JP2021101668A - Estrus diagnosis system, estrus diagnosis method, program and individual identification system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an estrus diagnosis system, an estrus diagnosis method, and a program for detecting an estrus state easily and non-invasively, and an individual identification system. An estrus diagnosis system 100 is different from an acquisition unit 11 that acquires an image captured by a camera 20, an extraction unit 12 that extracts an image of an animal, an identification unit 13 that identifies an individual, and predetermined daily activities. It includes a detection unit 14 for detecting extraordinary behavior and a determination unit 15 for determining the possibility of estrus of an animal. [Selection diagram] Fig. 1

Description

The present invention relates to an estrus diagnosis system, an estrus diagnosis method, and a program, and an individual identification system.

Managing the estrus state of livestock is very important for good livestock management. In the case of free-range livestock, the estrus state can be detected by observing estrus behavior such as standing and mounting. In the case of tethered livestock, the estrus state can be detected by observing changes in the state of the pubic area (swelling, color, etc.) of the livestock and the state of mucus. Such observations are generally made visually. The detection rate of the estrus state based on visual observation is about 70%, which is highly accurate.

However, such a method is laborious and time-consuming, and it is difficult to carry out properly especially in a large-scale farm. Therefore, in recent years, a technique for detecting the estrus state of a cow based on data measured by an accelerometer, a temperature sensor, a pedometer, etc. attached to the cow has been developed and put into practical use (Patent Documents 1 and 2). ).

Japanese Unexamined Patent Publication No. 2018-7613 WO2017 / 183344

In the above-mentioned conventional technique for detecting an estrus state, the estrus state can be detected with high accuracy, particularly when a temperature sensor for measuring the temperature of the vagina is used. However, since the attachment of the sensor is invasive to the body of the livestock, it easily affects the physiological state of the livestock and may have an adverse effect such as mucus becoming cloudy. Further, although the temperature sensor, the acceleration sensor, and the pedometer for measuring the body surface temperature are being put into practical use, erroneous detection and non-detection are likely to occur, and the reliability is inferior. Therefore, there is a need to develop a technique for detecting an estrus state that is non-invasive to the body of livestock and can achieve a detection rate based on visual observation.

One aspect of the present invention is to realize a technique for detecting an estrus state non-invasively and easily.

In order to solve the above problems, the present invention includes the following aspects.
1) An acquisition unit that acquires at least one of a visible light image and an infrared image captured by a camera, an extraction unit that extracts an animal image from the image acquired by the acquisition unit, and an animal extracted by the extraction unit. Based on an identification unit that identifies an individual in an image, a detection unit that detects an extraordinary behavior different from a predetermined daily behavior in the image of the individual identified by the identification unit, and an extraordinary behavior detected by the detection unit. , An estrus diagnosis system including a determination unit for determining the estrus possibility of the animal.
2) The estrus diagnosis system according to 1), wherein the identification unit further extracts skeleton information of the animal from the image of the animal extracted by the extraction unit, and identifies an individual animal based on the skeleton information.
3) The estrus diagnosis system according to 1) or 2), wherein the acquisition unit acquires images captured by using a plurality of cameras.
4) The individual animal identified by the identification unit is further provided with a storage unit that stores daily activities extracted from the tracking images that track the behavior between a plurality of images, and the detection unit is identified by the identification unit. The estrus diagnosis system according to any one of 1) to 39, wherein a behavior different from the daily behavior stored in the storage unit is detected as an extraordinary behavior from an image of an individual animal.
5) The detection unit detects daily behaviors stored in the storage unit and behaviors having different frequencies or durations as extraordinary behaviors from images of individual animals identified by the identification unit as described in 4). Estrus diagnosis system.
6) The detection unit detects as an extraordinary behavior a behavior pattern different from the behavior pattern of daily behavior performed per unit time stored in the storage unit from an image of an individual animal identified by the identification unit. The estrus diagnosis system described in 4).
7) The estrus diagnosis system according to any one of 4) to 6), wherein the storage unit stores the extraordinary behavior in association with the possibility of estrus.
8) The estrus diagnosis system according to any one of 1) to 7), wherein the animal is a domestic animal.
9) Identification that identifies an individual in an acquisition step of acquiring an image captured by a camera, an extraction step of extracting an animal image from the image acquired in the acquisition step, and an animal image extracted in the extraction step. In the image of the individual identified in the step and the identification step, the possibility of estrus of the animal is determined based on the detection step of detecting the extraordinary behavior different from the predetermined daily behavior and the extraordinary behavior detected in the detection step. An estrus diagnosis method including a judgment step to be performed.
10) An estrus diagnosis program for operating a computer as the estrus diagnosis system according to any one of 1) to 8), wherein the acquisition unit, the extraction unit, the identification unit, the detection unit, and the determination unit. A program to make your computer work as.
11) An acquisition unit that acquires an image captured by a camera, an extraction unit that extracts an animal image from the image acquired by the acquisition unit, and an animal skeleton information from the animal image extracted by the extraction unit. An individual identification system including an identification unit that further extracts and identifies an individual animal based on the skeletal information.

