Device for pet

Abstract

The present disclosure relates to a device for a pet. A device for a pet according to one embodiment of the present disclosure comprises: a housing; a camera that photographs an internal space of the housing; a temperature sensor disposed adjacent to the bottom of the housing; and a control unit, wherein the control unit may, when a pet is detected in a predetermined image photographed by the camera, determine whether the pet is located in a predetermined area of the bottom corresponding to the temperature sensor, on the basis of the predetermined image, and, when the pet is located in the predetermined area, obtain the body temperature of the pet by means of the temperature sensor.

Description

Devices for pets

[0001] The present disclosure relates to a device for companion animals.

[0002] As the number of households owning pets continues to increase, research is actively underway into products that promote pet health and enhance the convenience of pet ownership. For example, various devices are being developed, such as waste disposal devices that dispose of pet waste and waterers that provide pets with clean water at all times.

[0003] Unlike people, pets cannot directly communicate with their owners, making it difficult for owners to easily monitor their pets' health. Regular visits to the vet to check their pets' health can be a burden, both in terms of time and cost. Furthermore, if a pet's health is difficult to detect with the naked eye, the pet's condition may already be deteriorating by the time the owner notices something is wrong.

[0004] Meanwhile, a pet's health is typically monitored based on its body temperature. Traditionally, owners would use a thermometer to directly measure the temperature of a specific part of their pet's body, such as the pet's ears or anus. However, repeatedly measuring a pet's temperature requires significant effort on the part of the owner, and it can be difficult to measure the pet's temperature when the owner is away.

[0005] The present disclosure aims to solve the above-mentioned and other problems.

[0006] Another purpose is to provide a device for pets that can monitor the pet's body temperature.

[0007] Another purpose is to provide a device for pets that can accurately measure the body temperature of the pet.

[0008] Another purpose is to provide a device for pets that can optimize various settings used for measuring the pet's body temperature.

[0009] Another purpose is to provide a device for pets that can provide messages related to the pet's health status to the pet owner.

[0010] In order to achieve the above object, a device for a companion animal according to one embodiment of the present disclosure comprises: a housing; a camera for photographing an internal space of the housing; a temperature sensor disposed adjacent to a bottom portion of the housing; and a control unit, wherein, when a companion animal is detected in a predetermined image acquired through the camera, the control unit determines whether the companion animal is located in a predetermined area of ​​the bottom portion corresponding to the temperature sensor based on the predetermined image, and when the companion animal is located in the predetermined area, the body temperature of the companion animal can be acquired through the temperature sensor.

[0011] The effects of the companion animal device according to the present disclosure are described as follows.

[0012] According to at least one embodiment of the present disclosure, the body temperature of a companion animal can be monitored.

[0013] According to at least one embodiment of the present disclosure, the body temperature of a companion animal can be accurately measured.

[0014] According to at least one embodiment of the present disclosure, various settings used for measuring body temperature of a companion animal can be optimized.

[0015] According to at least one embodiment of the present disclosure, a message related to the health status of a companion animal can be provided to the guardian.

[0016] FIGS. 1 to 3 are drawings for reference in the description of a companion animal device according to one embodiment of the present disclosure.

[0017] FIG. 4 is a flowchart of an operation method of a companion animal device according to one embodiment of the present disclosure.

[0018] FIGS. 5 to 11 are drawings for reference in explaining the operation of a companion animal device according to embodiments of the present disclosure.

[0019] Hereinafter, the present disclosure will be described in detail with reference to the drawings. In the drawings, portions irrelevant to the description are omitted to clearly and concisely describe the present disclosure, and the same reference numerals are used for identical or extremely similar portions throughout the specification.

[0020] The suffixes "module" and "part" used in the following description are given solely for the convenience of writing this specification and do not impart any particularly significant meaning or role to the components themselves. Therefore, the terms "module" and "part" may be used interchangeably.

[0021] In this application, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood not to preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0022] Additionally, while terms such as "first" and "second" may be used in this specification to describe various elements, these elements are not limited by these terms. These terms are used only to distinguish one element from another.

