Information processing device, information processing method, and information processing program

Abstract

The present invention provides a technology for easily implementing livestock breeding management in consideration of animal welfare. The present invention captures images of livestock animals, acquires identifiers of the livestock animals, and saves, in a storage unit, the acquired identifiers and the captured images in association with each other. In addition, the present invention compares the images, captured at different times, of the livestock animal that is identified by the same identifier, and notifies a switch of the livestock animal that is identified by the same identifier, when a change of the livestock animal, which cannot occur in a prescribed period, is found as a comparison result.

Description

[Technical Field]

[0001] [Statement about related applications] The present invention is based on a claim of priority from Japanese Patent Application No. 2022-013330 (filed January 31, 2022), the entire contents of which are incorporated herein by reference. The present invention relates to an information processing device, an information processing method, and an information processing program, and in particular to an information processing device, an information processing method, and an information processing program related to animal welfare. [Background technology]

[0002] In the case of cattle, a system is in place in which a tag issued by a government agency is attached to the ear of the cattle being raised, and an individual identification number is assigned to each cattle, thereby guaranteeing that the cattle are the same individual from the time they are raised until they are slaughtered. This system is also known as the traceability method, and is used for food safety purposes and to recall products that have been distributed in the event of an outbreak of BSE.

[0003] In recent years, animal welfare certification, organic JAS certification, drug-free rearing, grass-fed, and other specialized rearing methods that require more effort and cost than traditional standard rearing have led to livestock products being traded at higher prices than those produced by standard rearing. To demonstrate that livestock animals have been reared using specified methods, it is necessary to manage their rearing history, identify each individual animal, link it to its rearing history, and demonstrate that the individual was indeed raised according to its rearing history. In other words, individual identification is necessary to increase added value. Therefore, it can be said that the value of ensuring that livestock animals, not just cattle, remain the same from the time they are raised until they are slaughtered, is increasing. Furthermore, the value of ensuring traceability of goods, not just livestock animals, is also increasing.

[0004] For example, Patent Document 1 discloses an individual identification device for identifying livestock animals. Patent Document 2 discloses a livestock management system using nose print authentication. Furthermore, Patent Document 3 discloses a determination system for determining the origin of cattle. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 6-276877 [Patent Document 2] Japanese Patent Application Laid-Open No. 2001-148957 [Patent Document 3] Japanese Patent Publication No. 2021-140773 Summary of the Invention [Problem to be solved by the invention]

[0006] The following analysis has been made from the perspective of the present invention, and the disclosures of the above-mentioned prior art documents are incorporated herein by reference.

[0007] The technologies of Patent Documents 1 to 3 have the problem of being vulnerable to fraudulent attempts by malicious actors to switch the livestock animals linked to the tags. In other words, the technologies of Patent Documents 1 to 3 merely guarantee that the tags issued by government agencies and the like remain the same for the period from the start of rearing to slaughter. Therefore, for example, if an animal raised using special breeding methods becomes ill or dies during rearing, a malicious actor could switch it with another animal raised using standard breeding methods, thereby gaining unfair profits.

[0008] Under the Traceability Act, reporting of cattle deaths is mandatory and measures have been taken to prevent the above-mentioned fraud, but there is no mechanism to crack down on the above-mentioned fraud for other livestock animals (pigs, chickens, etc.) Furthermore, while the legal reporting requirement acts as a psychological deterrent to fraud, it does not immediately detect fraud.

[0009] In addition, with regard to cattle, individual identification is ultimately done by nose print authentication, which is a lot of work, and there is a problem in that fraud cannot be detected unless a supervisor or other person suspects fraud and actively investigates (by matching nose prints, etc.).