The estrus diagnosis system according to each aspect of the present invention may be realized by a computer. In this case, the estrus diagnosis system is made into a computer by operating the computer as each part (software element) included in the estrus diagnosis system. The estrus diagnosis control program of the estrus diagnosis system to be realized and the computer-readable recording medium on which the estrus diagnosis control program is recorded also fall within the scope of the present invention.

According to one aspect of the present invention, the estrus state can be detected non-invasively and easily.

It is a block diagram which shows the main part structure of the estrus diagnosis system which concerns on one Embodiment of this invention. It is a figure explaining the example of the breeding form of the livestock which is the object of the estrus diagnosis by the estrus diagnosis system which concerns on one Embodiment of this invention. It is a figure explaining another example of the breeding form of the livestock which is the object of the estrus diagnosis by the estrus diagnosis system which concerns on one Embodiment of this invention. It is a figure explaining the skeleton information used in the estrus diagnosis system which concerns on one Embodiment of this invention. It is another figure explaining the skeletal information used in the estrus diagnosis system which concerns on one Embodiment of this invention. It is another figure explaining the skeletal information used in the estrus diagnosis system which concerns on one Embodiment of this invention. It is a flowchart which shows the estrus diagnosis processing by the estrus diagnosis system which concerns on one Embodiment of this invention.

[Estrus diagnosis system]
Hereinafter, one embodiment of the present invention will be described in detail. The estrus diagnosis system according to an embodiment of the present invention is a system that identifies an individual from an image and diagnoses the estrus state for each individual. Here, estrus means that the animal is in a state of excitement associated with reproductive activity, and can be a state in which artificial insemination is likely to succeed.

An estrus diagnosis system according to an embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing a main configuration of an estrus diagnosis system according to an embodiment of the present invention. As shown in FIG. 1, the estrus diagnosis system 100 includes an acquisition unit 11, an extraction unit 12, an identification unit 13, a detection unit 14, and a determination unit 15. The acquisition unit 11, the extraction unit 12, the identification unit 13, the detection unit 14, and the determination unit 15 together with the storage unit 16 constitute an estrus diagnosis device 10. Further, the estrus diagnosis system 100 includes a camera 20.

(Diagnosis target)
The animal to be diagnosed by the estrus diagnosis system 100 is a domestic animal. In livestock farming where dairy products, skins, meat, etc. are obtained from livestock, it is extremely important to control the reproduction of livestock. In order to estimate the artificial insemination time of livestock and control breeding, it is desirable to accurately manage the estrus state of livestock for each individual. The estrus diagnosis system 100 can identify individual livestock and diagnose the estrus state of each individual. Examples of livestock to be diagnosed by the estrus diagnosis system include cattle, pigs, sheep, goats, horses, and the like, especially cattle.