[0023] Hereinafter, directions are defined based on the rectangular coordinate system. In the rectangular coordinate system, the x-axis direction can be defined as the left-right direction. At this time, the direction toward +x with respect to the origin can mean the right direction, and the direction toward -x can mean the left direction. In addition, the y-axis direction can be defined as the front-back direction. At this time, the direction toward +y with respect to the origin can mean the front direction, and the direction toward -y can mean the rear direction. In addition, the z-axis direction can be defined as the up-down direction. At this time, the direction toward +z with respect to the origin can mean the upward direction, and the direction toward -z can mean the downward direction.

[0024] Referring to FIG. 1, the companion animal device (10) can communicate with a user terminal (20) via wired and / or wireless communication. For example, the companion animal device (10) can communicate with the user terminal (20) via pairing using Bluetooth. The user terminal (20) may be a portable device such as a smartphone or tablet PC.

[0025] The companion animal device (10) can communicate with the server (30). The companion animal device (10) can communicate by connecting to the server (30) via a network (40) such as the Internet. For example, the companion animal device (10) can transmit data on the companion animal's condition to the server (30). At this time, the server (30) can transmit the result of determining the companion animal's condition based on the data received from the companion animal device (10) to the user terminal (20).

[0026] The user terminal (20) can communicate with the server (30). The user terminal (20) can connect to the server (30) via a network (40) and communicate. For example, the user terminal (20) can update the firmware of the companion animal device (10) based on data received from the server (30). For example, the user terminal (20) can transmit data on the condition of the companion animal received from the companion animal device (10) to the server (30). At this time, the server (30) can transmit the result of determining the condition of the companion animal based on the data received from the user terminal (20) to the user terminal (20).

[0027] Referring to FIGS. 2A and 2B, according to various embodiments of the present disclosure, a companion animal device (10) may include a housing (100) forming an exterior. The housing (100) may include a ceiling portion (101), a floor portion (102), and / or a wall portion (103).

[0028] The housing (100) can form an internal space (105) where the pet is located. The housing (100) can include an entrance (104) formed to allow the pet to enter and exit the internal space (105). The entrance (104) can be formed in a portion of the wall portion (103).

[0029] The companion animal device (10) may include a camera (130) that photographs the interior space (105). The camera (130) may photograph a predetermined area including the floor (102).

[0030] The bottom (120) of the pet device (10) may be made of a material that allows the pet to feel comfortable. The bottom (120) may be formed of a soft material.

[0031] FIG. 3 is an internal block diagram of a companion animal device according to one embodiment of the present disclosure.

[0032] Referring to FIG. 3, the companion animal device (10) may include a communication interface (110), a sensor unit (120), an input / output interface (130), a memory (150), and / or a control unit (160).

[0033] The communication interface (110) may include at least one communication module for communication with an external device and / or a network. For example, the communication interface (110) may include a communication module for WLAN (Wireless LAN), Wi-Fi (Wireless Fidelity), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, etc. For example, the communication interface (110) may include a communication module for wired communication such as USB (universal serial bus).

[0034] The sensor unit (120) may include at least one sensor.

[0035] The sensor unit (120) may include a weight sensor (121) that detects the weight of the companion animal. The weight sensor (121) may be positioned adjacent to the bottom unit (102). The weight sensor (121) may output a signal that changes in response to the weight of the companion animal. For example, the weight sensor (121) may include a load cell.

[0036] The sensor unit (120) may include a temperature sensor (122) that detects the temperature of the companion animal. The temperature sensor (122) may be placed adjacent to the bottom portion (102). The temperature sensor (122) may output a signal that changes in response to the body temperature of the companion animal. The temperature sensor (122) may include a contact sensor such as a thermocouple, a resistance temperature detector, or a thermistor. Meanwhile, the temperature sensor (122) may include a non-contact sensor such as an IR (infrared) sensor. For example, when the temperature sensor (122) is an IR sensor, the temperature sensor (122) may be placed downwardly from the bottom portion (102) at a predetermined distance and facing the internal space (105).

