Methods, systems, terminal equipment and storage media for monitoring dog and cat food intake

Abstract

This application relates to the field of pet food palatability testing, and provides a method, system, terminal device, and storage medium for monitoring dog and cat eating habits. The method includes: acquiring first video data of a dog or cat during the eating process captured by a first camera; the first video data being used to characterize the overall behavior of the dog or cat during the eating process; acquiring second video data of the dog or cat during the eating process captured by a second camera; the second video data being used to characterize the head movements of the dog or cat during the eating process; extracting features from the first video data to obtain key body part attributes corresponding to the dog or cat's eating process; extracting features from the second video data to obtain action state attributes corresponding to the dog or cat's eating process; and determining the dog or cat's eating behavior based on the key body part attributes and action state attributes. This method can comprehensively collect various data during the dog or cat's eating process, forming an integrated analysis system of multi-source heterogeneous data, thus improving the comprehensiveness and accuracy of the monitoring.

Description

Technical Field

[0001] This application belongs to the field of pet food palatability testing, and in particular relates to a method, system, terminal equipment and storage medium for monitoring dog and cat food consumption. Background Technology

[0002] With the rapid development of the pet food industry and the continuous deepening of research on pet palatability, accurate monitoring of canine and cat eating behavior has become a key link in pet food research and development and palatability testing. At present, the industry mainly relies on manual observation or simple video recording to carry out relevant monitoring work, and the supporting hardware devices can only observe the overall behavior.

[0003] The related technologies also suffer from problems such as insufficient optimization of behavior recognition algorithms, lack of personalized evaluation mechanisms, and incomplete utilization of multi-source heterogeneous data. Overall, they expose drawbacks such as missing observation details, short data retention period and cumbersome export operations, and low efficiency in analysis and monitoring. At the same time, traditional manual monitoring is limited by labor costs, the observation perspective of behavior testing is singular, it is difficult to capture the details of dog and cat eating behavior in the mouth and face, and remote analysis is not possible. The existence of many industry pain points urgently requires a dog and cat eating behavior monitoring solution that can achieve automated, refined behavior capture and intelligent analysis. Summary of the Invention

[0004] This application provides a method, system, terminal device, and storage medium for monitoring dog and cat feeding, which can comprehensively collect various data during the dog and cat feeding process, forming an integrated analysis system of multi-source heterogeneous data, and improving the comprehensiveness and accuracy of monitoring.

[0005] In a first aspect, embodiments of this application provide a method, system, terminal device, and storage medium for monitoring dog and cat feeding, applied to a dog and cat feeding monitoring system. The dog and cat feeding monitoring system further includes a feeding box, with a first camera positioned above the feeding area in the feeding box; and a second camera positioned below the feeding base of the feeding area; wherein the feeding base is made of transparent glass; the method includes: Acquire first video data of dogs and cats during the feeding process captured by a first camera; wherein, the first video data is used to characterize the overall behavior of dogs and cats during the feeding process; Acquire second video data of dogs and cats during the feeding process captured by a second camera; wherein, the second video data is used to characterize the head movements of dogs and cats during the feeding process; Feature extraction was performed on the first video data to obtain the key body part attributes corresponding to the dog and cat feeding process; Feature extraction was performed on the second video data to obtain the action state attributes corresponding to the dog and cat's feeding process; The feeding behavior of dogs and cats during the feeding process is determined based on the attributes of key body parts and the attributes of their movement status.

[0006] In this embodiment, a first camera and a second camera are respectively positioned above the feeding area and below the transparent glass feeding base to simultaneously capture overall behavior video and fine head movement video. Key body part attributes and movement state attributes are extracted and comprehensively determined to assess the feeding behavior. The use of complementary dual-view, multi-source data covers both overall posture and captures details of the mouth and head, overcoming the limitations of traditional single-view methods that cannot observe fine feeding movements. This significantly improves the completeness and accuracy of behavior recognition, enabling comprehensive collection of various data during the dog / cat feeding process. It forms an integrated analysis system of multi-source heterogeneous data, enhancing the comprehensiveness and accuracy of monitoring.

[0007] In one possible implementation of the first aspect, the target video data is either first video data or second video data, and the target features are key part attributes or action state attributes; the steps of extracting features from the target video data to obtain the target features include: Frame segmentation is performed on the target video data to obtain multiple first frames; Image target enhancement processing is performed on the first image of each frame to obtain the second image; Feature extraction is performed on each frame of the second image to obtain the target features corresponding to each frame of the second image; wherein, when the target video data is the first video data, the target features are key part attributes; when the target video data is the second video data, the target features are action state attributes.

[0008] In this embodiment of the application, by performing standardized frame segmentation, image enhancement and targeted feature extraction on video data from different perspectives, it is possible to accurately obtain the overall key part attributes and head action state attributes of dogs and cats eating, providing high-quality and differentiated feature data support for subsequent behavior judgment.