With reference to FIGS. 2 and 3, a breeding mode of livestock to be diagnosed by the estrus diagnosis system 100 will be described. FIG. 2 is a diagram illustrating an example of a breeding form of livestock subject to estrus diagnosis by the estrus diagnosis system according to the embodiment of the present invention, and FIG. 3 is a diagram for explaining an example of a livestock breeding mode according to the embodiment of the present invention. It is a figure explaining another example of the breeding form of the livestock which is the object of the estrus diagnosis by.

The estrus diagnosis system 100 can diagnose the free-range livestock 200 in which a plurality of livestock are free-ranged in the controlled area 300 as shown in FIG. In addition, the estrus diagnosis system 100 can also diagnose a tethered livestock 200 that is bred in a chain or the like in an indoor partitioned area 400 as shown in FIG. Since the estrus diagnosis system 100 identifies an individual from an image and diagnoses the estrus state for each individual, it is possible to diagnose the estrus state for each individual regardless of whether the livestock is free-range or tethered.

(camera)
The camera 20 included in the estrus diagnosis system 100 images an animal to be diagnosed. The image captured by the camera 20 is sent to the acquisition unit 11. The camera 20 may be controlled to continuously take an image for a predetermined period of time, or may be controlled to take an image based on an input from a user. In the camera 20, control of imaging, lens orientation, angle of view, focus, zoom adjustment, and the like is controlled by a control unit (not shown) of the estrus diagnosis device 10.

The estrus diagnosis system 100 preferably includes a plurality of cameras 20. As a result, a plurality of images taken from various directions can be obtained, so that individual identification and estrus diagnosis can be performed more accurately based on these images. The number of cameras 20 is not particularly limited. The installation position of the camera 20 is not particularly limited, but it is preferable to install the camera 20 at a position that does not interfere with the behavior of the animal and that widens the imageable range.

When imaging the free-range livestock shown in FIG. 2, for example, the camera 20 is installed outside the controlled area 300 at a position where the livestock can be imaged from diagonally above. Further, in the case of photographing the livestock of the tethered animal shown in FIG. 3, for example, the camera 20 is installed at a position where the image can be taken from diagonally above in each area 400. When imaging a livestock in a tethered house, the cameras 20 may be installed either in front of or behind the livestock, but it is preferable to install the cameras 20 in both of them.

The camera 20 is at least one of a visible light camera and an infrared camera. The camera 20 preferably includes at least one visible light camera and at least one infrared camera. Thereby, for example, by taking an image with a visible light camera in the daytime and taking an image with an infrared camera at night, it is possible to take an image of an animal day or night.

The visible light camera includes an optical system such as a lens, a light detection element, and the like, detects light from a subject, and generates visible light image data. An infrared camera includes an optical system such as a lens, an infrared detection element, and the like, and detects infrared rays emitted from a subject to generate infrared image data. The infrared image is a color representation of the temperature of each part of the subject.

(Acquisition department)
The acquisition unit 11 acquires at least one of a visible light image and an infrared image captured by the camera 20. The acquisition unit 11 acquires at least one of a visible light image and an infrared image as a moving image. The acquisition unit 11 acquires a plurality of images captured by the plurality of cameras 20. The acquisition unit 11 is implemented as a wireless or wired communication interface. The acquisition unit 11 sends the acquired image data to the extraction unit 12. Further, the acquisition unit 11 may send the acquired image data to the storage unit 16.

(Extractor)
The extraction unit 12 extracts an image of an animal from the image acquired by the acquisition unit 11. The extraction unit 12 extracts an animal image from each of the plurality of images acquired by the acquisition unit 11. For example, the extraction unit 12 acquires the information of the feature points in the animal image stored in advance in the storage unit 16 and detects the feature points in the image captured by the camera 20. Information on feature points in an animal image includes, for example, the position or shape of the animal's eyes, nose, mouth, ears, horns, tail, hooves, and the like. The process of extracting an animal image in the extraction unit 12 can be executed by using a conventionally known image analysis technique. The extraction unit 12 may perform extraction processing according to the type of image (visible light image, infrared image, etc.) acquired by the acquisition unit 11.