[0037] Meanwhile, the sensor unit (120) may further include a sensor that detects the companion animal's bio-signals. Here, the bio-signals may include the companion animal's heartbeat, respiration, electrocardiogram (ECG) generated from the heart, etc. For example, respiration, heartbeat, etc. among the bio-signals may have periodicity. At this time, the sensor unit (120) may detect the periodic signal characteristics of the bio-signals using radio waves such as continuous wave (CW), frequency modulated continuous wave (FMCW), pulse, and ultra-wide band (UWB) radar. At this time, the periodic characteristics of the bio-signals detected using the radar signal may be measured as Doppler frequency. The Doppler frequency components may be composed of macro Doppler due to body motion and micro Doppler due to various organs (vital). Accordingly, the sensor unit (120) can detect the pet's breathing, heartbeat, etc. based on the Doppler frequency component of the biosignal.

[0038] The camera (130) can capture the interior space (105) of the companion animal device (10). The camera (130) can be positioned so as to face the bottom (102) from the inside of the companion animal device (10). The camera (130) can include an image sensor (131), a lens, an image signal processor (ISP), etc.

[0039] The input / output interface (140) may include an input device that receives commands from a user and / or an output device that outputs information to the user. For example, the input device may include a touch panel, a physical button, a microphone, etc. For example, the output device may include a display device that outputs visual information, such as a display or a light emitting diode (LED), an audio device that outputs auditory information, such as a speaker or a buzzer, etc.

[0040] The input / output interface (140) can transmit data corresponding to a command input from a user through an input device to other component(s) of the pet house (100). The input / output interface (140) can output information corresponding to data received from other component(s) of the pet device (10) through an output device.

[0041] The memory (150) can store programs for signal processing and control within the control unit (160). The memory (150) can store data processed by the control unit (160) and data to be processed. For example, the memory (150) can store application programs designed for the purpose of performing various tasks that can be processed by the control unit (160). The memory (150) can selectively provide some of the stored application programs upon request from the control unit (160).

[0042] The memory (150) may include at least one of volatile memory (e.g., DRAM, SRAM, SDRAM, etc.) or non-volatile memory (e.g., flash memory, hard disk drive (HDD), solid-state drive (SSD), etc.).

[0043] The control unit (160) can control the overall operation of the companion animal device (10). The control unit (160) can be connected to each component provided in the companion animal device (10). The control unit (160) can control the overall operation of each component by transmitting and / or receiving signals between each component.

[0044] The control unit (160) may include at least one processor. The control unit (160) may control the overall operation of the companion animal device (10) using the processor. Here, the processor may be a general processor such as a central processing unit (CPU). Of course, the processor may be a dedicated device such as an ASIC or another hardware-based processor.

[0045] According to one embodiment, the companion animal device (10) can process data using an algorithm learned using machine learning.

[0046] Artificial intelligence (AI) is the study of artificial intelligence or the methodologies for creating it, while machine learning (ML) defines various problems in the field of AI and studies the methodologies for solving them. Machine learning is also defined as an algorithm that improves performance on a task through consistent experience.

[0047] An artificial neural network (ANN) is a model used in machine learning. It can refer to a model with problem-solving capabilities, comprised of artificial neurons (nodes) that form a network through the connection of synapses. An ANN can be defined by the connection patterns between neurons in different layers, the learning process that updates model parameters, and the activation function that generates output values.

[0048] An artificial neural network may include an input layer, an output layer, and optionally one or more hidden layers. Each layer contains one or more neurons, and the artificial neural network may include synapses connecting neurons. In an artificial neural network, each neuron can output a function value of an activation function based on input signals, weights, and biases received through the synapses.

[0049] Model parameters are parameters determined through learning, including synaptic connection weights and neuron biases. Hyperparameters are parameters that must be set before learning in machine learning algorithms, including the learning rate, number of iterations, mini-batch size, and initialization function.

[0050] The goal of artificial neural network training can be seen as determining model parameters that minimize a loss function. The loss function can be used as an indicator for determining optimal model parameters during the artificial neural network training process.

[0051] Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning depending on the learning method.

[0052] Supervised learning refers to a method for training an artificial neural network when given labels for the training data. The labels can refer to the correct answer (or output value) that the artificial neural network must infer when the training data is input to the artificial neural network. Unsupervised learning can refer to a method for training an artificial neural network when the training data is not given labels. Reinforcement learning can refer to a learning method in which an agent defined within a given environment is trained to select actions or action sequences that maximize the cumulative reward in each state.