[0009] In one possible implementation of the first aspect, the feeding behavior of dogs and cats during the feeding process is determined based on key body part attributes and action state attributes, including: By fusing key body part attributes and action state attributes at the same moment, comprehensive characteristic attributes of dogs and cats at different moments are obtained; The feeding behavior of dogs and cats during the feeding process is determined based on comprehensive characteristic attributes.

[0010] In this embodiment of the application, the feeding behavior is determined by fusing the overall part attributes and head action attributes acquired at the same moment from dual perspectives into a comprehensive feature attribute. This can eliminate the limitations of single-view features and greatly improve the comprehensiveness and accuracy of dog and cat feeding behavior recognition.

[0011] In one possible implementation of the first aspect, the feeding behavior of dogs and cats during the feeding process is determined based on comprehensive characteristic attributes, including: The comprehensive feature attributes are matched with the preset behavioral feature library; If the behavioral feature store contains a first behavioral feature that matches the comprehensive feature attribute, then the first behavioral feature is determined as the current feeding behavior of the dog or cat.

[0012] In this embodiment, by matching comprehensive feature attributes with a preset behavioral feature library to determine feeding behavior, standardized, automated, objective and accurate behavior recognition can be achieved, avoiding human judgment errors and improving recognition efficiency and consistency.

[0013] In one possible implementation of the first aspect, various feeding behaviors of dogs and cats during the feeding process are scored to obtain feeding score results for dogs and cats; The palatability rating of the food consumed by dogs and cats is determined based on the scoring results; A feeding behavior score report is generated based on the feeding score and palatability rating.

[0014] In this embodiment, the fused comprehensive feature attributes are matched with a preset behavioral feature library to determine the feeding behavior, thereby achieving standardized and automated identification of canine and cat feeding behavior and ensuring the objectivity and consistency of the behavior determination results.

[0015] Secondly, this application provides a dog and cat feeding monitoring system, including a control device and a feeding box. A first camera is installed above the feeding area in the feeding box; a second camera is installed below the feeding base plate of the feeding area; wherein the feeding base plate is made of transparent glass. The control device is used to implement the dog and cat feeding monitoring method as described in any of the first aspects above; The first camera is used to collect initial video data of the dogs and cats during the feeding process; The second camera is used to collect secondary video data of dogs and cats during the feeding process.

[0016] In one possible implementation of the second aspect, camera tracks are respectively set above and below the feeding area of ​​the feeding box; the camera tracks are used to adjust the sampling position according to the position of the dog or cat; and the second camera automatically adjusts the sampling angle according to the head movement of the dog or cat.

[0017] In one possible implementation of the second aspect, supplementary lights are installed above and below the feeding area of ​​the feeding box, and the supplementary lights are used to adjust the light in the feeding box.

[0018] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the dog and cat feeding monitoring method as described in any of the first aspects above.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the dog and cat feeding monitoring method as described in any of the first aspects above.

[0020] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the dog and cat feeding monitoring method described in any of the first aspects above.

[0021] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the feeding box provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the dog and cat feeding monitoring method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the process for feature extraction from video data provided in an embodiment of this application; Figure 4 This is a schematic diagram of the process for determining feeding behavior provided in the embodiments of this application. Figure 1 ; Figure 5 This is a schematic diagram of the process for determining feeding behavior provided in the embodiments of this application. Figure 2 ; Figure 6 This is a schematic diagram of the process for generating a feeding score report provided in an embodiment of this application; Figure 7 This is a time-series flowchart of canine and cat feeding behavior provided in the embodiments of this application; Figure 8 This is a system flowchart of the dog and cat feeding monitoring method provided in the embodiments of this application; Figure 9 This is a schematic diagram illustrating the classification of dog and cat eating behavior tags provided in an embodiment of this application; Figure 10 This is a schematic diagram illustrating the weighting of canine and feline feeding behavior scoring in an embodiment of this application; Figure 11This is a schematic diagram illustrating the classification of palatability levels for dogs and cats provided in the embodiments of this application; Figure 12 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0025] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0026] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0028] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0030] With the rapid development of the pet food industry and the continuous deepening of research on pet palatability, accurate monitoring of canine and cat eating behavior has become a key link in pet food research and development and palatability testing. At present, the industry mainly relies on manual observation or simple video recording to carry out relevant monitoring work, and the supporting hardware devices can only observe the overall behavior.

[0031] The related technologies also suffer from problems such as insufficient optimization of behavior recognition algorithms, lack of personalized evaluation mechanisms, and incomplete utilization of multi-source heterogeneous data. Overall, they expose drawbacks such as missing observation details, short data retention period and cumbersome export operations, and low efficiency in analysis and monitoring. At the same time, traditional manual monitoring is limited by labor costs, the observation perspective of behavior testing is singular, it is difficult to capture the details of dog and cat eating behavior in the mouth and face, and remote analysis is not possible. The existence of many industry pain points urgently requires a dog and cat eating behavior monitoring solution that can achieve automated, refined behavior capture and intelligent analysis.

