evaluation device and a cattle evaluation method that can be applied to a variety of breeding sites.

FIG. 1 is a block diagram showing the configuration of a cattle evaluation device according to the first embodiment. FIG. 2 is a functional block diagram of the control unit in the first embodiment. FIG. 3 is an example of a captured image of a cow acquired by the image acquisition unit. FIG. 4 is a diagram (part 1) showing the process executed by the control unit in the first embodiment when evaluating the fleshiness of a cow. FIG. 5 is a diagram (part 2) showing the process executed by the control unit in the first embodiment when evaluating the fleshiness of a cow. 6(a) to 6(c) are images of cows with different body sizes. 7A to 7D are diagrams showing the relationship between the degree of inclination of the peak portion and the angle between the first tangent line and the second tangent line in the first embodiment. FIG. 8 shows the results of an experiment investigating the correlation between body condition score and angle α _min . FIG. 9 is a flowchart showing an example of a method for evaluating beef meatiness in the first embodiment. FIG. 10 is a diagram showing a process executed by the control unit in the second embodiment when evaluating the fleshiness of a cow. FIG. 11 is a diagram showing a process executed by the control unit in the third embodiment when evaluating the fleshiness of a cow. 12A and 12B are diagrams showing the relationship between the degree of inclination of the peak and the angle between a first line segment and a second line segment in the third embodiment. FIG. 13 is a graph showing the relationship between body condition score and standard deviation for multiple angles. FIG. 14 is a graph showing the relationship between body condition score and coefficient of variation for multiple angles. FIG. 15 is a graph showing the relationship between body condition score and the ratio (slope) of the magnitude of change in angle to the magnitude of change in radius of the circle. FIG. 16(a) is an image of a cow in an upright position captured from substantially directly behind, and FIG. 16(b) is an image of the cow in FIG. 16(a) captured from substantially the front. FIGS. 17(a) and 17(b) are images in which the contour lines of the cow are extracted from the captured images of FIGS. 16(a) and 16(b).

First Embodiment
A cow evaluation device 100 according to a first embodiment will be described below with reference to Figs. 1 to 9. Fig. 1 shows a block diagram of the configuration of the cow evaluation device 100 according to the first embodiment. The evaluation device 100 is, for example, a portable information device carried and used by a user. As the evaluation device 100, for example, a smartphone, a tablet computer, a PDA (Personal Digital Assistant), smart glasses, etc. can be adopted. In this first embodiment, the evaluation device 100 is a smartphone. The evaluation device 100 has a telephone function, an e-mail function, a communication function for connecting to the Internet, etc., and a data processing function for executing a program, etc.

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 memory unit 20, and a control unit 22.

The display unit 12 is, for example, an LCD (Liquid Crystal Display) and displays images, various information, and images for operation input such as touch operation buttons.

The operation unit 14 includes a touch panel and a switch. The touch panel accepts information input in response to a user's touch and transmits the accepted operation information to the control unit 22. The touch panel is, for example, incorporated in the display unit 12. Thus, the touch panel accepts various information inputs in response to the user touching the surface of the display unit 12. The switch is an operation member that accepts operations on the evaluation device 100 from the user and transmits the accepted operation information to the control unit 22.

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

The imaging unit 18 includes a lens, an imaging element, an image processing unit, etc., and 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 contours of the cow's left and right hip angles. Therefore, the operator captures an image, for example, 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 cow's left and right hip angles are captured.

The memory unit 20 is a non-volatile semiconductor memory such as a flash memory, and stores various information.

The control unit 22 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc. The control unit 22 controls the entire evaluation device 100 by the CPU executing a program stored in the ROM, etc.

When evaluating the beefiness of a cow, the control unit 22 functions as an image acquisition unit 30, an extraction unit 32, a calculation unit 34, and an evaluation unit 36 as shown in FIG. 2 by the CPU executing a program stored in the ROM or the like.

Figure 3 shows an example of an image 50 of a cow acquired by the image acquisition unit 30. As shown in Figure 3, the image acquisition unit 30 acquires an image 50 of a cow in an upright position, captured from approximately directly behind the cow. The acquired image 50 of the cow 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 acquired image 50 of the cow may also be one stored in the memory 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 that is to be evaluated for fleshiness.

4 and 5 show an example of the process executed by the extraction unit 32 and the calculation unit 34 when evaluating the beefiness of a cow in the first embodiment. FIG. 5 is an enlarged view of the upper part of the contour line 60. In FIG. 5, the upper part of the contour line 60 is shown in a schematic manner for clarity (the same applies to the following similar figures). As shown in FIG. 4, the extraction unit 32 extracts the 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 extraction of the contour line 60 can be performed using a commonly known image processing technique. The extraction unit 32 may display an extracted captured 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 the contour of the cow to be evaluated for beefiness on the display unit 12. The outer shape of the extracted captured 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 captured image 51 and the captured image 50.