[0053] Machine learning implemented with a deep neural network (DNN) containing multiple hidden layers among artificial neural networks is also called deep learning, and deep learning is a subset of machine learning. Hereinafter, the term "machine learning" is used to encompass deep learning.

[0054] Object detection models using machine learning include the single-stage YOLO (You Only Look Once) model and the two-stage Faster R-CNN (Regions with Convolution Neural Networks) model.

[0055] The YOLO (You Only Look Once) model is a model that can predict objects and their locations within an image by looking at the image only once.

[0056] The YOLO (You Only Look Once) model divides the original image into grids of equal size. For each grid, it predicts the number of bounding boxes in a predefined shape centered around the grid center, and calculates a confidence level based on this prediction.

[0057] Afterwards, whether the image contains an object or is just a background is included, and locations with high object confidence are selected so that the object category can be identified.

[0058] The Faster R-CNN (Regions with Convolution Neural Networks) model is a model that can detect objects faster than the RCNN model and the Fast RCNN model.

[0059] This article specifically explains the Faster R-CNN (Regions with Convolution Neural Networks) model.

[0060] First, feature maps are extracted from the image using a Convolution Neural Network (CNN) model. Based on the extracted feature maps, multiple regions of interest (RoIs) are extracted. RoI pooling is performed for each region of interest.

[0061] RoI pooling is a process of setting a grid to a predetermined size of H x W for the feature map onto which the region of interest is projected, extracting the largest value for each cell included in each grid, and extracting a feature map with a size of H x W.

[0062] A feature vector is extracted from a feature map having a size of H x W, and object identification information can be obtained from the feature vector.

[0063] The companion animal device (10) may further include a learning processor (not shown) that learns a model composed of an artificial neural network using learning data. Here, the learned artificial neural network may be referred to as a learning model. The learning model may be used to infer a result value for new input data other than the learning data, and the inferred value may be used as a basis for making a judgment for performing a certain action.

[0064] At this time, the running processor may include a memory integrated or implemented in the companion animal device (10). Alternatively, the running processor may be implemented using a memory (150), an external memory directly coupled to the companion animal device (10), or a memory maintained in an external device.

[0065] The control unit (160) can request, search, receive or utilize data from the running processor and control components of the companion animal device (10) to execute at least one of the executable operations, a predicted operation or an operation determined to be desirable.

[0066] The control unit (160) can collect history information including the operation details of the companion animal device (10) or user feedback on the operation, and store the information in the memory (150) or the learning processor, or transmit the information to an external device such as a server (30). The collected history information can be used to update the learning model.

[0067] According to embodiments of the present disclosure, the running processor may be a separate component distinct from the control unit (160) or may be a component included in the control unit (160).

[0068] FIG. 4 is a flowchart of an operation method of a companion animal device according to one embodiment of the present disclosure.

[0069] Referring to FIG. 4, the pet device (10) can detect weight based on a signal from a weight sensor (121) in operation S410.

[0070] The companion animal device (10) can determine, in operation S420, whether the detected weight falls within a predetermined weight range. Here, the predetermined weight range can be set according to a preset weight of the companion animal. For example, the minimum value of the preset weight range can correspond to 90% of the preset weight of the companion animal, and the maximum value can correspond to 110% of the preset weight of the companion animal.

[0071] The companion animal device (10) can set the breed, age, weight, etc. of the companion animal based on data received from the user terminal (20) and / or server (30) via the communication interface (110). The companion animal device (10) can set the breed, age, weight, etc. of the companion animal based on user input received via the input / output interface (140).

[0072] According to one embodiment, the companion animal device (10) can update the preset weight of the companion animal. For example, the companion animal device (10) can update the preset weight of the companion animal based on a representative value of the weight detected through the weight sensor (121) according to a predetermined number of times, a predetermined period, etc. Here, the representative value can include an average, a mode, a median, etc. In this case, the companion animal device (10) can update the preset weight of the companion animal based on the weight detected through the weight sensor (121) when the companion animal is detected in the image.

