JP7238050B2 - Biological information processing device - Google Patents

Description

The present invention relates to a biological information processing apparatus, and more particularly to a biological information processing apparatus that processes biological information obtained from an image of an animal.

A pet biometric data measurement system is provided that can detect abnormalities in a non-contact manner without stressing the pet. For example, Patent Document 1 (Japanese Patent Application Laid-Open No. 2009-165416) discloses a method such as actively stimulating a pet living in a natural state to attract the pet's line of sight and capture a face image. At least one biometric data of pupil size, eye temperature, and nose gloss is extracted from the image data. In Patent Literature 1, the health condition of the pet is determined from this extracted data.

JP 2009-165416 A

The technique of Patent Literature 1 does not disclose a method for individual identification of pets. In recent years, there has been an increase in the number of cases where multiple pets are raised, and there is a demand to manage biometric data for each pet. However, Patent Document 1 does not propose a pet identification method. Therefore, it was difficult to meet the request.

Therefore, an object of the present disclosure is to provide a biological information processing apparatus capable of processing individual biological information while identifying individual animals.

A biological information processing apparatus according to an aspect of the present disclosure includes a biological information acquisition unit that acquires predetermined biological information from a captured image of an animal; an information acquisition unit, a matching unit that matches unique information acquired from the imaged animal with identification information of one or more individuals stored in advance, and a processing unit that processes biometric information based on the results of the matching. And prepare.

Preferably, the identification information includes a feature amount of an image of a predetermined part of the individual, the unique information acquisition unit includes a feature extraction unit that extracts the feature amount of the part from the captured image, and the matching unit extracts the feature amount from the captured image. It includes a feature matching unit that matches the extracted feature amount with one or more pre-stored feature amounts.

Preferably, the processing unit includes a storage processing unit for storing the biometric information in association with the identification information when the matching result indicates a match.

Preferably, the captured image includes a temperature image in which temperature of the body surface of the animal is imaged, and the biological information acquiring section acquires the surface temperature of a specific portion of the body surface of the animal from the temperature image.

Preferably, the captured image is stored when the matching result indicates a mismatch.

In one aspect of the present disclosure, it is possible to process individual biometric information while identifying individual animals.

FIG. 3 is a diagram showing a state in which three cat litter boxes 200 according to Embodiment 1 are lined up; FIG. 4 is a diagram schematically showing how a cat enters the litter box 200. FIG. 3A and 3B are diagrams schematically showing an image 202 of a cat's face captured by the image capturing unit 20 according to Embodiment 1 and a feature amount 203 of the face extracted from the captured image 202; FIG. 4 is a diagram showing a thermography image 204 of a cat's face captured by the imaging unit 20 according to Embodiment 1. FIG. 1 is a diagram schematically showing a hardware configuration of a biological data processing device 100 according to an embodiment; FIG. 1 is a diagram schematically showing a functional configuration of a biological data processing device 100 according to Embodiment 1; FIG. 4 is a diagram showing an example of storing biometric information according to Embodiment 1. FIG. 4 is a flow chart for data processing according to an embodiment of the present invention;

Hereinafter, the body motion signal processing device of each embodiment will be described with reference to the drawings. In the drawings referred to below, the parts denoted by the same reference numerals perform the same functions, and therefore description thereof will not be repeated unless particularly necessary.

[overview]
The biological data processing apparatus 100 according to the present disclosure acquires unique information unique to an individual, which is information that can identify the individual from the individual of an animal such as a pet, and acquires the biological body of the animal from the captured image of the animal. Get information. The processing unit collates the acquired unique information with one or more pieces of individual identification information stored in advance, and processes the biometric data based on the collation result.

Therefore, it is possible to process acquired biological information while identifying each animal such as a pet.

In each embodiment, the individual whose biometric information is to be acquired is exemplified by a cat that is kept as a pet, but the present invention is not limited to cats and can be applied to animals in general.

[Embodiment 1]
FIG. 1 is a diagram showing a state in which three cat litter boxes 200 according to the embodiment are lined up. FIG. 2 is a diagram schematically showing how a cat enters the toilet 200. As shown in FIG. Focusing on the cat's behavior, when it enters the toilet 200, it always enters from the head. Moreover, since the toilet 200 is provided with an entrance, it is possible to surely encourage the user to enter the toilet 200 head first.