There are peaks 61a and 61b on both the left and right sides of the upper part of the contour line 60. Peak 61a has a vertex 62a at the approximate center point of peak 61a on the contour line 60, a first curved portion 63a extending from the vertex 62a to the upper side of the contour line 60, and a second curved portion 64a extending from the vertex 62a to the side of the contour line 60. Similarly, peak 61b has a vertex 62b at the approximate center point of peak 61b on the contour line 60, a first curved portion 63b extending from the vertex 62b to the upper side of the contour line 60, and a second curved portion 64b extending from the vertex 62b to the side of the contour line 60.

The apex 62a of the mountain 61a and the apex 62b of the mountain 61b can be specified, for example, by the following method. For example, a first inclined straight line inclined from the top to the bottom left in the extracted captured image 51 may be moved from the upper left end point 52 of the extracted captured image 51 toward the contour line 60, and the point where the first inclined straight line first touches the contour line 60 may be specified as the apex 62a of the mountain 61a located on the left side. Similarly, a second inclined straight line inclined from the top to the bottom right in the extracted captured image 51 may be moved from the upper right end point 54 of the extracted captured image 51 toward the contour line 60, and the point where the second inclined straight line first touches the contour line 60 may be specified as the apex 62b of the mountain 61b located on the right side. The first and second inclined straight lines are preferably straight lines inclined, for example, by 30° to 60° from the horizontal line in the extracted captured image 51, more preferably by 40° to 50°, and even more preferably by 45°. Also, for example, the apex 62a of the peak 61a may be the point on the contour 60 that is the shortest distance from the upper left end point 52 of the extracted captured image 51, and the apex 62b of the peak 61b may be the point on the contour 60 that is the shortest distance from the upper right end point 54 of the extracted captured image 51. Note that the apex 62a of the peak 61a and the apex 62b of the peak 61b may be identified by a method other than the above method.

The calculation unit 34 calculates an index value indicating the degree of inclination of at least one of the two peaks 61a, 61b present on both the left and right sides of the upper part of the contour line 60. For example, as shown in FIG. 5, the calculation unit 34 specifies an angle α1 between a first tangent 66a at a point on the first curved portion 63a and a second tangent 68a at a point on the second curved portion 64a (the angle of the angle between the first tangent 66a and the second tangent 68a facing the vertex 62a). The calculation unit 34 also specifies an angle α2 between a first tangent 66b at a different point on the first curved portion 63a and a second tangent 68b at a different point on the second curved portion 64a. Furthermore, the calculation unit 34 determines an angle α3 between a first tangent 66c at a further different point on the first curved portion 63a and a second tangent 68c at a further different point on the second curved portion 64a. In this way, the calculation unit 34 determines a plurality of angles between a first tangent at a point on the first curved portion 63a and a second tangent at a point on the second curved portion 64a, with the points being different from each other.

A plurality of tangents can be generated to the peak portion 61a, and the angle between the first tangent at a point on the first curved portion 63a and the second tangent at a point on the second curved portion 64a also varies. The smallest angle among such angles reflects the degree of inclination of the peak portion 61a well. Therefore, in the first embodiment, the calculation unit 34 calculates the smallest angle α _min (e.g., α3 in FIG. 5) among the identified angles α1, α2, α3, ... as an index value indicating the degree of inclination of the peak portion 61a.

The number of angles between the first tangent at a point on the first curved portion 63a and the second tangent at a point on the second curved portion 64a, which are specified by the calculation unit 34, is not particularly limited. However, in order to obtain an angle that reflects the degree of inclination of the peak portion 61a well, it is preferable to vary the positions of the points on the first curved portion 63a and the second curved portion 64a to draw the first tangent and the second tangent, and to specify as many angles as possible. The calculation unit 34 may set points at a predetermined interval on each of the first curved portion 63a and the second curved portion 64a of the contour line 60, and set the straight lines connecting the pixels corresponding to the adjacent points as the first tangent and the second tangent for each combination of adjacent points, and perform a process of determining the angle between the first tangent and the second tangent for each combination of the first tangent and the second tangent that has been executed.

Here, we will explain the relationship between the index value indicating the degree of inclination of the peak portion 61a calculated by the calculation unit 34 and the body condition score. The body condition score is an index indicating the state of body fat deposition, and may be assigned a score of, for example, 1.00 to 5.00, with the higher the value, the more fleshy the body.

Figures 6(a) to 6(c) are images 50a to 50c of cows with different levels of fleshiness. Figure 6(a) is an image 50a of a cow with poor fleshiness, Figure 6(b) is an image 50b of a cow with better fleshiness than the cow in Figure 6(a), and Figure 6(c) is an image 50c of a cow with even better fleshiness. The cow in Figure 6(a) was given a body condition score of 2.25 by an expert. The cow in Figure 6(b) was given a score of 3.00, and the cow in Figure 6(c) was given a score of 4.00. As shown in Figures 6(a) to 6(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 viewed from approximately directly behind a cow in a standing position is different.