[0073] The companion animal device (10) can acquire an image through the camera (130) when the detected weight falls within a predetermined weight range in operation S430. At this time, the image acquired through the camera (130) can correspond to the bottom (102) and the internal space (105). For example, the companion animal device (10) can supply power to the camera (130) to operate the camera (130) when the detected weight falls within a predetermined weight range.

[0074] The companion animal device (10) can process images acquired through a camera (130). For example, the companion animal device (10) can detect objects included in an image using a learning model learned through machine learning. For example, the companion animal device (10) can detect companion animals included in an image using a YOLO (You Only Look Once) model.

[0075] The companion animal device (10) can determine, in operation S440, whether the companion animal is located in a predetermined area. Here, the predetermined area may be an area corresponding to a temperature sensor (122) that measures the companion animal's body temperature.

[0076] Referring to FIG. 5, the predetermined area (500) may be an area included in the bottom portion (102). The predetermined area (500) may correspond to a temperature sensor (122). The predetermined area (500) may include a location where the temperature sensor (122) is placed. For example, the temperature sensor (122) may be located at the center of the predetermined area (500).

[0077] The predetermined area (500) may have a size corresponding to the pet. For example, as the weight of the preset pet increases, the size of the predetermined area (500) may increase. Depending on the size of the predetermined area (500), the width (W) and / or length (L) of the predetermined area (500) may vary.

[0078] In one embodiment, the size of the predetermined area (500) may correspond to the breed of the companion animal. In the present disclosure, the companion animal is exemplified as a dog, but is not limited thereto.

[0079] Referring to FIG. 6, the companion animal device (10) can determine a predetermined area (500) based on a database (151) containing data corresponding to the breed of the companion animal. The database (151) can be stored in the memory (150) of the companion animal device (10). The database (151) can also be stored in a server (30).

[0080] Data corresponding to the pet's breed may include the size of a predetermined area (500) corresponding to the pet's breed, age, weight, etc. Depending on the pet's breed, the pet's skeleton, such as leg length, waist length, head size, etc., may differ. Therefore, if the pet's breed is different, the size of the predetermined area (500) may be determined differently even if the weight is the same.

[0081] According to one embodiment, the companion animal device (10) can determine the size of a predetermined area (500) based on an image acquired through a camera (130). For example, the companion animal device (10) can determine the size of a predetermined area (500) by processing images containing a companion animal acquired through the camera (130) over a predetermined period of time.

[0082] The companion animal device (10) can detect an area corresponding to a companion animal from an image containing the companion animal using the YOLO (You Only Look Once) model. At this time, the companion animal device (10) can determine the size of a predetermined area (500) based on a representative value of the sizes of areas corresponding to companion animals detected over a predetermined period of time (e.g., 3 days).

[0083] The companion animal device (10) can obtain skeleton data corresponding to the companion animal's skeleton from an image containing the companion animal using a learning model. For example, the skeleton data may include a plurality of joints corresponding to each body part of the companion animal, a skeleton connecting the plurality of joints, etc. In this case, the companion animal device (10) can obtain information about the companion animal's skeleton, such as leg length, waist length, etc., based on the skeleton data. In addition, the companion animal device (10) can correct the size of a predetermined area (500) set based on a database (151) based on the information about the companion animal's skeleton. That is, even if the companion animal's breed is the same, considering that each object has a different skeleton, the size of the predetermined area (500) can be optimized for the companion animal.

[0084] Referring to FIG. 7, the companion animal device (10) can determine an area (700) corresponding to the companion animal (1) based on an image acquired through the camera (130). For example, the companion animal device (10) can determine an area (700) corresponding to the companion animal (1) included in the image acquired through the camera (130) using a YOLO (you Only Look Once) model.

[0085] The companion animal device (10) can determine the degree of overlap between a predetermined area (500) and an area (700) corresponding to the companion animal (1). At this time, the companion animal device (10) can determine that the companion animal (1) is located in the predetermined area if the degree of overlap between the predetermined area (500) and the area (700) corresponding to the companion animal (1) is greater than or equal to a predetermined standard. For example, the companion animal device (10) can determine that the companion animal (1) is located in the predetermined area if the ratio of the area overlapping with the area (700) corresponding to the companion animal (1) among the predetermined areas (500) is greater than or equal to a predetermined ratio (e.g., 90%).