(Identification section)
The identification unit 13 identifies an individual in the image of the animal extracted by the extraction unit 12. The identification unit 13 identifies an individual among a plurality of images of an animal. The individual identification process by the identification unit 13 is a process for distinguishing one animal from another animal in an animal image. The identification unit 13 sends the identification result to the detection unit 14.

The identification unit 13 acquires characteristic information representing the characteristics of the animals shown in these images from the images of the animals, and identifies the individual animal based on the characteristic information. The characteristic information representing the characteristics of the animal includes the skeleton information, the body shape, the hair pattern, the shape of the part, the posture, the behavior, the gait, the flow line, the place of stay, and the like. The identification unit 13 may perform identification processing according to the type of image (visible light image, infrared image, etc.) acquired by the acquisition unit 11.

In addition, the identification unit 13 may identify an individual by reading, for example, an identification number written on a tag attached to an animal's ear or the like or a marking attached to the body from an image. Further, the identification unit 13 may identify an individual by combining an IC tag attached to the animal, a radio beacon, and a technique for identifying a unique signal transmitted from an acceleration sensor. Further, in the case where the camera 20 is provided for each individual in the livestock of the tethered breeding, the individual may be identified by associating the identification number of the camera 20 with the individual.

<Skeletal detection>
The identification unit 13 may further extract the skeleton information of the animal from the image of the animal extracted by the extraction unit 12, and identify the individual animal based on the skeleton information. The identification unit 13 extracts skeletal information from a plurality of images of an animal and identifies an individual animal among the plurality of images.

Animal skeletal information can be extracted using, for example, known systems such as OpenPose, DeepPose, DeepLabCut and the like. Techniques for obtaining bovine skeleton information in images are described in Reference 1 below:
Reference 1: Xiangyuan Li et al., Computers and Electronics in Agriculture 164 (2019) 104885.
Here, reference 1 in its entirety is incorporated herein by reference.

The skeleton information of an animal is both information indicating an animal and information indicating an animal part. Animal skeletal information may include, for example, the position of the animal's joints, the position of the tip of the animal's part, the distance between adjacent joints, and the like.

For example, in an animal image, the identification unit 13 extracts a skeleton pattern obtained from the coordinates of a marker representing the position of a joint forming the animal skeleton, the tip of a portion, or the like as animal skeleton information. The marker included in the skeletal pattern is not particularly limited, but may be, for example, a site to which a numerical value is given in the bovine model shown in FIG. FIG. 4 is a diagram for explaining skeletal information used in the estrus diagnosis system according to the embodiment of the present invention, and is a side view and a top view of a cow model.

As shown in FIG. 4, the skeletal pattern is, for example, in bovine, 1: nose tip, 2: left ear tip, 3: left ear base, 4: crown, 5: right ear base, 6: right ear tip, 7: Left elbow joint, 8: instep, 9: right elbow joint, 10: dorsal bay, 11: left lumbar angle (iliac / iliac), 12: cross, 13: right lumbar angle (ilium / iliac) , 14: Left ilium, 15: Caudal vertebra, 16: Right ilium, 17: Left carpal joint, 18: Left hoof (anterior), 19: Right carpal joint, 20: Right hoof (anterior), 21: Left knee joint, 22: Left ankle joint, 23: Left hoof (posterior), 24: Right knee joint, 25: Right ankle joint, 26: Right hoof (posterior), and 27: Includes markers selected from the tip of the tail. Although FIG. 4 shows a case where the skeleton pattern includes 27 markers, the position and number of markers are not limited to this.