Fig. 7(a) to Fig. 7(d) are diagrams showing the relationship between the degree of inclination of the peak 61a and the angle between the first tangent and the second tangent in the first embodiment. Fig. 7(a) to Fig. 7(d) are diagrams showing the upper part of the contour line 60 obtained from the captured image 50 of cows with different body fatness . Fig. 7(a) shows the contour line 60 of a thin cow, Fig. 7(b) shows the contour line 60 of a cow that is fatter (fatter) than the cow in Fig. 7(a), Fig. 7(c) shows the contour line 60 of a cow that is fatter (fatter) than the cow in Fig. 7(b), and Fig. 7(d) shows the contour line 60 of a cow that is fatter (fatter) than the cow in Fig. 7(c). Figures 7(a) to 7(d) show a first tangent 66z and a second tangent 68z that form the smallest angle α _min among the multiple angles identified by a first tangent at a point on the first curved portion 63a and a second tangent at a point on the second curved portion 64a, with the positions of the points being varied.

As shown in Figures 7(a) to 7(d), the beefier the cow, the more rounded the peaks 61a and 61b, which are the portions corresponding to the hip angle, become, and the less the peaks 61a and 61b protrude. Therefore, the more beefier the cow, the larger the angle α _min becomes. Therefore, it is possible to determine the angle between the first tangent at a point on the first curved portion 63a and the second tangent at a point on the second curved portion 64a in at least one of the peaks 61a and 61b, by varying the position of the point, and to evaluate the beefiness of the cow from the smallest angle α _min among the determined angles.

Therefore, an experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the smallest angle α min among the angles determined by the first tangent at a point on the first curved portion 63a of the peak portion 61a and the second tangent at a point on the second curved portion _64a , with the positions of the points being varied. The experiment was conducted on dairy cows (Holstein breed).

FIG. 8 shows the results of an experiment investigating the correlation between the body condition score and the angle α _min . The horizontal axis (X axis) of FIG. 8 is the body condition score evaluated by an expert, and the vertical axis (Y axis) is the angle α _min . A plurality of black circles in FIG. 8 represent each of the dairy cows tested, and the dotted straight line represents an approximation line. As shown in FIG. 8, the larger the angle α _min , the higher the body condition score. The approximation line (dotted straight line) was found to be y = 29.828x - 15.056, and the coefficient of determination R ² was 0.9119. From this, it was confirmed that there is a strong correlation between the body condition score and the angle α _min . Therefore, in this embodiment, the evaluation unit 36 evaluates the beefiness (body condition score) of the cow from the smallest angle α _min calculated by the calculation unit 34 as an index value indicating the degree of inclination of the peak portion 61a.

Returning to Figure 2, the evaluation unit 36 uses score information stored in the memory unit 20 that associates an angle (an index value indicating the degree of inclination of the peak portion) with the body condition score, and evaluates the body condition score from the angle α _min calculated by the calculation unit 34.

Table 1 shows an example of score information stored in the storage unit 20. As shown in Table 1, in the score information, an angle (an index value indicating the degree of inclination of the peak) is associated with a body condition score. For example, the angle is associated with the body condition score such that an angle of less than a° is 1.00, and an angle of a° or more and less than b° is 1.50. Note that, although Table 1 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.

The score information stored in the memory unit 20 may be other than the score information shown in Table 1, as long as it is information that associates the angle with the body condition score. For example, a linear function (y = ax + b) such as the approximate straight line shown in Figure 8 may be stored in the memory unit 20 as the 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.

Next, an example of a method for evaluating beef meatiness in the first embodiment will be described with reference to the flowchart in FIG. 9. The process in FIG. 9 is executed by the control unit 22 of the evaluation device 100. Note that, as a prerequisite for this process, it is assumed that an app for evaluating beef meatiness (evaluation app) has been installed. Also, it is assumed that the memory unit 20 stores score information such as that shown in Table 1, as an example.

In the process of FIG. 9, first, in step S10, the image acquisition unit 30 of the control unit 22 waits until the evaluation app is started. In this case, the process proceeds to step S12 when the control unit 22 starts the evaluation app in response to an operation by the worker (e.g., an input to the operation unit 14 or a voice input to a microphone (not shown)).

When the process proceeds to step S12, the image acquisition unit 30 acquires an image 50 of the cow to be evaluated for meatiness. As described above, the image 50 of the cow is an image of the cow in an upright position captured from approximately directly behind the cow. For example, the image acquisition unit 30 acquires an image of the cow captured by the operator using the image capture unit 18, 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 multiple images of the cow stored in the storage unit 20. 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 image capture unit 18 after the evaluation app is started. In this case, the image of the captured cow and a selection button asking whether or not to select this 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.

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. When extracting the contour line 60, the extraction unit 32 may perform a process to remove background other than the cow from the captured image 50 in order to extract the contour line 60 with good accuracy.