Cat litter 201 is spread on the floor surface of the toilet 200 because cats have excretion habits of excreting on sand. Furthermore, the floor surface of the toilet 200 is provided with a load cell 14 that constitutes a weight scale for measuring the load.

Therefore, when a cat enters the litter box 200, the output of the load cell 14 changes. Also, the toilet 200 is equipped with a biological data processing device 100 having an imaging unit 20, which will be described later. As shown in FIG. 2, the imaging unit 20 is mounted so that the cat's face is positioned within the imaging range when the cat enters from the entrance of the toilet 200 . The imaging unit 20 includes a camera 16 (described later) that captures normal images and a thermography 17 (described later) that is an infrared camera. Therefore, the image of the cat in the toilet 200 is photographed by the image pickup unit 20, mainly the face, and the biometric data processing device 100 extracts information unique to the individual for identifying the individual from the partial image of the face included in the photographed image. Body temperature is detected by contact, and furthermore, body temperature is detected in a non-contact manner from the temperature distribution detected from the image of the eyes and the surroundings of the eyes. The above unique information is obtained by analyzing the color components from the face image and analyzing the hair color distribution.

(Captured image and feature value)
FIG. 3 is a diagram schematically showing an image 202 of a cat's face captured by the image capturing unit 20 according to Embodiment 1, and a facial feature amount 203 extracted from the captured image 202. As shown in FIG. The imaging unit 20 is installed on the side opposite to the entrance so that when the cat enters the toilet 200 from the entrance, the face can be photographed from the front with the face as the center. A captured image 202 in FIG. 3A shows a case in which the entire cat's face is captured from almost the front.

As shown in FIG. 3B, the captured image 202 has a facial image feature quantity 203 that indicates the distribution of facial hair color. A feature amount 203 indicates the color distribution of the three primary colors of R (red), G (green), and B (blue) in the face image. It is generally known that the distribution of facial hair color of a cat is unique to an individual and can serve as information for distinguishing the individual from others.

In Embodiment 1, the feature amount 203 representing the distribution of coat colors in FIG. 3B is used as unique information for identifying an individual, but the present invention is not limited to this. For example, it may be the feature amount of the arrangement pattern of facial parts (scratches, eyes, mouth, nose, etc.), or a combination of both feature amounts. When individual identification is performed using a combination, identification accuracy can be improved compared to the case where only the feature quantity 203 is used. Note that a well-known technique can be used for the method of extracting the feature amount of the arrangement pattern of facial parts, so the details will not be repeated here.

FIG. 4 is a diagram showing a thermographic image 204 by the imaging unit 20 according to Embodiment 1. FIG. In a thermography image 204, which is an image captured by the thermography 17 in FIG. 4, the temperature of the face surface is distinguished by color. Here, since it is known that the body temperature of a cat can be measured in and around the eyes, in the thermography image 204, the positions of the eyes and the areas around the eyes are identified by matching the arrangement patterns described above. Temperature from the color information of the location, ie body temperature, can be detected.

In FIG. 4, the measured body temperature (36.6° C.) in and around the eyes is displayed in the upper left, and the temperature of the face surface has a range of approximately 25° C. to 36° C. in the lower part. are shown, the thermography image 204 actually output from the thermography 17 does not contain this information.

(Configuration of biological data processing device 100)
FIG. 5 is a diagram schematically showing the hardware configuration of the biological data processing device 100 according to the embodiment. Referring to FIG. 5, biological data processing apparatus 100 includes a control section 10 having a CPU (Central Processing Unit). The control unit 10 includes a communication unit 12 for communicating with an external wired or wireless network NT, a display unit 13 including a display such as a liquid crystal display, a load cell 14, a sensor driving unit 15 for driving the sensor of the load cell 14, An imaging unit 20 for imaging a subject and a storage unit 11 are connected. The storage unit 11 includes storage media such as ROM (Read Only Memory), RAM (Random Access Memory), and HDD (Hard Disk Drive).