[0032] To address the aforementioned issues, this application provides a method, system, terminal device, and storage medium for monitoring dog and cat feeding behavior. Employing a combined hardware and software design, it utilizes dual cameras—one above the feeding area and one below a transparent glass base—along with adjustable tracks and supplementary lighting, to achieve multi-angle, multi-source heterogeneous data acquisition. Through video frame segmentation, Gaussian smoothing, and image morphological processing, intelligent behavioral recognition is achieved, and personalized scoring and report generation are performed using a scoring method. This system can automatically monitor dog and cat feeding behavior 24 hours a day, comprehensively collecting various data during the feeding process and forming an integrated analysis system for multi-source heterogeneous data, thus improving the comprehensiveness and accuracy of monitoring.

[0033] See Figure 1 This is a schematic diagram of the feeding box provided in the embodiments of this application. A first camera is arranged above the feeding area in the feeding box; a second camera is arranged below the feeding base plate of the feeding area; wherein the feeding base plate is made of transparent glass.

[0034] Inside the feeding box, directly above the designated feeding area for pets, is a first camera (panoramic camera) ②, primarily used to capture the pet's overall posture, body movements, and eating process. Simultaneously, below the feeding area's base plate, is a second camera (panoramic camera) ②. To ensure the lower camera can clearly and unobstructedly capture key feeding details such as the pet's mouth and face, the feeding base plate is specially made of transparent glass (10mm reinforced tempered glass plate) ④. This provides clear shooting conditions for the bottom camera without affecting the pet's normal standing and eating, thereby enabling the dual cameras to collect feeding behavior data from multiple angles and in all directions.

[0035] In one embodiment, camera tracks are respectively installed above and below the feeding area of ​​the feeding box; the camera tracks are used to adjust the sampling position according to the position of the dog or cat; and the second camera automatically adjusts the sampling angle according to the head movements of the dog or cat.

[0036] The feeding box is equipped with camera rails (left and right convenient guide rails) ⑤⑥⑦⑧ and stepper motors (front and back direction and left and right direction) ①③ above and below the feeding area. The rails can automatically adjust the camera's acquisition position according to the actual position of the dog or cat during the feeding process, ensuring that the shooting image is always aimed at the feeding subject. At the same time, the second camera ② located below the feeding base can also automatically adjust the acquisition angle in real time according to the head movement of the dog or cat, ensuring clear and complete capture of the fine feeding movements of the head and mouth.

[0037] In one embodiment, supplementary lights are installed above and below the feeding area of ​​the feeding box, and the supplementary lights are used to adjust the light in the feeding box.

[0038] The feeding box is equipped with supplemental lighting above and below the feeding area. The supplementary light is used to adjust the brightness inside the feeding box, avoiding problems such as excessive darkness, reflections, or glare in the image. It provides a uniform, stable, and clear shooting lighting environment for the two cameras, ensuring the accuracy of video capture and behavior recognition. In addition, the feeding box also includes a framed glass door⑨ and a wooden cabinet⑩.

[0039] In use Figure 1 Before monitoring dog and cat feeding in the feeding box shown, the hardware and software of the dog and cat feeding monitoring system are started, parameters are set, and linkage is debugged to ensure the system can enter a normal working state for data collection, analysis, and scoring. For example, the supplementary lights at the top and bottom of the feeding box are first turned on and adjusted to a uniform, glare-free lighting state. The first and second cameras are then adjusted to their initial acquisition positions in the corresponding feeding areas using the camera track, and the angle of the second camera is pre-calibrated. At the same time, a feeding behavior database is established or loaded, and algorithm parameters such as video frame segmentation, Gaussian smoothing, feature extraction, behavior matching, and scoring are preset, along with behavioral feature libraries and palatability level standards. This ensures that the cameras, supplementary lights, track, and analysis software are all in sync and ready to carry out dog and cat feeding monitoring normally.

[0040] In addition, a dedicated database is built within the dog and cat feeding monitoring system to structure and store all relevant data generated during the feeding process, enabling unified management, retention, and reuse of data. This provides data support for subsequent behavior analysis, palatability assessment, and data review. If the database is built and configured during the initialization phase, it stores various types of feeding behavior-related data according to a preset data structure. This includes basic dog and cat information (breed, age, weight), raw video data collected by the first / second camera, image data after frame segmentation, extracted key body part attributes / action state attributes, fused comprehensive feature attributes, identified feeding behavior types, detailed scores for each behavior, total feeding score, palatability level, and the final generated scoring report.

[0041] For example, the database archives data according to the dimensions of "dog / cat ID-feeding time-food type". It can quickly query the video data of a British Shorthair cat eating cat food A on March 21, 2026, the scores of various behaviors (5 points for immediate eating, 4 points for continuous eating), the total score of 9 points, the palatability level of excellent, and other full information, supporting subsequent data retrieval, statistical analysis and scientific research reuse.