Next, in step S16, the calculation unit 34 of the control unit 22 identifies multiple angles between a first tangent drawn from a point on the first curved portion 63a of at least one of the two peaks 61a, 61b present on both the left and right sides of the upper part of the contour line 60, and a second tangent drawn from a point on the second curved portion 64a, with the positions of the points being different, and calculates the smallest angle among the multiple identified angles as an index value indicating the degree of inclination of the peak 61a.

Next, in step S18, 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 calculated in step S16 as an index value indicating the degree of inclination and the score information such as that in Table 1 stored in the memory unit 20.

Next, in step S20, the evaluation unit 36 displays the body condition score evaluated in step S18 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 associate individual identification information, such as the individual identification number of the cow, input by the operator operating the operation unit 14 with the evaluated body condition score and store it in the memory unit 20. Note that the evaluation unit 36 is not limited to acquiring individual identification information input by the operator 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 barn so that the sensors can detect cows passing through the passages, and the 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. Also, 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.

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. The extraction unit 32 extracts the cow's contour line 60 from the captured image 50. The calculation unit 34 specifies a plurality of angles between a first tangent drawn from a point on the first curved portion 63a of the crest portion 61a and a second tangent drawn from a point on the second curved portion 64a as an index value indicating the degree of inclination of at least one of the two crest portions 61a and 61b present on both the left and right sides of the upper part of the contour line 60, with the positions of the points being different, and calculates the smallest angle among the specified plurality of angles. The evaluation unit 36 evaluates the fleshiness of the cow depicted in the captured image 50 from the angle calculated by the calculation unit 34 as an index value indicating the degree of inclination. In this way, in the first embodiment, the beefiness of the cow is evaluated using the two-dimensional captured image 50 captured from approximately behind the cow in an upright position, so that special equipment for capturing images of the cow in three dimensions or capturing images of the cow from above is not required, and the method can be applied to a variety of breeding sites. In addition, since the beefiness of the cow is evaluated from an 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 well without processing such as normalization. Furthermore, when a person evaluates the beefiness of the cow, the judgment criteria become ambiguous and judgments vary, but in the first embodiment, the control unit 22 judges the beefiness of the cow, so that judgment variation can be suppressed. Furthermore, since the beefiness of the cow is evaluated using the two-dimensional captured image 50 captured from approximately directly behind the cow in an upright position, the evaluation device 100, which is highly portable and highly versatile, such as a smartphone, can be used.

Second Embodiment
The configuration of the cattle evaluation device according to the second embodiment is the same as the configuration of the cattle evaluation device 100 according to the first embodiment in Fig. 1, and therefore will not be illustrated or described again. In the second embodiment, the value calculated by the calculation unit 34 in the functional block diagram of Fig. 2 as an index value indicating the degree of slope of the peak portion is different from that in the first embodiment.

Figure 10 shows an example of the processing executed by the extraction unit 32 and the calculation unit 34 when evaluating the beefiness of a cow in the second embodiment. The processing of the extraction unit 32 is the same as that in the first embodiment, so a description thereof will be omitted. In the second embodiment, as shown in Figure 10, the calculation unit 34 specifies a plurality of angles α1, α2, α3, ... by specifying a plurality of angles between the first tangent drawn from a point on the first curved portion 63a of the mountain portion 61a and the second tangent drawn from a point on the second curved portion 64a while changing the positions of the points. In addition, the calculation unit 34 specifies a plurality of angles β1, β2, β3, ... by specifying a plurality of angles between the first tangent drawn from a point on the first curved portion 63b of the mountain portion 61b and the second tangent drawn from a point on the second curved portion 64b while changing the positions of the points. The calculation unit 34 then calculates the average or total value of the values obtained from the multiple angles α1, α2, α3, ... specified in the peak 61a and the values obtained from the multiple angles β1, β2, β3, ... specified in the peak 61b as an index value indicating the degree of peak inclination. When the evaluation unit 36 determines the body condition score, it can use information such as that in Table 1 that associates angles (index values indicating the degree of peak inclination) with the body condition score, but the angle column is set to a value corresponding to the average or total value.

For example, the calculation unit 34 calculates the average value ((α min + β min )/2) or the sum (α _min + β _min ) of the smallest angle α min among the multiple angles α1, α2, α3, ... identified in the peak portion 61a and the smallest angle β _min among the multiple angles β1, _β2 , _β3 , _... identified in the peak portion 61b, as an index value indicating the degree of inclination.

According to the second embodiment, the average or total value of the values obtained from the multiple angles specified by the peak 61a and the values obtained from the multiple angles specified by the peak 61b is used as an index value indicating the degree of inclination of the peaks 61a and 61b. As a result, even if the cow is photographed at an angle, for example, by using the values obtained from the angles specified by the left and right peaks 61a and 61b, it is possible to reduce errors in determining the fleshiness of the cow due to the cow being photographed at an angle, and to accurately evaluate the fleshiness of the cow.