The skeletal pattern is information unique to each individual animal. The identification unit 13 obtains a skeleton pattern for each individual animal from an image of the animal, for example, as shown in FIGS. 5 and 6. 5 and 6 are diagrams for explaining skeletal information used in the estrus diagnosis system according to the embodiment of the present invention, FIG. 5 is a visible light image of a free-range cow, and FIG. 6 is a tethered cow. It is a visible light image of. In addition, in FIG. 5 and FIG. 6, only some markers are numbered and displayed for convenience of explanation.

As shown in FIG. 5, the markers M1, M2, and M3 in the cow 201 and the markers M1', M2', and M3'in the cow 202 are attached to the same site. In cow 201, the skeletal pattern including the straight line shown by B1 connecting M1 and M2 and the straight line shown by B2 connecting M2 and M3 is the straight line shown by B1'connecting M1'and M2'in cow 202. And the skeletal pattern including the straight line shown in B2'connecting between M2'and M3'.

As shown in FIG. 6, the markers M4, M5, and M6 in bovine 203 and the markers M4', M5', and M6'in bovine 204 are attached to the same site. In bovine 203, the skeletal pattern including the straight line shown by B3 connecting M4 and M5 and the straight line shown by B4 connecting M5 and M6 is the straight line shown by B3'connecting M4'and M5'in bovine 204. And the skeletal pattern including the straight line shown in B4'connecting between M5'and M6'.

Therefore, the identification unit 13 compares the skeleton pattern of each individual animal stored in the storage unit 16 in advance with the skeleton pattern in the image of the animal extracted by the extraction unit 12, and determines the degree of similarity thereof. , Can identify individual animals. The skeleton pattern for each individual animal may be obtained, for example, by accumulating and classifying a plurality of skeleton patterns extracted from animal images.

(Detection unit)
The detection unit 14 detects an extraordinary behavior different from a predetermined daily behavior in the image of the individual identified by the identification unit 13. The detection unit 14 acquires a predetermined daily action stored in the storage unit 16 in advance, and compares it with the action in the image in which the individual identified by the identification unit 13 is captured. Then, when the behavior of the individual in the image is different from the daily behavior, the detection unit 14 detects the behavior of the individual as an extraordinary behavior. The detection unit 14 sends the detection result to the determination unit 15.

A daily behavior is a behavior extracted from a tracking image that tracks the behavior of an animal among a plurality of images. In addition, the daily behavior may be a behavior extracted from a tracking image in which the behavior of the animal in the non-estrus period is tracked for each individual among a plurality of images. Animals are known to behave differently during estrus and non-estrus. Therefore, it can be assumed that the extraordinary behavior different from the daily behavior is the behavior during the estrus period. Daily activities are extracted in advance and stored in the storage unit 16.

The predetermined daily behavior used by the detection unit 14 in the detection process may be common to the animals to be diagnosed, but is preferably different for each individual. The daily behavioral patterns of animals can vary from individual to individual. Therefore, it is possible to detect extraordinary behavior more accurately because the predetermined daily behavior is different for each individual. When the daily behavior is different for each individual, the detection unit 14 acquires a predetermined daily behavior of the individual identified by the identification unit 13 from the storage unit 16 and compares it with the behavior of the individual in the image.

The detection unit 14 detects the daily behavior stored in the storage unit 16 and the behavior having a different frequency or duration as the extraordinary behavior from the image of the individual animal identified by the identification unit 13. Extraordinary behaviors differ in frequency and duration from daily behaviors. For example, if the cow's roaring behavior is less than 5 times within a predetermined time in daily behavior, and if the cow's roaring behavior in the image is 5 times or more within a predetermined time, the behavior is detected as an extraordinary behavior. To do. Further, for example, when the standing time of the cow is less than 30 minutes within the predetermined time in daily activities, and the standing time of the cow within the predetermined time in the image is 30 minutes or more, the detection unit 14 may perform the detection unit 14. , The behavior is detected as an extraordinary behavior.