The imaging unit 20 includes a camera 16 and a thermography 17 such as a CCD (Charge Coupled Device). Power is supplied from the power supply unit 18 to each unit of the biological data processing apparatus 100 . Power supply 18 includes a rechargeable battery. A data storage unit 250 corresponding to a cloud server device is connected to the network NT. The biological data processing device 100 communicates with the data storage section 250 via the network NT. The biometric data processing device 100 may include an operation unit including switches and the like for receiving user instructions to the device itself.

FIG. 6 is a diagram schematically showing the functional configuration of the biological data processing device 100 according to Embodiment 1. As shown in FIG. Functions of the respective units in FIG. 6 are realized by reading and executing programs stored in storage unit 11 by control unit 10 mainly having a CPU. Alternatively, it can be realized by a combination of a program and a circuit.

Referring to FIG. 6, biometric data processing apparatus 100 includes captured image input unit 30A, biometric information acquisition unit 38 for acquiring predetermined biometric information from a captured image of an animal (cat), A unique information acquisition unit 32 that acquires information unique to the individual from the individual, and a matching unit 37 that matches the acquired unique information with identification information of one or more individuals stored in advance in the storage unit 11. , and a processing unit 40 that processes the biometric data based on the result of this collation. The captured image input section 30A includes an image acquisition section 30 and a thermography image acquisition section 31 . The image acquisition unit 30 receives image data output from the camera 16 and outputs a captured image 202 after performing noise processing and the like. The thermography image acquisition unit 31 receives captured image data output from the thermography 17 and outputs a thermography image 204 after performing noise processing and the like.

The identification information includes the feature amount of the facial image of the animal, and the unique information acquisition section 32 includes a feature extraction section 32A that extracts the feature amount of the facial image from the captured image. The matching unit 37 also includes a feature matching unit 37</b>A that matches the feature amount extracted from the captured image with the feature amount of one or more individual face images stored in the storage unit 11 .

When the matching result output from the matching unit 37 indicates a match, the processing unit 40 stores the biometric information output from the biometric information acquisition unit 38 in the storage unit 11 in association with the above-described identification information. includes a memory processing unit 42 of Further, when the collation result indicates a mismatch, the processing unit 40 stores the image output from the captured image input unit 30A, more specifically, the output image from the image acquisition unit 30, in a predetermined area of the storage unit 11. memorize to

The processing unit 40 includes a communication processing unit 43 that controls the communication unit 12 to store the acquired biometric information and the identifier in the data storage unit 250 via the network NT, and a communication processing unit 43 that stores the acquired information (including the biometric information). It includes a display processing unit 41 that controls the display unit 13 to display.

The temperature distribution analysis unit 36 receives the thermography image 204 output from the thermography image acquisition unit 31, extracts the eyes and the area around the eyes in the face image from the thermography image 204 by the above pattern matching, and analyzes the extracted area. Detect the color distribution of the partial image. Then, the temperature distribution analysis unit 36 outputs the detected color information to the biological information acquisition unit 38 . Based on the color information from the temperature distribution analysis unit 36, the temperature acquisition unit 39 of the biological information acquisition unit 38 retrieves a color temperature table (not shown) in which color-temperature correspondences stored in advance in the storage unit 11 are registered. and read the corresponding temperature data from the color temperature table. Thereby, the body temperature is acquired by the biological information acquisition unit 38 as the biological information of the cat. The acquired body temperature data is output to the processing unit 40 .

The feature extraction unit 32A of the unique information acquisition unit 32 receives the captured image 202 output from the image acquisition unit 30 as input. In the feature extraction unit 32A, the face recognition unit 33 identifies a partial image of the face in the captured image 202 by the above-described pattern matching performed by the eye/nose/mouth analysis unit 35 . The color component analysis section 34 analyzes the color distribution of the specified partial image and outputs the analyzed color distribution information to the matching section 37 . The color distribution information indicates the distribution of coat colors peculiar to cats, and is an example of identification information for each individual.

The collation unit 37 collates unique information (that is, hair color distribution information) output from the unique information acquisition unit 32 with one or more pieces of identification information stored in advance in the storage unit 11 . One or more pieces of identification information is information for uniquely identifying each individual who may use the toilet 200, and in the first embodiment, it is information representing the distribution of facial hair color. A feature matching unit 37A of the matching unit 37 obtains the color distribution information (specific information) of cats in the litter box 200 from the unique information acquisition unit 32 and the identification information of the storage unit 11 (each individual who may use the litter box 200). information representing distribution of facial hair color), and outputs the result of matching (matching or non-matching) to the processing unit 40 .