[0010] Therefore, an object of the present invention is to provide technology that makes it easy to realize livestock rearing management that takes animal welfare into consideration. [Means for solving the problem]

[0011] According to a first aspect of the present invention, a camera for imaging livestock animals; an identifier acquisition unit that acquires an identifier of the livestock animal; a storage unit that stores the identifier acquired by the identifier acquisition unit and the image captured by the camera in association with each other; an image comparison unit that compares images taken at different times of livestock animals identified by the same identifier; a reporting unit that reports the substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison by the image comparing unit; An information processing device comprising:

[0012] According to a second aspect of the present invention, an imaging step of imaging a livestock animal; an identifier acquisition step of acquiring an identifier of the livestock animal; a storing step of storing the acquired identifier and the captured image in a storage unit in association with each other; an image comparison step of comparing images taken at different times of livestock animals identified by the same identifier; a reporting step of reporting a substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison; An information processing method is provided, comprising:

[0013] According to a third aspect of the present invention, an imaging process for imaging livestock animals; an identifier acquisition process for acquiring an identifier of the livestock animal; a storage process of storing the acquired identifier and the captured image in association with each other in a storage unit; an image comparison process for comparing images taken at different times of livestock animals identified by the same identifier; a reporting process for reporting the substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison; An information processing program that causes a computer to execute the above is provided. [Effects of the Invention]

[0014] According to each aspect of the present invention, an information processing device, an information processing method, and an information processing program are provided that contribute to easily realizing livestock breeding management that takes animal welfare into consideration. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a diagram for explaining an overview of the present invention. [Figure 2] FIG. 1 is a diagram showing an example of a fraudulent method assumed in the present application. [Figure 3] FIG. 1 is a diagram showing an example of a fraudulent method assumed in the present application. [Figure 4] FIG. 1 is a diagram for conceptually explaining the present invention. [Figure 5] 1 is a block diagram showing an example of the configuration of an information processing apparatus 100 according to a first embodiment. [Figure 6] FIG. 2 is a diagram showing an example of the arrangement of cameras 10 assumed in the first embodiment. [Figure 7] 1 is a flowchart showing the flow of processing by the information processing device 100. FIG. [Figure 8] FIG. 1 illustrates an example of a computer as an information processing device 100. DETAILED DESCRIPTION OF THE INVENTION

[0016] Preferred embodiments of the present invention will be described in detail with reference to the drawings. Note that the reference numerals used in the following description are used for convenience to identify each element as an example to facilitate understanding, and are not intended to limit the present invention to the illustrated embodiment. Furthermore, the connecting lines between blocks in each drawing include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of the main signal (data) and do not exclude bidirectionality. Furthermore, although not explicitly shown, input and output ports exist at the input and output ends of each connecting line in the circuit diagrams, block diagrams, internal configuration diagrams, connection diagrams, and the like shown in this disclosure. The same applies to input and output interfaces.

[0017] First, an overview of the present invention will be described. As shown in Fig. 1, an information processing device 100 includes a camera 10, an identifier acquisition unit 20, a storage unit 30, an image comparison unit 40, and a reporting unit 50.

[0018] The camera 10 captures images of livestock animals. The identifier acquisition unit 20 acquires the identifiers of the livestock animals. The memory unit 30 stores the identifiers of the livestock animals in association with the captured images. The image comparison unit 40 compares images captured at different times of livestock animals identified with the same identifier. The reporting unit 50 reports that a livestock animal identified with the same identifier has been swapped if a change in the livestock animal that cannot occur within a specified period of time is found.

[0019] To give a specific example, it is assumed that the information processing device 100 of the present invention will report the substitution of livestock animals in cases such as those shown in Figures 2 and 3. Figure 2 shows a fraudulent case in which a tag with identifier: ABC is attached to a brand pig traded at a high price, and when the brand pig dies, the tag with identifier: ABC is replaced with a regular pig traded at a low price. Figure 3 shows a fraudulent case in which, when a brand pig traded at a high price dies, the tag with identifier: ABC attached to the brand pig is deemed to have been damaged, and a new tag with identifier: DEF is reissued and replaced with a regular pig traded at a low price.