The detection unit 14 detects as an extraordinary behavior a behavior pattern different from the behavior pattern of the daily behavior performed per unit time stored in the storage unit 16 from the image of the individual animal identified by the identification unit 13. Behavioral patterns of extraordinary behavior can differ from behavioral patterns of daily behavior. For example, a standing that allows a cow to ride another cow is performed only during the cow's estrus and is not routinely performed outside the estrus. Therefore, if the cow in the image is standing, the detection unit 14 detects the behavior as an extraordinary behavior.

Examples of behaviors of animals to be detected by the detection unit 14 include standing, mounting, following other animals or sniffing behavior of the vulva, raising behavior, tailing behavior, roaring behavior, standing state, and sitting state. , Walking, running, etc.

(Judgment unit)
The determination unit 15 determines the estrus possibility of the animal based on the extraordinary behavior detected by the detection unit 14. Behaviors of animals in estrus generally include standing, mounting, follow-up to other animals or increased vulvar sniffing behavior, increased number of tails and time, increased number of tail swings and time, number of roars and time. Is known to increase, standing time increases, walking amount or running amount (activity amount) increases, and the like. The determination unit 15 determines whether or not the extraordinary behavior detected by the detection unit 14 is the behavior of the animal in the estrus period, and determines the estrus possibility of the animal.

When the pattern, number of times, duration, etc. of the extraordinary behavior detected by the detection unit 14 are equal to or greater than a predetermined threshold value, the determination unit 15 determines that the behavior of the animal is in estrus. The threshold value may be set for each action, or may be set for each action pattern in which a plurality of actions are combined.

The determination unit 15 may determine the possibility of estrus by determining a plurality of extraordinary behaviors in a complex manner. For example, the determination unit 15 does not determine that the animal is in estrus when only the standing time increases, and determines that the animal is in estrus when both the standing time and the amount of activity increase. judge.

The determination unit 15 may determine the ratio of estrus possibility. For example, the determination unit 15 determines that the possibility of estrus is 100% when the extraordinary behavior is standing, and determines the possibility of estrus as 50% when the extraordinary behavior is mounting.

The determination unit 15 may determine the possibility of estrus in consideration of the estrous cycle. Even if the animal is not in estrus, it may behave differently from its daily behavior even when it is in a state of excitement due to other factors. When the determination unit 15 determines in consideration of the estrous cycle, it is possible to distinguish between the behavior during the estrus period and other extraordinary behaviors. For example, since the estrous cycle of cattle is about 21 days, the judgment unit 15 determines that the extraordinary behavior in the period around 21 days from the previous estrus period is the behavior in the estrus period, and the extraordinary behavior in other periods is Do not judge it as an action during estrus.

The determination unit 15 may acquire information relating the extraordinary behavior and the estrus possibility stored in the storage unit 16 in advance, and determine the estrus possibility of the extraordinary behavior detected by the detection unit 14.

(Memory)
The storage unit 16 stores a program for realizing the function of the estrus diagnosis device 10. In addition, the storage unit 16 stores the daily behavior of the individual animal identified by the identification unit 13 extracted from the tracking image that traces the behavior between the plurality of images. Further, the storage unit 16 stores the image data acquired by the acquisition unit 11, the information representing the feature points in the animal image used by the extraction unit 12, the information representing the skeleton pattern of each individual, the extraordinary behavior and the possibility of estrus. Store the associated information, etc.

The storage unit 16 stores a database in which a plurality of tables are stored. The database stores, for example, a table that associates extraordinary behavior with estrus for each individual animal, and a table that associates general-purpose extraordinary behavior with estrus regardless of the individual. In addition, the database stores a table in which data for identifying individual animals and daily activities are associated with each other, and a table in which data for identifying individual animals and skeletal patterns are associated with each other.

In the database stored in the storage unit 16, the table relating the extraordinary behavior and the possibility of estrus and the table in which the daily behavior of each individual is stored may be updated as necessary.

(Estrus diagnosis processing)
The estrus diagnosis process using the estrus diagnosis system 100 will be described with reference to FIG. 7. FIG. 7 is a flowchart showing an estrus diagnosis process by the estrus diagnosis system according to the embodiment of the present invention. The following estrus diagnosis process is a process controlled by a control unit (not shown) of the estrus diagnosis device 10.