The processing unit 40 processes the biological information (body temperature data) from the biological information acquisition unit 38 by the display processing unit 41, the storage processing unit 42, or the communication processing unit 43 based on the collation result described above.

(Another example of biometric information)
In Embodiment 1, the body temperature is acquired as the cat's biometric information, but the type of biometric information is not limited to the body temperature. For example, it may be the weight, the degree of dryness of the nose, and the like. The body weight is detected by the biological information acquisition unit 38 from the change in the output of the load cell 14 when the cat enters the litter box 200 . Also, the degree of dryness of the nose is detected by the biometric information acquisition unit 38 from the color information of the nose region based on the output from the feature extraction unit 32A.

(Contents of stored data)
7 is a diagram illustrating an example of storing biometric information according to Embodiment 1. FIG. Storage unit 11 stores identification information 51 of one or more individual cats, and body temperature data 52, weight data 53, and data 54 indicating the degree of dryness of the nose in association with each identification information 51. FIG. Although FIG. 7 shows the data storage format in the storage unit 11, biometric information for each individual is stored in the data storage unit 250 according to the same storage format. Note that the data storage formula is not limited to this.

(flowchart)
FIG. 8 is a flow chart for data processing according to an embodiment of the present invention. A program according to the flowchart of FIG. 8 is stored in storage unit 11 in advance, and the CPU of control unit 10 reads the program from storage unit 11 and executes the read program to realize processing.

First, the CPU determines whether or not a cat has entered (entered) the toilet 200 (step S1). For this detection, for example, when the displacement of the output of the load cell 14 exceeds a predetermined threshold value, it is determined that the object (cat) has entered the room. Further, when the CPU determines that the user has entered the room, it turns on the power of the camera 16 and the thermography 17 so that the image can be taken. Further, when the CPU determines that the displacement of the output of the load cell 14 exceeds a predetermined threshold value after determining that the user has entered the room, the CPU determines that the user has left the toilet 200, and cuts off the power to the camera 16 and the thermography 17. do. Thereby, power consumption can be saved.

While the CPU does not determine whether the cat has entered the room (NO in step S1), it repeats the determination of whether the cat has entered the room based on the output from the load cell (step S1).

When the CPU determines that the cat has entered the room (YES in step S1), the CPU performs shutter control of the camera 16 and the thermography 17. FIG. As a result, an image centering on the cat's face near the entrance is captured (step S3).

A captured image 202 and a thermography image 204 obtained by photographing are output to the unique information acquisition section 32 and the temperature distribution analysis section 36 via the captured image input section 30A, respectively. The unique information acquisition unit 32 acquires color information, which is the feature quantity of the hair color of the face, from the captured image 202 using the feature extraction unit 32A, and outputs the color information to the matching unit 37 (step S5).

In the collation unit 37 , the feature collation unit 37A collates the hair color information output from the unique information acquisition unit 32 and the identification information of each individual in the storage unit 11 . A collation result (whether or not the color information matches the identification information) is output to the processing unit 40 .

The processing unit 40 determines whether or not the collation result indicates a match (step S7). When it is determined that the collation result does not indicate a match (NO in step S7), the series of processing ends.

In step S<b>9 , the temperature distribution analysis unit 36 detects color distribution information representing the distribution of temperature around the eyes from the thermography image 204 and outputs the color distribution information to the biological information acquisition unit 38 . In the biometric information acquisition section 38, the temperature acquisition section 39 acquires the temperature corresponding to the color distribution, ie body temperature, based on the color distribution information from the temperature distribution analysis section 36 (step S9).

The processing unit 40 processes the biological information from the biological information acquisition unit 38 , that is, body temperature, using the display processing unit 41 , the storage processing unit 42 or the communication processing unit 43 . The storage processing unit 42 stores the body temperature in the storage unit 11 as body temperature data 52 in association with the corresponding identification information 51 . In addition, in step S9, biometric information indicating the weight or the degree of dryness of the nose may be acquired. In this case, in step S11, the weight and the degree of dryness of the nose are associated with the corresponding identification information 51 and stored in the storage unit 11 as the weight data 53 and the data 54 of the degree of dryness of the nose.