[0042] See Figure 2 This is a flowchart illustrating the dog and cat feeding monitoring method provided in this application embodiment. It is intended as an example and not a limitation. The method may include the following steps: S101, acquire first video data of dogs and cats during the feeding process captured by the first camera; wherein, the first video data is used to characterize the overall behavior of dogs and cats during the feeding process.

[0043] In this embodiment of the application, a first camera located above the feeding area is invoked to collect complete video data of the dog or cat from the start to the end of eating, namely the first video data, which is specifically used to reflect the overall behavior of the dog or cat during feeding.

[0044] For example, while dogs and cats are eating in the feeding area of ​​the feeding box, the first camera located directly above the feeding area will continuously record and generate the first video data in real time. This video will fully record the dog's or cat's body posture, standing position, head movements, eating rhythm, and overall eating actions during the feeding process. It is specifically used to reflect and characterize the dog's or cat's overall behavior during the entire feeding process, providing comprehensive overall perspective data for subsequent behavior recognition, analysis, and scoring.

[0045] S102, acquire second video data of dogs and cats during the feeding process captured by the second camera; wherein, the second video data is used to characterize the head movements of dogs and cats during the feeding process.

[0046] In this embodiment of the application, a second camera located below the transparent feeding base is used to capture video of the entire feeding process of dogs and cats, which is specifically used to capture and reflect the fine movements of dogs and cats' heads and mouths while feeding.

[0047] For example, during the feeding process of dogs and cats in the feeding box, a second camera installed under the transparent glass feeding base will continuously record, capturing second video data of dogs and cats eating through the transparent glass. This video can clearly capture the fine head-related behaviors of dogs and cats, such as lowering their heads to eat, chewing with their mouths, licking with their tongues, and facial movements. It is specifically used to characterize the details of the head movements of dogs and cats throughout the feeding process, providing key close-up, high-detail video information for the system to accurately analyze feeding behavior and conduct palatability evaluation.

[0048] S103, feature extraction is performed on the first video data to obtain the key body attributes corresponding to the dog and cat feeding process.

[0049] In this embodiment, the system performs algorithmic processing on the video of the dog and cat eating behavior captured by the first camera above, extracts key feature information that can represent the eating state, and obtains relevant attribute data of key parts of the dog and cat's body during the eating process, providing a basis for subsequent behavior recognition and analysis.

[0050] S104, extract features from the second video data to obtain the action state attributes corresponding to the dog and cat eating process.

[0051] In this embodiment, the system performs algorithmic analysis and feature extraction on the video of dogs and cats eating through transparent glass captured by the bottom second camera. It identifies and extracts the core action features that reflect the eating situation, and finally obtains the action state attributes of the head, mouth and other parts of the dog and cat during the eating process, providing a detailed action basis for subsequent behavior judgment and scoring.

[0052] In one embodiment, see Figure 3 This is a schematic diagram of the feature extraction process for video data provided in an embodiment of this application, such as... Figure 3 As shown, the target video data is either the first video data or the second video data, and the target features are key body part attributes or action state attributes; the steps for extracting features from the target video data to obtain the target features include: S201, perform frame segmentation on the target video data to obtain multiple first frames.

[0053] In this embodiment of the application, the target video data (feeding video captured by the first / second camera) is split into continuous single-frame still images according to time to prepare for subsequent image feature extraction, which is a standard preprocessing step for video analysis.

[0054] For example, first determine whether the target video data to be processed is the overall behavior video captured by the first camera or the head action video captured by the second camera. Then, use a video image segmentation algorithm to split the continuously playing target video stream at fixed time intervals or frame by frame, and sequentially extract a series of ordered, non-overlapping single-frame first images so that each frame can independently present the scene of the dog or cat eating at a certain moment, which is convenient for subsequent Gaussian smoothing, morphological processing and feature extraction of the images.

[0055] S202, perform image target enhancement processing on the first image of each frame to obtain the second image.

[0056] In this embodiment of the application, Gaussian smoothing algorithm is used to enhance the image target, reduce noise and highlight the feeding subject (dog and cat) and feeding action for each frame of the split image, so as to obtain a clearer image that is suitable for feature extraction, namely the second image.

[0057] For example, each frame of the first image obtained from frame segmentation is sequentially traversed, with the dog / cat's head and feeding area as the target region. A Gaussian filter function is used to perform convolution smoothing on the image. While removing image noise and weakening background interference, the target edge and feeding action details are preserved, and the visual difference between the target subject and the background is increased. Finally, a second image with higher clarity and less interference is generated, providing high-quality image data for subsequent feature extraction and behavior recognition.

[0058] S203, extract features from each frame of the second image to obtain the target features corresponding to each frame of the second image; wherein, when the target video data is the first video data, the target features are key part attributes; when the target video data is the second video data, the target features are action state attributes.