[0020] In either case, ordinary pigs traded at low prices end up being shipped as branded pigs. The case in Figure 3 can also occur when cattle are swapped. Under the Traceability Act, tags used when raising cattle are usually designed so that they cannot be reattached once removed, and in case a tag is damaged, a system is in place that allows for the use of a different tag upon application. In other words, when swapping cattle, this system can also be abused, and the tag can be made to appear damaged, allowing for fraud like that shown in Figure 3 to occur.

[0021] In the case of Fig. 2, the information processing device 100 compares a captured image of a brand pig tagged with the same identifier: ABC with a captured image of a regular pig. In addition, in the case of Fig. 3, the information processing device 100 considers the identifiers: ABC and DEF to be the same identifier, and compares a captured image of a brand pig tagged with identifier: ABC with a captured image of a regular pig tagged with identifier: DEF. Here, since an appearance change that cannot occur within a predetermined period of time is found between the brand pig and the regular pig, the information processing device 100 reports the substitution of livestock animals.

[0022] Conceptually, livestock animals should exhibit gradual and incremental growth over time t in terms of attribute values ​​such as withers height and weight, as shown in FIG. 4(A). Therefore, discontinuities, sudden changes, and non-standard changes in attribute values, such as those shown in FIG. 4(B), cannot occur for the same livestock animal. The information processing device 100 of the present invention detects discontinuities, sudden changes in short periods, and non-standard changes in attribute values ​​from images of livestock animals captured continuously or periodically, and reports the substitution of livestock animals. Note that attribute values ​​can also be described as elements that do not change suddenly over a short period, such as body size, body patterns, facial features, body parts such as ears, coat, joint positions, joint lengths, and relationships therebetween. In other words, the information processing device 100 of the present invention reports the substitution of livestock animals not only based on quantified information but also when external changes that would not occur in the same animal over a short period (e.g., disappearance of markings) occur. In the information processing device 100 of the present invention, since all images stored in the storage unit 30 must be forged in order to switch livestock animals, a high effect of preventing switching can be expected.

[0023] [Embodiment 1] Next, the above-mentioned information processing device 100 will be described in more detail as embodiment 1. As shown in Fig. 5, the information processing device 100 includes a storage unit 30, a plurality of cameras 10, a livestock animal position acquisition unit 120, an individual identification information acquisition unit 130, an individual identification information change unit 140, an individual attribute information acquisition unit 150, a fraud detection unit 160, and a reporting unit 50.

[0024] The cameras 10 are placed in various locations in the field, as shown in FIG. 6, for example, and capture images of pigs in the field from various angles, such as the front, side, and above, continuously or intermittently. The captured images are stored in the storage unit 30 in chronological order. The cameras 10 may be preferentially placed in locations where pigs inevitably pass through each day, such as passageways and feeding areas. The captured images are preferably stored in the storage unit 30 in a data format that allows the pig's location (distance from the camera 10) to be determined later. The pig's location can be determined using various techniques, such as a time-of-flight (ToF) camera, marker positioning, or integrating images captured by multiple cameras 10. The captured images are preferably stored in the storage unit 30 in a data format that allows the capture time to be identified, for example, with a timestamp. It is also preferable that the camera 10 stores a list of the camera ID (identification / identifier), camera location information, camera orientation information, and sensor information (livestock distance information, livestock location information) in the storage unit 30 along with the captured images.

[0025] The livestock position acquisition unit 120 assigns livestock position information to images stored in the memory unit 30. Specifically, the livestock position acquisition unit 120 identifies the position of the livestock in the field from the size and position of the livestock (livestock) in images captured by the camera 10 around the same time. Here, if the camera 10 is a camera capable of acquiring livestock distance information and livestock position information, such as a positioning camera or a ToF camera, the livestock position acquisition unit 120 may also use this information. In other words, a ToF camera, a marker positioning camera, or the like may be used as a component that integrates the camera 10 and the livestock position acquisition unit 120.