As shown in FIG. 7, first, an image captured by the camera 20 is acquired (step S1). In step S1, the acquisition unit 11 acquires an image from the camera 20. The acquisition unit 11 sends the acquired image to the extraction unit 12. Next, an animal image is extracted from the image acquired in step S1 (step S2). In step S2, the extraction unit 12 extracts an image of the animal from the image. The extraction unit 12 sends an image of the extracted animal to the identification unit 13.

Then, the individual is identified in the image of the animal extracted in step S2 (step S3). In step S3, the identification unit 13 identifies the individual in the image of the animal. The identification unit 13 sends the identification result of the individual to the detection unit 14. Next, in the image of the individual identified in step S3, an extraordinary behavior different from the predetermined daily behavior is detected (step S4). In step S4, the detection unit 14 detects an extraordinary behavior different from the predetermined daily behavior in the image of the identified individual. The detection unit 14 sends the detection result of the extraordinary behavior to the determination unit 15.

Then, based on the extraordinary behavior detected in step S4, the possibility of estrus of the animal is determined (step S5). In step S5, the determination unit 15 determines the possibility of estrus of the animal. The determination unit 15 notifies the user of the determination result of the possibility of estrus by displaying it on a display device (not shown) or the like. Further, the determination unit 15 may store the determination result of the possibility of estrus in the storage unit 16.

In the estrus diagnosis system 100, an animal is constantly photographed by the camera 20 day and night. Therefore, by performing a series of processes from step S1 to step S5 every time an image is acquired, the estrus diagnosis of the animal is always performed. It can be carried out.

Further, according to the above method, an acquisition step (step S1) of acquiring an image captured by the camera 20, an extraction step (step S2) of extracting an animal image from the image acquired in the acquisition step, and extraction. An identification step (step S3) for identifying an individual in the image of the animal extracted in the step, and a detection step (step S4) for detecting an extraordinary behavior different from a predetermined daily behavior in the image of the individual identified in the identification step. An estrus diagnosis method including the determination step (step S5) for determining the estrus possibility of the animal based on the extraordinary behavior detected in the detection step is realized.

Since the estrus diagnosis system determines the estrus possibility of an animal based on the image of the animal, it is possible to easily diagnose the estrus without constantly visually checking the behavior of the animal or collecting body fluid from the animal. Can be done. In addition, the estrus diagnosis system is non-invasive because it is not necessary to attach a sensor to the animal, and the burden on the animal is small. Further, since the estrus diagnosis system diagnoses estrus based on a preset standard, there is no variation in the diagnosis and the diagnosis is highly reliable.

[Individual identification system]
The individual identification system according to the embodiment of the present invention includes an acquisition unit that acquires an image captured by a camera, an extraction unit that extracts an animal image from the image acquired by the acquisition unit, and an animal extracted by the extraction unit. It is provided with an identification unit that further extracts the skeleton information of the animal from the image of the above and identifies an individual animal based on the skeleton information.

The individual identification system is a system for identifying an individual animal based on skeletal information extracted from an image. The individual identification system includes an individual identification device including an acquisition unit 11, an extraction unit 12, and an identification unit 13 of the above-mentioned estrus diagnosis system 100, and a camera 20. The individual identification device may further include a storage unit 16.

Since the individual identification system identifies an individual animal based on the skeleton information extracted from the image, it is not necessary to attach an IC tag or a radio beacon to the individual animal or to provide a receiver for receiving a signal. Since the individual identification system can identify an individual animal only by acquiring an image of the animal, individual management of the animal is easy.

[Example of realization by software]
The control block (acquisition unit 11, extraction unit 12, identification unit 13, detection unit 14, and determination unit 15) of the estrus diagnosis device 10 included in the estrus diagnosis system 100 is a logic circuit formed in an integrated circuit (IC chip) or the like. It may be realized by (hardware) or by software.