[0059] In this embodiment, for each frame of the second image after Gaussian smoothing and noise reduction enhancement, feature extraction is performed frame by frame and behavior labeling is completed simultaneously. The extracted and labeled feature types are automatically distinguished according to the video source (first / second camera) - key part attributes are extracted and labeled in the first video, and action state attributes are extracted and labeled in the second video.

[0060] For example, all second images obtained after Gaussian smoothing are traversed frame by frame. Feature extraction and synchronous labeling are performed on each frame. When the target video data is the first video data captured by the first camera, key attributes such as the dog's body posture, feeding position, tail state, and overall movement trajectory are identified and extracted from the image, and the above attributes are labeled accordingly. When the target video data is the second video data captured by the second camera, action state attributes such as the dog's head posture, chewing action, and facial feeding details are identified and extracted from the image, and the above attributes are labeled accordingly. Finally, target features and labeling results matching the video source are generated and bound for each frame of the second image.

[0061] The above method, by performing standardized frame segmentation, image enhancement, and targeted feature extraction on video data from different perspectives, can accurately obtain the overall key part attributes and head movement state attributes of dogs and cats eating, providing high-quality and differentiated feature data support for subsequent behavior judgment.

[0062] S105, determine the feeding behavior of dogs and cats during the feeding process based on key body part attributes and action state attributes.

[0063] In this embodiment, the overall key part attributes obtained by the upper camera and the head movement state attributes obtained by the lower camera are combined to comprehensively judge the real and complete eating behavior of dogs and cats when eating, rather than looking at data from only a single perspective, so that the recognition results are more accurate and comprehensive.

[0064] In the above method, a first camera and a second camera are respectively installed above the feeding area and below the transparent glass feeding base to simultaneously capture overall behavior video and fine head movement video. Key body part attributes and movement state attributes are extracted and comprehensively judged to determine the feeding behavior. The method employs complementary dual-view, multi-source data, covering both overall posture and capturing details of the mouth and head. This overcomes the limitation of traditional single-view methods that cannot observe fine feeding movements, significantly improving the completeness and accuracy of behavior recognition. It comprehensively collects various data during the feeding process of dogs and cats, forming an integrated analysis system of multi-source heterogeneous data, thus improving the comprehensiveness and accuracy of monitoring.

[0065] In one embodiment, see Figure 4 This is a flowchart illustrating the process of determining feeding behavior provided in the embodiments of this application. Figure 1 ,like Figure 4 As shown, step S105 includes: S301 integrates key body part attributes and action state attributes at the same moment to obtain comprehensive characteristic attributes of dogs and cats at different moments.

[0066] In this embodiment, feature data from two cameras at the same time point are aligned and merged, and the overall part attributes and head movement attributes are fused into a complete set of features for accurate determination of feeding behavior.

[0067] For example, based on the video timestamp, the key part attributes extracted by the first camera and the action state attributes extracted by the second camera at the same time are time-series aligned and data fused. The overall posture, part information and head feeding action information at the same time point are integrated into a single comprehensive feature attribute. Comprehensive features corresponding to different times in the entire feeding process of dogs and cats are generated in time sequence, providing a complete and unified feature basis for subsequent feeding behavior recognition and scoring.

[0068] S302, Determine the feeding behavior of dogs and cats during the feeding process based on comprehensive characteristic attributes.

[0069] In this embodiment, intelligent judgment is made based on the complete and comprehensive feature attributes fused from the dual cameras at the same time, and the true and accurate type and state of the dog or cat's eating behavior during the feeding process are finally determined, avoiding the recognition bias caused by single-view features and making the behavior judgment more comprehensive and reliable.

[0070] The above method integrates the overall part attributes and head movement attributes acquired at the same moment from dual perspectives into a comprehensive feature attribute to determine the feeding behavior. This can eliminate the limitations of single-view features and greatly improve the comprehensiveness and accuracy of dog and cat feeding behavior recognition.

[0071] In one embodiment, see Figure 5 This is a flowchart illustrating the process of determining feeding behavior provided in the embodiments of this application. Figure 2 ,like Figure 5 As shown, step S302 includes: S401, match the comprehensive feature attributes with the preset behavioral feature library.

[0072] In this embodiment of the application, the integrated feature attributes of dogs and cats during feeding are compared and matched with a pre-set standard feeding behavior feature library in the system, so as to automatically identify the corresponding feeding behavior type.

[0073] For example, the system compares the comprehensive feature attributes obtained after time alignment with a pre-established and stored standard feeding behavior feature library one by one and calculates the similarity. The feature matching algorithm determines which standard feeding behavior feature in the library is most similar to the comprehensive feature attributes, thereby completing the automatic identification and classification of real-time feeding behavior of dogs and cats.

[0074] S402, if the behavioral feature store contains a first behavioral feature that matches the comprehensive feature attribute, then the first behavioral feature is determined as the current feeding behavior of the dog or cat.