[0026] The individual identification information acquisition unit 130 corresponds to the identifier acquisition unit 20, and extracts the identifier assigned to each pig from any of the images captured by the multiple cameras 10 to identify the individual. Specifically, the individual identification information acquisition unit 130 identifies individual livestock animals and assigns individual ID information to images captured from a direction in which individual identifiable information such as tags, markers, and faces can be detected, among the images stored in the storage unit 30. Even for images in which individual identification is not possible, the individual identification information acquisition unit 130 preferably assigns individual ID information to the pigs in the captured images based on clues such as the time of capture, the position and distance of the pig, etc.

[0027] The individual identification information change unit 140 is a functional unit used when the tag is damaged (the case in FIG. 3), and updates the individual ID information assigned to the pig in the captured image when there is a change in the individual ID information. The individual ID information may be managed as an individual ID database, and the IDs before and after the change may be managed.

[0028] The individual attribute information acquisition unit 150 acquires attribute information of each individual (e.g., the size of the target individual) by quantifying it from the images stored in the storage unit 30 and the positional information of the livestock animals. For example, the individual attribute information acquisition unit 150 classifies the captured images stored in the storage unit 30 into views such as from the front, back, right side, left side, and top for each individual ID, measures attribute values ​​such as the pig's size for each image, and assigns the attribute values ​​to the captured image. The pig's size can be measured in a variety of ways, such as by sensor fusion with 3D, marker positioning, or calculation based on comparison with a reference object in the image, such as a striped pole. As a result of the assignment of attribute information by the individual attribute information acquisition unit 150, time-series data of the attribute information for each target individual is stored in the storage unit 30.

[0029] The fraud detection unit 160 detects fraud by comparing past images with the latest images. Specifically, if attribute information that should normally fluctuate slowly changes suddenly and unexpectedly within a predetermined time period, the fraud detection unit 160 determines that fraud has been committed and issues a report using the reporting unit 50.

[0030] The component combining the individual attribute information acquisition unit 150 and the fraud detection unit 160 corresponds to the image comparison unit 40 .

[0031] The reporting unit 50 reports fraud (i.e., substitution of livestock animals) to a supervisor such as a certification body or parent company.

[0032] Next, the flow of processing by the information processing device 100 will be described. As shown in FIG. 7, the information processing device 100 captures images of livestock animals (step S01) and assigns location information and individual ID information (step S02). The information processing device 100 then digitizes the attribute information of each individual animal (step S03). If an unexpected sudden change occurs within a predetermined time period in the attribute information, which is normally subject to gradual fluctuations (step S04, Yes), the information processing device 100 reports fraud (substitution of livestock animals) (step S05). Note that steps S01 to S03 may be performed continuously, in other words, in a loop. Step S04 may also be performed at any timing. That is, growth logs in which location information, individual ID information, and attribute information are assigned to captured images of livestock animals may be accumulated in the storage unit 30, and fraud may be detected by comparing the growth logs at any timing. Note that if no sudden change occurs in the attribute information (step S04, No), the information processing device 100 terminates the fraud detection process, but may continue steps S01 to S03.

[0033] A variation of the first embodiment will be described below.

[0034] In the first embodiment, a case where fraud is detected by comparing a past image with a latest image has been described. However, other sensor data, in addition to images, may be used to acquire attributes. For example, a thermosensor (or a thermo camera) may be installed instead of the camera 10 to monitor the average body temperature.

[0035] It is also possible to detect cheating from the behavior of individuals. For example, cheating can be detected based on events such as a quiet individual becoming active on a certain day, an individual that does not socialize starting to socialize, or a sudden change in the amount of food eaten. Alternatively, it is possible to train an individual to behave in a specific way using a specific sound or a specific pattern of light, and then determine that cheating has occurred if the individual is no longer able to behave in that way on a certain day.

[0036] Furthermore, in the first embodiment, a case has been described in which fraud (substitution of livestock animals) is reported when an unexpected sudden change occurs within a predetermined time period in attribute information that is supposed to change gradually. However, the information processing device 100 can also report fraud (substitution of livestock animals) even when attribute information that is supposed to change rapidly suddenly changes gradually. For example, a case in which a young livestock animal in its growing stage is swapped with a livestock animal that has grown older and has stabilized in growth can be considered as a case in which attribute information that is supposed to change rapidly suddenly changes gradually. In other words, the information processing device 100 can report the substitution of livestock animals when it detects discontinuities in attribute values, sudden changes in a short period, or non-standard changes in the attribute values ​​from images of livestock animals captured continuously or periodically.