[0086] Referring to FIG. 8, the companion animal device (10) can determine the degree of overlap between a predetermined area (500) and an area (700) corresponding to the companion animal (1). At this time, if the ratio of the area (800) overlapping with the area (700) corresponding to the companion animal (1) among the predetermined areas (500) is 70%, which is less than the predetermined ratio (e.g., 90%), it can be determined that the companion animal (1) is not located in the predetermined area.

[0087] Meanwhile, referring to FIG. 9, the companion animal device (10) can determine the degree of overlap between a predetermined area (500) and an area (700) corresponding to the companion animal (1). At this time, if the ratio of the area (900) overlapping with the area (700) corresponding to the companion animal (1) among the predetermined areas (500) is 100%, which is greater than or equal to a predetermined ratio (e.g., 90%), it can be determined that the companion animal (1) is located in the predetermined area.

[0088] Referring back to FIG. 4, the companion animal device (10) can, in operation S450, determine whether the companion animal's posture corresponds to a predetermined posture when the companion animal is positioned in a predetermined area. Here, the predetermined posture may refer to a posture for measuring the companion animal's body temperature. For example, in the case of a dog, the predetermined posture may be a posture in which the belly, a body part with relatively little hair, touches the floor. Meanwhile, the predetermined posture may vary depending on the companion animal's breed.

[0089] When a pet is standing or a part of the pet with relatively thick fur touches the floor, the temperature detected by the temperature sensor (122) may be lower than the pet's actual body temperature. For example, the temperature detected by the temperature sensor (122) when the pet's body temperature is normal may be 38.5°C when the pet's belly touches the floor, whereas it may be 35°C when the pet's back, which has relatively thick fur, touches the floor. Therefore, the pet device (10) can detect the pet's body temperature based on the temperature detected by the temperature sensor (122) when the pet's posture corresponds to a predetermined posture.

[0090] In one embodiment, the companion animal device (10) can determine the companion animal's posture based on the direction in which the companion animal's body parts are facing. For example, the companion animal device (10) can determine the companion animal's posture based on the direction in which the companion animal's head is facing, the respective directions in which the companion animal's front and rear paws are facing, the position of the companion animal's tail, etc.

[0091] According to one embodiment, the companion animal device (10) can determine the companion animal's posture based on skeleton data. The companion animal device (10) can determine the companion animal's posture based on the joints and skeleton of the companion animal included in the skeleton data.

[0092] Referring to FIG. 10, the device for a pet (10) can determine that the pet (1) is in a lying position with its belly on the floor (102) based on the joint (1010) and the frame (1020) for the pet (1).

[0093] Meanwhile, referring to FIG. 11, the companion animal device (10) can determine, based on the joint (1110) and frame (1120) for the companion animal (1), that the companion animal (1) is in a side-lying position with its stomach separated from the bottom (102).

[0094] Referring back to FIG. 4, in operation S460, the companion animal device (10) can determine whether the companion animal maintains the posture for a predetermined period of time if the companion animal's posture corresponds to a predetermined posture. For example, if the companion animal's posture corresponds to a posture in which the companion animal's belly touches the floor, the companion animal device (10) can count the time the companion animal maintains the posture in which the belly touches the floor.

[0095] The companion animal device (10) can obtain the body temperature of the companion animal when the companion animal maintains a posture for a predetermined period of time in operation S470. For example, the companion animal device (10) can obtain the body temperature of the companion animal based on the temperature detected by the temperature sensor (122) when the companion animal maintains a posture for a predetermined period of time. For example, the companion animal device (10) can obtain the body temperature of the companion animal based on the temperature detected by the temperature sensor (122) during the predetermined period of time during which the companion animal maintains the posture.

[0096] The companion animal device (10) can transmit data on the companion animal's body temperature to a user terminal (20) and / or a server (30). The companion animal device (10) can output a message on the companion animal's condition using an input / output interface (140) based on the companion animal's body temperature.

[0097] As described above, according to embodiments of the present disclosure, the body temperature of a companion animal can be monitored.

[0098] Additionally, according to embodiments of the present disclosure, the body temperature of a companion animal can be accurately measured.

[0099] Additionally, according to embodiments of the present disclosure, various settings used for measuring the body temperature of a companion animal can be optimized.