In the latter case, the estrus diagnostic apparatus 10 includes a computer that executes instructions of a program that is software that realizes each function. The computer includes, for example, one or more processors and a computer-readable recording medium that stores the program. Then, in the computer, the processor reads the program from the recording medium and executes it, thereby achieving the object of the present invention. As the processor, for example, a CPU (Central Processing Unit) can be used. As the recording medium, a "non-temporary tangible medium", for example, a ROM (Read Only Memory) or the like, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, a RAM (Random Access Memory) for expanding the above program may be further provided. Further, the program may be supplied to the computer via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. In addition, one aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims, and the embodiments obtained by appropriately combining the technical means disclosed in the different embodiments. Is also included in the technical scope of the present invention.

The present invention can be used in the livestock field.

10 Estrus diagnosis device 11 Acquisition unit 12 Extraction unit 13 Identification unit 14 Detection unit 15 Judgment unit 16 Storage unit 20 Camera 100 Estrus diagnosis system

Claims (11)

An acquisition unit that acquires at least one of a visible light image and an infrared image captured by a camera, and
An extraction unit that extracts an animal image from the image acquired by the acquisition unit, and an extraction unit.
In the image of the animal extracted by the extraction unit, the identification unit that identifies the individual and the identification unit
In the image of the individual identified by the identification unit, a detection unit that detects an extraordinary behavior different from a predetermined daily behavior, and a detection unit.
An estrus diagnosis system including a determination unit for determining the estrus possibility of the animal based on the extraordinary behavior detected by the detection unit. The estrus diagnosis system according to claim 1, wherein the identification unit further extracts skeleton information of the animal from the image of the animal extracted by the extraction unit, and identifies an individual animal based on the skeleton information. The estrus diagnosis system according to claim 1 or 2, wherein the acquisition unit acquires images captured by using a plurality of cameras. An individual animal identified by the identification unit is further provided with a storage unit that stores daily activities extracted from tracking images that track the behavior between a plurality of images.
The detection unit detects any behavior different from the daily behavior stored in the storage unit as an extraordinary behavior from an image of an individual animal identified by the identification unit, according to any one of claims 1 to 3. Described estrus diagnostic system. The fourth aspect of claim 4, wherein the detection unit detects daily behaviors stored in the storage unit and behaviors having different frequencies or durations as extraordinary behaviors from an image of an individual animal identified by the identification unit. Estrus diagnosis system. The detection unit detects, as an extraordinary behavior, a behavior pattern different from the behavior pattern of daily behavior performed per unit time stored in the storage unit from an image of an individual animal identified by the identification unit. The estrus diagnosis system according to 4. The estrus diagnosis system according to any one of claims 4 to 6, wherein the storage unit stores the extraordinary behavior in association with the possibility of estrus. The estrus diagnosis system according to any one of claims 1 to 7, wherein the animal is a domestic animal. The acquisition step of acquiring the image captured by the camera, and
An extraction step of extracting an animal image from the image acquired in the acquisition step,
In the animal image extracted in the extraction step, an identification step for identifying an individual and an identification step
In the image of the individual identified in the identification step, a detection step for detecting an extraordinary behavior different from a predetermined daily behavior, and a detection step.
An estrus diagnosis method including a determination step of determining the estrus possibility of the animal based on the extraordinary behavior detected in the detection step. An estrus diagnosis program for operating a computer as the estrus diagnosis system according to any one of claims 1 to 8, wherein the acquisition unit, the extraction unit, the identification unit, the detection unit, and the determination unit are used. A program to make your computer work as. An acquisition unit that acquires images captured using a camera,
An extraction unit that extracts an animal image from the image acquired by the acquisition unit, and an extraction unit.
An individual identification system including an identification unit that further extracts skeleton information of the animal from the image of the animal extracted by the extraction unit and identifies an individual animal based on the skeleton information.

Images