In the body temperature measurement according to the first embodiment, the accuracy of body temperature measurement may be improved by taking a focused image of a characteristic part such as an eye to increase the accuracy of integral averaging in image processing.

In addition, by enabling non-contact individual identification and body temperature measurement from the feature amount of the face image, it is possible to deal with a plurality of toilets 200 and multiple pets, and the health management of each individual can be stressful to the individual. It can be realized while reducing the burden on the owner.

(Embodiment 2)
Embodiment 2 describes a modification of Embodiment 1. FIG. In FIG. 8, when the individual can be identified (that is, when the matching result indicates a match) (YES in step S7), biometric information is acquired (step S9). is not limited to For example, after the biometric information is acquired, the matching/mismatching determination may be performed. In this case, if the matching result is a mismatch, the processing unit 40 stores the captured image 202 in a predetermined area of the storage unit 11 . As a result, when the number of matching mismatches reaches a predetermined number, that is, when a predetermined number of captured images 202 are stored, the CPU performs feature matching so as to reduce the number of matching mismatches. The reference threshold value for determining match/mismatch of collation set in the section 37A is changed. Alternatively, when it is determined from the captured image that the matching mismatch is caused by the deviation of the imaging range, the imaging angle of the camera is adjusted.

(Embodiment 3)
In each of the above embodiments, fur color distribution information is used to identify individuals, but the present invention is not limited to this. For example, the unique information acquisition unit 32 receives information from an electronic chip for individual identification embedded in the body of the animal, noseprint information extracted from the captured image 202, printed information on the collar attached to the individual, and the like. may be obtained and used as the unique information of the individual.

Also, as the unique information of the individual, the feature amount of the hair color of the image of the face, which is an example of a predetermined part of the individual, is used, but the part from which the feature amount is extracted is not limited to the face.

Further, the temperature acquisition unit 39 acquires the surface temperature around the eyes, which is an example of a specific part of the body surface, from the thermography image 204, but the part from which the surface temperature is acquired is not limited to the eyes and around the eyes. .

(Embodiment 4)
Modifications of the above embodiments are shown. In each embodiment, the biological data processing device 100 is installed in the toilet 200, but the installation target is not limited to the toilet 200. FIG. Any installation mode may be used as long as the face image of the individual to be measured can be imaged without applying stress.

(Embodiment 5)
A modification of each of the above embodiments will be described. In each embodiment, the biometric data processing device 100 is attached integrally with the toilet 200 , but the biometric data processing device 100 may be detachable from the toilet 200 . Alternatively, load cell 14, camera 16 and thermography 17 may be attached to toilet 200 and control unit 10 may receive and process their output data via remote communication.

(Embodiment 6)
A modification of each of the above embodiments will be described. In each embodiment, body temperature, weight, and dryness of the nose are obtained as biological information, but the present invention is not limited to these. For example, based on the output of the load cell 14, based on the difference in the output of the load cell 14 before entering the toilet 200 and after leaving the toilet 200, the excretion amount (urine amount, etc.) and the excretion time of the individual are measured, and this is used as the identification information 51. They may be stored in association with each other. This makes it possible to manage the amount and time of excretion for each individual.

(Embodiment 7)
Embodiment 7 provides a program for causing a CPU to execute the processes according to the above-described embodiments. Such a program is stored in a computer-readable recording medium such as a flexible disk, CD-ROM (Compact Disk-Read Only Memory), ROM, RAM and memory card attached to the computer (control unit 10) of the biological data processing device 100. , and can be provided as a program product. Alternatively, the program can be provided by recording it in a recording medium such as the HDD of the storage unit 11 . The program can also be provided by downloading via network NT.

The program may call necessary modules in a predetermined arrangement at predetermined timing among program modules provided as part of the computer's OS (Operating System) to execute processing. In that case, the program itself does not include the above module, and the process is executed in cooperation with the OS.

Also, the program according to the seventh embodiment may be provided by being incorporated into a part of another program. Even in that case, the program itself does not include the modules included in the other program, and the processing is executed in cooperation with the other program. A program incorporated in such other program can also be included in the program according to the seventh embodiment.