[0100] Additionally, according to embodiments of the present disclosure, messages related to the health status of a companion animal can be provided to the guardian.

[0101] Referring to FIGS. 1 to 11, a companion animal device (10) according to one aspect of the present disclosure includes a housing (100); a camera (130) for photographing an internal space (105) of the housing (100); a temperature sensor (122) disposed adjacent to a bottom portion (102) of the housing (100); and a control unit (160). When a companion animal (1) is detected in a predetermined image acquired through the camera (130), the control unit (160) determines whether the companion animal (1) is located in a predetermined area of ​​the bottom portion (102) corresponding to the temperature sensor (122) based on the predetermined image, and when the companion animal (1) is located in the predetermined area, the body temperature of the companion animal (1) can be acquired through the temperature sensor (122).

[0102] In addition, according to one aspect of the present disclosure, the control unit (160) can detect the companion animal (1) included in the predetermined image using a YOLO (you Only Look Once) model.

[0103] In addition, according to one aspect of the present disclosure, the control unit (160) may determine that the pet (1) is located in the predetermined area when the ratio of the second area overlapping the first area corresponding to the pet (1) among the predetermined areas is greater than or equal to a predetermined ratio, and may determine that the pet (1) is not located in the predetermined area when the ratio of the second area among the predetermined areas is less than the predetermined ratio.

[0104] Additionally, according to one aspect of the present disclosure, the size of the predetermined area may increase as the preset weight of the companion animal (1) increases.

[0105] In addition, according to one aspect of the present disclosure, the control unit (160) can acquire images including the companion animal (1) through the camera (130) for a predetermined period of time, and determine a representative value of the size of an area corresponding to the companion animal (1) included in the images as the size of the predetermined area.

[0106] In addition, according to one aspect of the present disclosure, a memory is further included in which a database including the size of the predetermined area corresponding to the breed is stored, and the control unit (160) can determine the size of the predetermined area corresponding to the breed set for the companion animal (1).

[0107] In addition, according to one aspect of the present disclosure, the control unit (160) can obtain skeleton data corresponding to the skeleton of the companion animal (1) based on images including the companion animal (1) acquired through the camera (130) over a predetermined period of time, and correct the size of the predetermined area corresponding to the breed based on the skeleton data.

[0108] In addition, according to one aspect of the present disclosure, the control unit (160) can determine the posture of the companion animal (1) when the companion animal (1) is located in the predetermined area, and obtain the body temperature of the companion animal (1) based on the posture of the companion animal (1) corresponding to the predetermined posture.

[0109] In addition, according to one aspect of the present disclosure, the control unit (160) can obtain skeleton data corresponding to the skeleton of the companion animal (1) based on the predetermined image, and determine the posture of the companion animal (1) based on the skeleton data.

[0110] In addition, according to one aspect of the present disclosure, when the posture of the companion animal (1) corresponds to a predetermined posture, the control unit (160) can count the time for which the companion animal (1) maintains the predetermined posture, and when the time for which the companion animal (1) maintains the predetermined posture is longer than a predetermined time, the control unit (160) can obtain the body temperature of the companion animal (1).

[0111] In addition, according to one aspect of the present disclosure, the housing (100) further includes a weight sensor (121) disposed adjacent to the bottom (102), and the control unit (160) can drive the camera (130) to acquire the predetermined image when the weight detected through the weight sensor (121) is within a predetermined weight range corresponding to a preset weight.

[0112] In addition, according to one aspect of the present disclosure, the control unit (160) updates the preset weight based on a representative value of weights detected multiple times through the weight sensor (121), and the weights detected multiple times may be detected when the companion animal (1) is detected in an image acquired through the camera (130).

[0113] In addition, according to one aspect of the present disclosure, the temperature sensor (122) may be an IR (infrared) sensor that is positioned at a predetermined distance downward from the bottom portion (102) and faces the internal space (105).

[0114] In addition, according to one aspect of the present disclosure, a communication interface (110) for communicating with a server is further included, and when the control unit (160) obtains the body temperature of the companion animal (1), it can transmit data on the obtained body temperature to the server through the communication interface (110).