As in the first and second embodiments described above, the calculation unit 34 identifies multiple angles between a first tangent drawn from a point on the first curved portion of the crest and a second tangent drawn from a point on the second curved portion, with the positions of the points being different, and calculates a value obtained from the multiple identified angles as an index value indicating the degree of slope of the crest. The evaluation unit 36 evaluates the fleshiness of the cow from the index value calculated by the calculation unit 34. This allows for good evaluation of the fleshiness of the cow in a variety of breeding sites.

Third Embodiment
The configuration of the cattle evaluation device according to the third embodiment is the same as the configuration of the cattle evaluation device 100 according to the first embodiment in Fig. 1, and therefore will not be illustrated or described again. In the third embodiment, the value calculated by the calculation unit 34 in the functional block diagram of Fig. 2 as an index value indicating the degree of slope of the peak portion is different from that in the first embodiment.

Figure 11 shows an example of the processing executed by the extraction unit 32 and the calculation unit 34 when evaluating the fleshiness of a cow in the third embodiment. The processing by the extraction unit 32 is the same as that in the first embodiment, so a description thereof will be omitted. As shown in Figure 11, the calculation unit 34 determines an angle δ1 between a first line segment 86a connecting the point where a circle 80a centered on the apex 62a of the mountain portion 61a intersects with the first curved portion 63a and the apex 62a, and a second line segment 88a connecting the point where the circle 80a intersects with the second curved portion 64a and the apex 62a. The calculation unit 34 also determines an angle δ2 between a first line segment 86b that connects the point where a circle 80b, which has a radius different from that of the circle 80a and is centered on the apex 62a of the mountain portion 61a, intersects the first curved portion 63a and the apex 62a, and a second line segment 88b that connects the point where the circle 80b intersects the second curved portion 64a and the apex 62a. The calculation unit 34 also determines an angle δ3 between a first line segment 86c that connects the point where a circle 80c, which has a radius different from that of the circles 80a and 80b and is centered on the apex 62a of the mountain portion 61a, intersects the first curved portion 63a and the apex 62a, and a second line segment 88c that connects the point where the circle 80c intersects the second curved portion 64a and the apex 62a.

In this way, the calculation unit 34 identifies a plurality of angles, with different radii of the circles, between a first line segment connecting the point where a circle centered on the vertex 62a of the mountain portion 61a intersects the first curved portion 63a and the vertex 62a, and a second line segment connecting the point where the circle intersects the second curved portion 64a and the vertex 62a. The radius of the circle is set to a value smaller than the distance between the vertex 62a of the mountain portion 61a and the uppermost point 91 located at the uppermost position of the contour line 60, for example, a value equal to or smaller than half the distance between the vertex 62a and the uppermost point 91.

12(a) and 12(b) are diagrams showing the relationship between the degree of inclination of the peak 61a and the angle between the first and second line segments in the third embodiment. 12(a) and 12(b) show schematic views of the upper part of a contour line 60 obtained from an image 50 of cows with different body builds, with the cow in 12(b) being beefier (i.e., having a higher body condition score) than the cow in 12(a). In 12(a) and 12(b), the corresponding circles have the same ratio of radius to distance between the apex 62a and the top point 91 of the peak 61a.

As shown in Fig. 12(a) and Fig. 12(b), the more fleshy the ridges 61a and 61b, which are the parts corresponding to the waist angle, are, the more rounded the shape. Therefore, the angle between the first line segment and the second line segment formed by the corresponding circle becomes larger as the fleshy part becomes. That is, the angles δa, δb, and δc in Fig. 12(b) are larger than the corresponding angles δa, δb, and δc in Fig. 12(a). Therefore, in at least one of the ridges 61a and 61b, the angle between the first line segment connecting the vertex 62a of the ridge 61a and the point where the circle centered on the vertex 62a intersects with the first curved part 63a and the vertex 62a, and the second line segment connecting the point where the circle intersects with the second curved part 64a and the vertex 62a is determined multiple times with different radii of the circle, and the fleshy part can be evaluated using the determined multiple angles.

Therefore, an experiment was conducted to investigate the correlation between the body condition score evaluated by a veterinarian or other expert and the angle formed by a first line segment connecting the vertex 62a to the point where a circle centered on the vertex 62a of the mountain portion 61a intersects the first curved portion 63a and the vertex 62a, and a second line segment connecting the point where the circle intersects the second curved portion 64a and the vertex 62a, with the radii of the circles being different, and the value obtained from the identified angles. The experiment was conducted on dairy cows (Holstein breed), and four concentric circles were used with radii of 1/2 (L/2), 1/3 (L/3), 1/4 (L/4), and 1/6 (L/6) times the distance L between the vertex 62a and the top point 91 as the circle centered on the vertex 62a.