[0075] In this embodiment of the application, when the system matches a standard behavioral feature in the feature library that is consistent with the real-time comprehensive feature, it directly determines this standard feature as the feeding behavior that the dog or cat is currently exhibiting, thus completing the behavior recognition.

[0076] For example, the system compares the similarity of the fused comprehensive feature attributes with each standard behavioral feature in the behavioral feature library. When the similarity reaches a preset threshold and is determined to be a successful match, it is determined that there is a corresponding first behavioral feature. Subsequently, the system automatically identifies the first behavioral feature as the dog or cat's eating behavior at the current moment and outputs the recognition result. For example, if the comprehensive feature attributes include "head continuously lowered, mouth continuously chewing, and body posture stable", and it is successfully matched with the first behavioral feature "normal continuous eating" in the feature library, then the system determines that the current dog or cat's behavior is normal continuous eating.

[0077] The above method determines feeding behavior by matching comprehensive feature attributes with a preset behavioral feature library, which can achieve standardized, automated, objective and accurate behavior recognition, avoid human judgment errors, and improve recognition efficiency and consistency.

[0078] In one embodiment, see Figure 6 This is a schematic diagram of the process for generating a feeding score report provided in an embodiment of this application, such as... Figure 6 As shown, it includes: S501 scores various eating behaviors of dogs and cats during the feeding process to obtain the feeding score results of dogs and cats.

[0079] In this embodiment of the application, the system quantifies and scores all the identified dog and cat eating behaviors according to the preset scoring rules, and calculates an objective eating score to evaluate the eating enthusiasm and food palatability.

[0080] For example, the system scores various behaviors identified before, during, and after feeding based on pre-set feeding behavior scoring standards. These behaviors include whether the dog or cat eats immediately, the duration of feeding, the stability of the feeding posture, the number of times the dog or cat refuses to eat by raising its head, the frequency of sniffing, and whether it searches for leftover food after feeding. The system accumulates or weights the scores of each behavior to generate the overall score for the dog or cat's feeding. For example, 5 points are awarded for eating immediately, 4 points for eating steadily, 3 points for no refusal to eat, and 2 points are deducted for refusing to eat after sniffing. The system automatically calculates the total score, which serves as a quantitative basis for evaluating the palatability of pet food.

[0081] S502, determine the palatability grade of the food consumed by dogs and cats based on the scoring results.

[0082] In this embodiment of the application, the palatability of the food eaten by dogs and cats is determined by the feeding score automatically calculated by the system and compared with the preset level standard, and a clear level conclusion is given for the evaluation of pet food palatability testing and research and development.

[0083] For example, the system first summarizes the scores of various feeding behaviors to obtain the final feeding score, and then compares the score with the pre-set palatability level range. According to the score, the corresponding palatability level is automatically matched. The higher the level, the higher the pet's acceptance of the food, the higher the feeding enthusiasm, and the better the palatability. For example, a total score of 90 points or above is excellent, 70-89 points is good, 60-69 points is average, and below 60 points is poor. If a dog or cat scores 92 points after eating, the palatability level of the food is determined to be excellent.

[0084] S503 generates a feeding behavior score report based on the feeding score results and palatability level.

[0085] In this embodiment of the application, the system integrates the previously calculated feeding score with the determined palatability level to automatically generate a complete, viewable, and storable feeding behavior score report for intuitively presenting the monitoring and evaluation results.

[0086] For example, after completing the feeding behavior scoring and palatability level determination, the system automatically integrates data from the entire feeding process, scores for each behavior, total score, palatability level, etc., and summarizes and formats it according to a fixed report template to generate a complete feeding behavior scoring report containing basic information about the dog or cat, key data from the feeding video, scoring details, and palatability level conclusions. The report also supports automatic data storage and export. For example, the report will clearly record the total feeding time of the dog or cat, the score for each behavior (88 points), the palatability level (good), and provide corresponding evaluation conclusions and data basis, which can be directly used for pet food palatability testing and scientific research analysis.

[0087] The above method matches the fused comprehensive feature attributes with a preset behavioral feature library to determine the feeding behavior, thereby achieving standardized and automated identification of canine and cat feeding behavior and ensuring the objectivity and consistency of the behavior determination results.

[0088] This application provides a dog and cat feeding monitoring system, including a control device and a feeding box. A first camera is installed above the feeding area in the feeding box; a second camera is installed below the feeding base plate of the feeding area; wherein the feeding base plate is made of transparent glass. The control device is used to implement the dog and cat feeding monitoring method as described in any of the steps above; The first camera is used to collect initial video data of the dogs and cats during the feeding process; The second camera is used to collect secondary video data of dogs and cats during the feeding process.