The provided program product is installed and executed in a program storage unit such as a hard disk. Note that the program product includes the program itself and a recording medium on which the program is recorded.

[Effects of Embodiment]
In the non-contact measurement by the pet biometric data measurement system of Patent Document 1, in order to acquire a face image, the pet is given a positive stimulus such as an odor to guide the line of sight to the camera.

However, it is not always the case that the pet reacts to a positive stimulus and directs its line of sight in the desired direction of the camera or the like. In that case, photographing the face image also fails to identify the health status. Since the applicable technology is limited only to users who keep one dog, there is a problem that it cannot be used by users who keep multiple dogs. In contrast, the biometric data processing apparatus 100 of each embodiment is configured to process biometric information while identifying each individual, so this problem can be resolved.

In addition, in Patent Document 1, it is essential to guide the pet's line of sight to the camera by actively giving a stimulus to the pet. It is not always possible to guide the line of sight in an expected direction and capture a face image. In addition, the fact that identification is not possible means that the state of health cannot be confirmed. On the other hand, in each embodiment, since the face image is captured in accordance with the natural behavior of the individual entering the toilet 200, the case in which the image cannot be captured in Patent Document 1 can be prevented.

It should be considered that the embodiments disclosed this time are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the scope of the claims rather than the above description, and is intended to include all modifications within the meaning and range of equivalents of the scope of the claims.

10 control unit, 11 storage unit, 12 communication unit, 13 display unit, 14 load cell, 16 camera, 17 thermography, 18 power supply unit, 20 imaging unit, 30 image acquisition unit, 30A captured image input unit, 31 thermography image acquisition unit, 32 unique information acquisition unit 32A feature extraction unit 33 face recognition unit 34 color component analysis unit 35 eyes/nose/mouth analysis unit 36 temperature distribution analysis unit 37 matching unit 37A feature matching unit 38 biometric information acquisition Unit 39 Temperature acquisition unit 40 Processing unit 41 Display processing unit 42 Storage processing unit 43 Communication processing unit 51 Identification information 52 Body temperature data 53 Body weight data 54 Nose dryness data 100 Biological data Processing device 200 toilet 202 captured image 203 feature quantity 204 thermographic image 250 data storage unit NT network.

Claims (7)

an imaging unit that starts imaging when it is detected that an animal has entered the toilet;
a biometric information acquisition unit that acquires predetermined biometric information from a captured image of the animal;
a unique information acquisition unit that acquires unique information that can identify an individual from the animal;
a matching unit for matching the unique information acquired from the animal to be imaged with identification information of one or more individuals stored in advance;
a processing unit that processes the biometric information based on the collation result;
a power supply unit ;
When the entry of the animal into the toilet is detected, the power is turned on from the power supply unit to the imaging unit so that the image can be captured, and when the exit from the toilet is detected, the power is cut off. Biological information processing equipment. The identification information includes a feature amount of an image of a predetermined part of the individual,
The unique information acquisition unit
A feature extraction unit that extracts a feature amount of the part from the captured image,
The collation unit
2. The biometric information processing apparatus according to claim 1, further comprising a feature collating unit that collates the feature amount extracted from the captured image with one or more pre-stored feature amounts. The processing unit is
3. The biometric information processing apparatus according to claim 2, further comprising a storage processing unit for storing said biometric information in association with said identification information when said matching result indicates a match. The captured image includes a temperature image in which the body surface temperature of the animal is imaged,
The biometric information acquisition unit
4. The biological information processing apparatus according to any one of claims 1 to 3, wherein the body surface temperature of said animal is acquired from a temperature image of a captured image of said animal. 5. The biometric information processing apparatus according to any one of claims 1 to 4, wherein said captured image is stored when said collation result indicates a mismatch. further comprising a load sensor provided on the floor of the toilet where the animal enters,
6. The biological information processing apparatus according to any one of claims 1 to 5, wherein the entry into the room is detected from the output of the load sensor. further comprising a load sensor provided on the floor of the toilet where the animal enters,
7. The biological information processing apparatus according to any one of claims 1 to 6, wherein the weight and excretion amount of said animal are measured from the output of said load sensor.

Images