Table 2 shows the results of an experiment investigating the correlation between the body condition score and the angle formed by the first line segment and the second line segment obtained from a plurality of circles centered on the apex 62a of the mountain 61a. FIG. 13 shows a graph showing the relationship between the body condition score and the standard deviation of the plurality of angles formed by the first line segment and the second line segment obtained from a plurality of circles centered on the apex 62a of the mountain 61a. FIG. 14 shows a graph showing the relationship between the body condition score and the coefficient of variation of the plurality of angles formed by the first line segment and the second line segment obtained from a plurality of circles centered on the apex 62a of the mountain 61a. The horizontal axis (X axis) of FIG. 13 and FIG. 14 is the body condition score evaluated by an expert, and the vertical axis (Y axis) is the standard deviation or the coefficient of variation. The plurality of black circles in FIG. 13 and FIG. 14 represent each of the dairy cows tested, and the dotted straight line represents an approximation straight line.

As shown in Figure 13, the smaller the standard deviation of the angle, the higher the body condition score. The approximate line (dotted line) was calculated as y = -5.994x + 36.488, and the coefficient of determination ^R2 was 0.6808. This confirmed that there is a strong correlation between the body condition score and the standard deviation of the angle.

As shown in Figure 14, the smaller the coefficient of variation of the angle, the higher the body condition score. The approximate line (dotted line) was calculated as y = -0.0465x + 0.2759, and the coefficient of determination ^R2 was 0.7215. This confirmed that there is a strong correlation between the body condition score and the coefficient of variation of the angle.

In this third embodiment, the calculation unit 34 identifies a plurality of angles, with different radii of circles, between a first line segment connecting the point where a circle centered on the vertex 62a of the crest 61a intersects the first curved portion 63a and the vertex 62a, and a second line segment connecting the point where the circle intersects the second curved portion 64a and the vertex 62a, and calculates the standard deviation or coefficient of variation of the identified angles as an index value indicating the degree of inclination of the crest 61a. The evaluation unit 36 then evaluates the beefiness (body condition score) from the standard deviation or coefficient of variation calculated by the calculation unit 34 as an index value indicating the degree of inclination of the crest 61a.

The evaluation unit 36 evaluates the body condition score from the standard deviation or coefficient of variation calculated by the calculation unit 34 using score information stored in the storage unit 20 in which the standard deviation or coefficient of variation is associated with the body condition score. The score information stored in the storage unit 20 may be, for example, the angle column in Table 1 replaced with the standard deviation or coefficient of variation. Note that the score information stored in the storage unit 20 may be other information in which the standard deviation or coefficient of variation is associated with the body condition score. For example, a linear function (y = ax + b) such as the approximate straight line shown in Figures 14 and 15 may be stored in the storage unit 20 as score information. In this case, the body condition score may be evaluated by performing fractional processing such as rounding up, rounding up, or rounding down on the value of x obtained by substituting the standard deviation or coefficient of variation for y.

According to the third embodiment, the calculation unit 34 identifies a plurality of angles, with different radii of the circles, between the first line segment connecting the vertex 62a of the crest 61a and the point where the circle centered on the vertex 62a intersects with the first curved portion 63a, and the second line segment connecting the vertex 62a and the point where the circle intersects with the second curved portion 64a. The evaluation unit 36 evaluates the beefiness of the cow from the standard deviation or coefficient of variation of the plurality of angles calculated by the calculation unit 34 as index values indicating the degree of inclination of the crest 61a. In this case, as in the first embodiment, the beefiness of the cow is evaluated using a two-dimensional image 50 captured from substantially behind the cow in an upright position, so that the method can be applied to a variety of breeding sites. In addition, because the beefiness of the cow is evaluated from an angle, which is information that has 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 well without processing such as normalization. Furthermore, because the control unit 22 judges the beefiness of the cow, variability in the judgment can be suppressed. Furthermore, because the beefiness of the cow is evaluated using a two-dimensional captured image 50 that captures a cow in an upright position from almost directly behind, the evaluation device 100, which is highly portable and versatile, such as a smartphone, can be used.

Fourth embodiment
The configuration of the cattle evaluation device according to the fourth embodiment is the same as the configuration of the cattle evaluation device 100 according to the first embodiment in Fig. 1, and therefore illustration and description thereof will be omitted. In the fourth embodiment, the value calculated by the calculation unit 34 as an index value indicating the degree of inclination of the mountain portion in the functional block diagram of Fig. 2 is different from that in the third embodiment. In this fourth embodiment, the calculation unit 34 specifies a plurality of angles formed by a first line segment connecting the point where a circle centered on the apex 62a of the mountain portion 61a intersects the first curved portion 63a and the apex 62a, and a second line segment connecting the point where the circle intersects the second curved portion 64a and the apex 62a, with different circle radii, and calculates the ratio of the magnitude of change in the plurality of angles to the magnitude of change in the radius of the circle (hereinafter, sometimes referred to as the gradient) as an index value indicating the degree of inclination of the mountain portion 61a.