[0089] This application provides a dog and cat feeding monitoring system, which mainly consists of a control device and a feeding box. A first camera is installed above the feeding area of ​​the feeding box, and a second camera is installed below the feeding box using a transparent glass feeding base. The first camera is responsible for collecting first video data reflecting the overall behavior of the dog or cat during feeding, while the second camera is responsible for collecting second video data reflecting the fine head movements of the dog or cat during feeding. The control device serves as the core processing unit, used to execute all the steps of the aforementioned dog and cat feeding monitoring methods, including video processing, feature extraction, behavior recognition, scoring, and palatability determination, thereby achieving fully automatic, all-round, and high-precision monitoring and analysis of dog and cat feeding behavior.

[0090] See Figure 7 This is a time-series flowchart of canine and cat feeding behavior provided in the embodiments of this application, such as... Figure 7 As shown, using a timeline as the core framework, the entire foraging process is divided into three stages: Feeding begins: At time 0:00, dogs and cats enter feeding mode, triggering the "start eating" behavior.

[0091] Foraging process (behavior alternation): 0:15: Dogs and cats engage in "continuous eating" behavior; 0:25: Briefly raises head, then resumes "feeding" at 0:30; 0:50: Looks up again, 0:55 resumes "continues feeding"; 1:15: "Licking lips" behavior appears; throughout the process, eating and short pauses alternate, fully restoring the real rhythm of feeding.

[0092] End of feeding: At 1:25, the feeding behavior ends and is marked as "feeding completed"; afterwards, the closing behaviors after feeding, such as "licking the bowl / foraging", can still be recorded.

[0093] Each node on the timeline corresponds to a specific foraging behavior and is marked with the precise time of occurrence, clearly demonstrating the dynamic changes of the behavior over time.

[0094] See Figure 8 This is a system flowchart of the dog and cat feeding monitoring method provided in the embodiments of this application, as follows: Figure 8 As shown, the overall structure is divided into three core functional areas: data acquisition, data analysis, and data reporting. Each area contains specific execution modules, and the modules are linked together by red arrows to form a complete data flow chain. Data collection phase: First, the feeding room is modified to adapt to the monitoring environment. At the same time, a dual-camera system is used to collect and retain high-quality video data of dogs and cats eating. The two types of work are combined to form a standardized "video sampling dataset". Data analysis phase: Based on the video sampling dataset, video tagging analysis is carried out to extract feeding behavior characteristics and construct a palatability assessment model, completing the transformation from raw video to quantitative palatability assessment; Data reporting phase: The output results of the palatability assessment model are summarized to generate a visual assessment report, completing the closed loop of the entire process from data collection to final conclusion output.

[0095] See Figure 9 This is a schematic diagram illustrating the classification of dog and cat eating behavior tags provided in the embodiments of this application, such as... Figure 9 As shown, a four-column structured design is used to standardize the labeling and storage of foraging behavior data: Tag Classification: Behaviors are divided into six categories: basic stage, pre-feeding behavior, core behavior during feeding, auxiliary behavior during feeding, post-feeding behavior, and feeding data, to achieve hierarchical management of behavior dimensions; Label name: The name of the specific behavior or data item, such as "feeding stage", "continuous feeding", "number of brief head lifts", "feeding duration", etc.; Field type: All fields are enumerated to ensure standardized and quantifiable data labeling; Tag Enumeration Values / Descriptions: Specify the optional values ​​or definitions for each tag, such as feeding stages including "before feeding, during feeding, and after feeding", and feeding duration in "seconds", etc.

[0096] See Figure 10 This is a schematic diagram illustrating the weighting of canine and feline feeding behavior scoring in an embodiment of this application. Figure 10 As shown, the core structure for quantifying and weighting feeding behavior is as follows: Tag name: Key behaviors and data items corresponding to each stage before / during / after feeding, such as "before feeding behavior", "core behaviors during feeding", "number of brief head lifts", etc. Enumerated values / range divisions: Clearly define the specific behavioral performance or numerical range for each tag. For example, "pre-feeding behavior" is divided into "eating immediately" and "eating after food sniffing". "Total feeding time" is divided into different time ranges for cats / dogs. Basic score: Each action is assigned a preset basic score. The score directly reflects the positive / negative impact of the behavior on palatability (e.g., "Eat immediately" is assigned 20 points, "Refuse to eat" is assigned 0 points). Weighting coefficients: Differentiated weights are set for different behavioral tags to reflect their importance to palatability assessment (e.g., "pre-feeding behavior" and "tail status" have a weight of 1.5, "core behaviors during feeding" have a weight of 1.2, and basic data items have a weight of 1.0).

[0097] See Figure 11This is a schematic diagram illustrating the classification of palatability levels for dogs and cats provided in the embodiments of this application, as shown below. Figure 11 As shown, the quantitative scoring results are transformed into an intuitive palatability rating system, with the core structure as follows: Palatability rating: As the main category, it governs the evaluation ratings corresponding to different score ranges; Score range: Clearly define the score range for each level, including 90-100 points, 75-89 points, 60-74 points, and <60 points; Grade abbreviation: The score range is simplified and identified using four grades: "Excellent", "Good", "Average", and "Poor". Level Description: Describes a pet's acceptance of food in plain language, visually reflecting the palatability level.