[0037] In the first embodiment, not only is a report made using the reporting unit 50, but past images and the latest images used in detecting fraud may also be output as evidence or made viewable. At this time, in order to increase the resistance to tampering of the stored images and attribute information and to increase the reliability as evidence, hash values ​​of the stored images and attribute information may be calculated and stored in a storage area separate from the images and attribute information. Furthermore, instead of storing the images and attribute information in a simple memory area, they may be stored in tamper-resistant distributed storage using a blockchain or the like.

[0038] Furthermore, it is conceivable that this method can be applied not only to livestock animals, but also to growing things and things that undergo irreversible changes over time, such as plants and cultural assets (when viewed over a long period of time).

[0039] In addition, the criteria for reporting can be changed, such as reporting when a sudden change in attribute information continues for a certain period of time, rather than reporting immediately when a sudden change in attribute information is detected.

[0040] The present invention can also be realized by a computer serving as the information processing device 100. Specifically, as shown in Fig. 8, the computer serving as the information processing device 100 includes a memory (corresponding to the storage unit 30), an interface (connected to the camera 10), a CPU (Central Processing Unit), etc. The CPU reads a program from the memory and realizes processing modules corresponding to the identifier acquisition unit 20, the image comparison unit 40, and the reporting unit 50.

[0041] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0042] (Appendix 1) a camera for imaging livestock animals; an identifier acquisition unit that acquires an identifier of the livestock animal; a storage unit that stores the identifier acquired by the identifier acquisition unit and the image captured by the camera in association with each other; an image comparison unit that compares images taken at different times of livestock animals identified by the same identifier; a reporting unit that reports the substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison by the image comparing unit; An information processing device comprising:

[0043] (Appendix 2) The information processing device according to claim 1, wherein the image comparison unit acquires attribute information of the livestock animal from each of the captured images and compares the acquired attribute information.

[0044] (Appendix 3) The attribute information is height, 3. The information processing device according to claim 2, wherein the image comparison unit determines the height of the livestock animal by comparing it with a reference object captured in the captured image.

[0045] (Appendix 4) The camera is a thermal camera, The attribute information is an average body temperature. 3. The information processing device according to claim 2.

[0046] (Appendix 5) The attribute information is a body pattern. 3. The information processing device according to claim 2.

[0047] (Appendix 6) The attribute information is the amount of food eaten. 3. The information processing device according to claim 2.

[0048] (Appendix 7) 7. The information processing device according to any one of appendices 1 to 6, wherein when a new captured image is stored in the storage unit, the image comparison unit compares the new captured image with a previously stored captured image.

[0049] (Appendix 8) a livestock animal position acquisition unit that acquires the position of the livestock animal from the captured image by the camera; The information processing device according to any one of appendices 1 to 7, wherein the identifier acquisition unit associates the image captured by the camera with the identifier based on the position of the livestock animal identified by the livestock animal position acquisition unit.

[0050] (Appendix 9) an imaging step of imaging a livestock animal; an identifier acquisition step of acquiring an identifier of the livestock animal; a storing step of storing the acquired identifier and the captured image in a storage unit in association with each other; an image comparison step of comparing images taken at different times of livestock animals identified by the same identifier; a reporting step of reporting a substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison; An information processing method including:

[0051] (Appendix 10) an imaging process for imaging livestock animals; an identifier acquisition process for acquiring an identifier of the livestock animal; a storage process of storing the acquired identifier and the captured image in association with each other in a storage unit; an image comparison process for comparing images taken at different times of livestock animals identified by the same identifier; a reporting process for reporting the substitution of livestock animals identified by the same identifier when a change in the livestock animals that cannot occur within a predetermined period is found as a result of the comparison; An information processing program that causes a computer to execute the above.