Figure 15 shows a graph showing the relationship between body condition score and slope, obtained from the experimental results in Table 2. The horizontal axis (X axis) of Figure 15 is the body condition score evaluated by experts, and the vertical axis (Y axis) is the slope. The multiple black circles in Figure 15 represent each of the dairy cows experimented on, and the dotted straight line is an approximation.

As shown in Figure 15, the closer the slope is to 0, the higher the body condition score. The approximate line (dotted line) was calculated as y = 1.2247x - 7.3673, with a coefficient of determination ^R2 of 0.7008. This confirmed that there is a strong correlation between the body condition score and the slope.

Therefore, in the fourth embodiment, the evaluation unit 36 evaluates the beefiness (body condition score) of the cattle from the ratio (slope) of the magnitude of the change in the radius of the circle calculated by the calculation unit 34 as an index value indicating the degree of the slope of the peak 61a. The evaluation unit 36 evaluates the body condition score from the slope calculated by the calculation unit 34 using score information stored in the storage unit 20 in which the slope and the body condition score are associated. The score information stored in the storage unit 20 can be, for example, the angle column in Table 1 changed to slope. Note that the score information stored in the storage unit 20 may be other information as long as it is information in which the slope and the body condition score are associated. For example, a linear function (y = ax + b) such as the approximate straight line shown in FIG. 15 may be stored in the storage unit 20 as score information. In this case, the body condition score may be evaluated by performing a fractional process such as rounding up, rounding up, or rounding down on the value of x obtained by substituting the slope for y.

According to the fourth embodiment, the calculation unit 34 identifies a plurality of angles formed by a first line segment connecting the vertex 62a of the crest 61a and a point where a circle centered on the vertex 62a intersects with the first curved portion 63a, and a second line segment connecting the vertex 62a and a point where the circle intersects with the second curved portion 64a, with different radii of the circles, and calculates the ratio of the magnitude of the change in the plurality of angles to the magnitude of the change in the radius of the circle as an index value indicating the degree of inclination of the crest 61a. The evaluation unit 36 evaluates the beefiness of the cow from the ratio of the magnitude of the change in the radius of the circle calculated by the calculation unit 34 as an index value indicating the degree of inclination of the crest 61a to the magnitude of the change in the plurality of angles. Even in this case, as in the fifth embodiment, the beefiness of the cow can be evaluated well in various breeding sites. In addition, the evaluation of the beefiness of the cow can be performed using an evaluation device that is highly portable and versatile, such as a smartphone.

As in the third and fourth embodiments, the calculation unit 34 identifies a plurality of angles, with different radii of circles, between a first line segment connecting the vertex 62a of the crest 61a and the point where a circle centered on the vertex 62a intersects with the first curved portion 63a, and a second line segment connecting the vertex 62a and the point where the circle intersects with the second curved portion 64a, and calculates values obtained from the identified angles as index values indicating the degree of inclination of the crest 61a. The evaluation unit 36 evaluates the beefiness of the cow from the index values calculated by the calculation unit 34. As described above, this allows the beefiness of the cow to be evaluated well in a variety of breeding sites.

In the above embodiment, the image acquisition unit 30 acquires an image of a cow in a standing position taken from approximately directly behind, but it may also acquire an image of a cow in a standing position taken from approximately the front. FIG. 16(a) is an image 50d of a cow in a standing position taken from approximately directly behind, and FIG. 16(b) is an image 50e of the cow shown in image 50d of FIG. 16(a) taken from approximately the front. As shown in FIG. 16(a), it is not limited to the case where a cow in a standing position is imaged from approximately directly behind. Even if a cow in a standing position is imaged from approximately the front, as shown in FIG. 16(b), it is possible to image the cow so that the contours around the left and right hip angles of the cow are visible.

Figures 17(a) and 17(b) are extracted images 51a and 51b in which the contour line 60 of the cow is extracted from the captured images 50d and 50e in Figures 16(a) and 16(b). As shown in Figure 17(a), even if the image of the cow in a standing position is taken from almost directly behind, as shown in Figure 17(b), the ridges 61a and 61b corresponding to the hip angle can be present on both the left and right sides of the upper part of the contour line 60. Therefore, even if an image of a cow in a standing position taken from almost directly in front is used, the beefiness of the cow can be evaluated by the same method as when an image of a cow taken from almost directly behind is used. In addition, even if a two-dimensional image of a cow in a standing position taken from almost directly in front is used, as in the case of using an image taken from almost directly behind, no special equipment is required to take an image of the cow from above, and it 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.