[0098] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] Figure 12 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. For example... Figure 12 As shown, the terminal device 12 of this embodiment includes: at least one processor 120 ( Figure 12 (Only one is shown in the image) a processor, a memory 121, and a computer program 122 stored in the memory 121 and executable on at least one processor 120. When the processor 120 executes the computer program 122, it implements the steps in any of the above embodiments of the canine and cat feeding monitoring methods.

[0101] The terminal device can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. This terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 12 This is merely an example of terminal device 12 and does not constitute a limitation on terminal device 12. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0102] The processor 120 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0103] In some embodiments, memory 121 may be an internal storage unit of terminal device 12, such as a hard disk or memory of terminal device 12. In other embodiments, memory 121 may be an external storage device of terminal device 12, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on terminal device 12. Furthermore, memory 121 may include both internal and external storage units of terminal device 12. Memory 121 is used to store operating system, application programs, boot loader, data, and other programs, such as program code of computer programs. Memory 121 may also be used to temporarily store data that has been output or will be output.

[0104] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described method embodiments.

[0105] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0106] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0107] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0108] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0109] In the embodiments provided in this application, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for monitoring canine and cat food intake, characterized in that, An application is made to a dog and cat feeding monitoring system, the system comprising a feeding box, a first camera positioned above the feeding area within the feeding box, and a second camera positioned below the feeding base of the feeding area; wherein the feeding base is made of transparent glass; the method includes: Acquire first video data of dogs and cats during the feeding process captured by the first camera; wherein, the first video data is used to characterize the overall behavior of the dogs and cats during the feeding process; Acquire second video data of dogs and cats during the feeding process captured by the second camera; wherein, the second video data is used to characterize the head movements of the dogs and cats during the feeding process; Feature extraction is performed on the first video data to obtain the key body part attributes corresponding to the dog and cat feeding process; Feature extraction is performed on the second video data to obtain the action state attributes corresponding to the dog and cat eating process; The feeding behavior of the dog or cat during the feeding process is determined based on the key body part attributes and action state attributes.

2. The method for monitoring canine and cat feeding as described in claim 1, characterized in that, The target video data is either the first video data or the second video data, and the target features are key part attributes or action state attributes. The steps for extracting features from target video data to obtain target features include: The target video data is segmented into frames to obtain multiple first images; Image target enhancement processing is performed on the first image in each frame to obtain the second image; Feature extraction is performed on each frame of the second image to obtain the target features corresponding to each frame of the second image; wherein, when the target video data is the first video data, the target feature is the key part attribute; when the target video data is the second video data, the target feature is the action state attribute.

3. The method for monitoring canine and cat feeding as described in claim 2, characterized in that, The step of determining the feeding behavior of the dog or cat during the feeding process based on the key body part attributes and action state attributes includes: By fusing the key part attributes and action state attributes at the same moment, the comprehensive feature attributes of the dog and cat at different moments are obtained. The feeding behavior of the dogs and cats during the feeding process is determined based on the comprehensive characteristic attributes.

4. The method for monitoring canine and cat feeding as described in claim 3, characterized in that, Determining the feeding behavior of dogs and cats during the feeding process based on the comprehensive feature attributes includes: The comprehensive feature attributes are matched with a preset behavioral feature library; If the behavioral feature store contains a first behavioral feature that matches the comprehensive feature attribute, then the first behavioral feature is determined as the current feeding behavior of the dog or cat.

5. The method for monitoring canine and cat feeding as described in claim 1, characterized in that, The method further includes: The various eating behaviors of the dogs and cats during the feeding process were scored to obtain the feeding score results of the dogs and cats; The palatability level of the food consumed by the dogs and cats is determined based on the scoring results. A feeding behavior score report is generated based on the feeding score results and the palatability level.

6. A dog and cat feeding monitoring system, characterized in that, The device includes a control unit and a feeding box. A first camera is installed above the feeding area in the feeding box, and a second camera is installed below the feeding base plate of the feeding area. The feeding base plate is made of transparent glass. The control device is used to implement the dog and cat feeding monitoring method as described in any one of claims 1-5 above; The first camera is used to collect first video data of dogs and cats during the feeding process; The second camera is used to collect second video data of dogs and cats during the feeding process.

7. The dog and cat feeding monitoring system as described in claim 6, characterized in that, Camera tracks are installed above and below the feeding area of ​​the feeding box; the camera tracks are used to adjust the shooting position according to the position of the dog or cat; and the second camera automatically adjusts the shooting angle according to the head movement of the dog or cat.

8. The dog and cat feeding monitoring system as described in claim 6, characterized in that, Supplemental lights are installed above and below the feeding area of ​​the feeding box, and these supplemental lights are used to adjust the light in the feeding box.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images