[0052] The disclosures of the above-cited patent documents and other documents are incorporated herein by reference and may be used as the basis or part of the present invention, as necessary. Modifications and adjustments of the embodiments and examples are possible within the scope of the entire disclosure of the present invention (including the claims), and further based on the basic technical concepts thereof. Furthermore, various combinations and selections (including partial deletions) of the various disclosed elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible within the scope of the entire disclosure of the present invention. In other words, the present invention naturally embraces various modifications and alterations that would be possible by a person skilled in the art in accordance with the entire disclosure and technical concepts, including the claims. In particular, with regard to the numerical ranges set forth herein, any numerical value or subrange within that range should be construed as specifically set forth, even if not otherwise specified. Furthermore, the disclosures of the above-cited documents, when used in part or in whole in combination with the disclosures herein as part of the disclosure of the present invention, in accordance with the spirit of the present invention, are also deemed to be included in the disclosures of this application. [Explanation of symbols]

[0053] 10: Camera 20: Identifier acquisition unit 30: Storage section 40: Image comparison section 50: Reporting Department 100: Information processing device 120: Livestock animal position acquisition unit 130: Individual identification information acquisition unit 140: Individual identification information change unit 150: Individual attribute information acquisition unit 160: Fraud detection unit

Claims

1. a camera for imaging livestock animals; an identifier acquisition unit that acquires an identifier of the livestock animal; a storage unit that stores the identifier acquired by the identifier acquisition unit and the image captured by the camera in association with each other; an image comparison unit that compares images taken at different times of livestock animals identified by the same identifier; a reporting unit that reports the substitution of livestock animals identified by the same identifier when a change in attribute information that cannot occur within a predetermined period is found as a result of the comparison by the image comparing unit; Equipped with The attribute information is one or more selected from the group consisting of height, weight, body size, body pattern, facial shape, body parts, coat, markings, average body temperature, joint position, joint-to-joint length, amount of food eaten, individual behavior, and response to training. Information processing device.

2. The information processing device according to claim 1 , wherein the image comparison unit acquires attribute information of the livestock animal from each of the captured images and compares the acquired attribute information.

3. The information processing apparatus according to claim 1 , wherein when a new captured image is stored in the storage unit, the image comparison unit compares the new captured image with a previously stored captured image.

4. a livestock animal position acquisition unit that acquires the position of the livestock animal from the captured image by the camera; The information processing device according to claim 1 , wherein the identifier acquisition unit associates the image captured by the camera with the identifier based on the position of the livestock animal identified by the livestock animal position acquisition unit.

5. An information processing method by an information processing device, comprising: an imaging step of imaging a livestock animal; an identifier acquisition step of acquiring an identifier of the livestock animal; a storing step of storing the acquired identifier and the captured image in a storage unit in association with each other; an image comparison step of comparing images taken at different times of livestock animals identified by the same identifier; a reporting step of reporting a substitution of livestock animals identified by the same identifier when a change in attribute information that cannot occur within a predetermined period is found as a result of the comparison; Including, The attribute information is one or more selected from the group consisting of height, weight, body size, body pattern, facial shape, body parts, coat, markings, average body temperature, joint position, joint-to-joint length, amount of food eaten, individual behavior, and response to training. Information processing methods.

6. an imaging process for imaging livestock animals; an identifier acquisition process for acquiring an identifier of the livestock animal; a storage process of storing the acquired identifier and the captured image in association with each other in a storage unit; an image comparison process for comparing images taken at different times of livestock animals identified by the same identifier; a reporting process for reporting the substitution of livestock animals identified by the same identifier when a change in attribute information that cannot occur within a predetermined period is found as a result of the comparison; An information processing program that causes a computer to execute the following: The attribute information is one or more selected from the group consisting of height, weight, body size, body pattern, facial shape, body parts, coat, markings, average body temperature, joint position, joint-to-joint length, amount of food eaten, individual behavior, and response to training. Information processing program.

Images