[0115] The attached drawings are only intended to facilitate understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, or substitutes included in the spirit and technical scope of the present disclosure.

[0116] Meanwhile, the operating method of the present disclosure can be implemented as processor-readable code on a processor-readable recording medium. A processor-readable recording medium includes all types of recording devices that store data that can be read by a processor. Examples of processor-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage devices, etc., and also include those implemented in the form of a carrier wave, such as transmission via the Internet. Furthermore, the processor-readable recording medium can be distributed across network-connected computer systems, so that the processor-readable code can be stored and executed in a distributed manner.

[0117] In addition, although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary skill in the art to which the present invention pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. Housing; A camera that photographs the interior space of the housing; a temperature sensor positioned adjacent to the bottom of the housing; and Including a control unit, The above control unit, When a pet is detected in a predetermined image acquired through the above camera, it is determined based on the predetermined image whether the pet is located in a predetermined area of ​​the floor corresponding to the temperature sensor, A device for a pet, characterized in that the body temperature of the pet is acquired through the temperature sensor when the pet is located in the predetermined area.

2. In paragraph 1, The above control unit, A device for a pet, characterized in that it detects the pet included in the predetermined image using the YOLO (you Only Look Once) model.

3. In paragraph 1, The above control unit, If the ratio of the second area overlapping the first area corresponding to the pet among the above-mentioned predetermined areas is greater than or equal to a predetermined ratio, it is determined that the pet is located in the above-mentioned predetermined area, A device for a pet, characterized in that when the ratio of the second area among the above-mentioned predetermined areas is less than the above-mentioned predetermined ratio, it is determined that the pet is not located in the above-mentioned predetermined area.

4. In paragraph 1, A device for a pet, characterized in that the size of the above-mentioned predetermined area increases as the preset weight of the pet increases.

5. In paragraph 1, The above control unit, Acquire images containing the pet through the camera for a predetermined period of time, A device for a pet, characterized in that a representative value of the size of an area corresponding to the pet included in the above images is determined as the size of the predetermined area.

6. In paragraph 1, Further comprising a memory in which a database including the size of the above-mentioned predetermined area corresponding to the variety is stored, The above control unit, A device for a pet, characterized in that the size of the predetermined area is determined in response to a preset breed of the pet.

7. In paragraph 6, The above control unit, Based on images containing the companion animal acquired through the camera over a predetermined period of time, skeleton data corresponding to the skeleton of the companion animal is acquired, A device for a companion animal characterized in that the size of the predetermined area corresponding to the breed is corrected based on the skeleton data.

8. In paragraph 1, The above control unit, When the above pet is located in the above-mentioned area, the posture of the pet is determined, A device for a pet, characterized in that the body temperature of the pet is acquired based on the posture of the pet corresponding to a predetermined posture.

9. In paragraph 8, The above control unit, Obtaining skeleton data corresponding to the skeleton of the companion animal based on the above-mentioned predetermined image, A device for a pet, characterized in that the posture of the pet is determined based on the skeleton data.

10. In paragraph 8, The above control unit, If the posture of the above pet corresponds to a predetermined posture, the time for which the pet maintains the predetermined posture is counted, A device for a pet characterized in that the body temperature of the pet is acquired when the time for which the pet maintains the above-mentioned predetermined posture is longer than a predetermined time.

11. In paragraph 1, Further comprising a weight sensor positioned adjacent to the bottom of the housing, The above control unit, A device for a pet, characterized in that when the weight detected through the weight sensor falls within a predetermined weight range corresponding to a preset weight, the camera is driven to acquire the predetermined image.

12. In paragraph 11, The above control unit, Based on the representative value of the weights detected multiple times through the above weight sensor, the preset weight is updated, A device for a pet, characterized in that the weights detected multiple times are detected when the pet is detected in an image acquired through the camera.

13. In paragraph 1, The above temperature sensor, A pet device characterized by an IR (infrared) sensor positioned at a predetermined distance downward from the floor and facing the internal space.

14. In paragraph 1, Further comprising a communication interface for communicating with the server, The above control unit, A device for a companion animal characterized in that, when the body temperature of the companion animal is acquired, data on the acquired body temperature is transmitted to the server through the communication interface.

Images