In the above embodiments, the evaluation device for evaluating the beefiness of the cow is a portable information device equipped with an image capturing unit 18 carried by the worker, 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 worker transmits an image of the cow taken 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 calculates an index value indicating the degree of inclination of at least one of the two peaks 61a, 61b present on both the left and right sides of the upper part of the contour line 60, and evaluates the beefiness of the cow from this index value. The stationary information device then transmits the evaluation result of the beefiness of the cow to a portable information device carried by the worker via the network. This reduces the load on the smartphone. Also, a camera may be installed in the cowshed 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 cow standing in a standing position taken by the camera installed in the cowshed, which is taken from approximately directly behind or approximately in front of the cow.

In the above embodiments, the body condition score is evaluated as the amount of meat a cow has, but other indices for evaluating the amount of meat a cow has may also be evaluated. Also, although Figures 8 and 13 to 15 show the results of experiments on dairy cows, it is believed that beef cows, which have a similar skeletal structure, would have similar results. Therefore, the above embodiments can be applied to beef cows as well as dairy cows.

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

REFERENCE SIGNS LIST 12 display unit 14 operation unit 16 communication unit 18 imaging unit 20 storage unit 22 control unit 30 image acquisition unit 32 extraction unit 34 calculation unit 36 evaluation unit 50, 50a, 50b, 50c, 50d, 50e captured image 51, 51a, 51b extracted captured image 52 upper left end point 54 upper right end point 60 contour line 61a, 61b mountain portion 62a, 62b apex 63a, 63b first curved portion 64a, 64b second curved portion 66a, 66b, 66c, 66z first tangent 68a, 68b, 68c, 68z second tangent 80a, 80b, 80c circle 86a, 86b, 86c first line segment 88a, 88b, 88c Second line segment 91 Top point 100 Evaluation device

Claims (9)

an image acquisition unit for acquiring two-dimensional images of a cow in a standing position from behind or from the front;
an extraction unit that extracts a contour line of the cow from the captured image;
A calculation unit that calculates an index value indicating the degree of inclination of at least one of two peaks corresponding to one and the other hip angles of the cow on the contour line, as an angle;
An evaluation unit that evaluates the beefiness of the cattle from the index value calculated by the calculation unit ,
the mountain portion has a first curved portion extending to one side from a vertex of the mountain portion identified on the contour line, and a second curved portion extending to the other side from the vertex,
The calculation unit identifies multiple angles between a first tangent drawn from a point on the first curved portion and a second tangent drawn from a point on the second curved portion by varying the positions of the points, and calculates the value obtained from the multiple identified angles as the index value . The cow evaluation device according to claim 1 , wherein the calculation unit calculates the smallest angle among the identified plurality of angles as the index value. The cow evaluation device according to claim 1 , wherein the calculation unit calculates an average or total value of values obtained from the multiple angles specified for each of the two peaks as the index value. an image acquisition unit for acquiring two-dimensional images of a cow in a standing position from behind or from the front;
an extraction unit that extracts a contour line of the cow from the captured image;
A calculation unit that calculates an index value indicating the degree of inclination of at least one of two peaks corresponding to one and the other hip angles of the cow on the contour line by an angle;
An evaluation unit that evaluates the beefiness of the cattle from the index value calculated by the calculation unit,
the mountain portion has a first curved portion extending to one side from a vertex of the mountain portion identified on the contour line, and a second curved portion extending to the other side from the vertex,
The calculation unit identifies a plurality of angles formed by a first line segment connecting the vertex to a first point where a circle centered on the vertex intersects with the first curved portion, and a second line segment connecting the vertex to a second point where the circle intersects with the second curved portion, with different circle radii, and calculates a value obtained from the plurality of identified angles as the index value. The cow evaluation device according to claim 4 , wherein the calculation unit calculates a standard deviation or a coefficient of variation of the identified angles as the index value. The cow evaluation device according to claim 4 , wherein the calculation unit calculates, as the index value, a ratio of a magnitude of change in the plurality of angles to a magnitude of change in a radius of the circle. 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. The cow evaluation device according to claim 1 , further comprising an imaging unit that images the cow. Extracting a contour line of a cow from a two-dimensional captured image of the cow in a standing position captured from behind or from the front;
Calculating an index value indicating the degree of inclination of at least one of two peaks corresponding to one and the other hip angles of the cow on the extracted contour line, in terms of an angle;
Evaluate the meatiness of the cattle based on the calculated index value.
The computer executes the process,
the mountain portion has a first curved portion extending to one side from a vertex of the mountain portion identified on the contour line, and a second curved portion extending to the other side from the vertex,
The index value is calculated by identifying a plurality of angles between a first tangent drawn from a point on the first curved portion and a second tangent drawn from a point on the second curved portion, with the positions of the points being different, and calculating the value obtained from the plurality of identified angles as the index value; or by identifying a plurality of angles between a first line segment connecting a first point where a circle centered on the vertex intersects with the first curved portion and the vertex, and a second line segment connecting a second point where the circle intersects with the second curved portion and the vertex, with different radii of the circle, and calculating the value obtained from the plurality of identified angles as the index value .

Images