Pet car intelligent management system integrating positioning and health data collection

Abstract

The application belongs to the technical field of pet care, and provides a pet car intelligent management system fusing positioning and health data collection, the system comprising an image monitoring module, a target marking module, an image processing module, a feature analysis module and a danger early warning module; the system uses visual intelligent technology to accurately identify the current psychological state of the pet, monitors the physiological changes of the pet in real time through visual detection, and combines the control logic linkage of the pet car, so that irreversible psychological damage caused by long-time high-pressure state can be reduced, and the intelligence and safety of the pet car in the automatic tracking mode can be significantly improved; the system can realize emotion-friendly accurate control of the pet, and helps to improve the comfort and compliance of the pet in the interaction process.

Description

Intelligent management system for pet strollers that integrates location tracking and health data collection Technical Field

[0001] This invention belongs to the field of pet care technology, specifically involving an intelligent management system for pet vehicles that integrates positioning and health data collection. Background Technology

[0002] As people's understanding of pets deepens, their social status is constantly rising. Locating and tracking pets, and analyzing their condition, is crucial for ensuring their safety and health. The combination of industrial vision and visual intelligence technologies makes pet location more precise. Location tracking allows pet owners to know their pet's location in real time, preventing them from getting lost. Simultaneously, visual detection technology is used to monitor a pet's condition, helping to assess not only their physical health (such as activity levels and rest patterns) but also providing important clues about their emotional state, such as signs of anxiety or depression. This monitoring can guide pet owners to adjust their pet's daily activities and environment to promote their physical and mental well-being. Furthermore, continuous, comprehensive location tracking of pets is essential, as it not only ensures their safety, preventing them from getting lost or suffering accidental injury, but also helps pet owners monitor their pet's location and activity status in real time, enabling better management and care. Utilizing AI vision technology for precise analysis, pet strollers can adjust their tracking strategies promptly based on the pet's condition, ensuring that the pet receives appropriate attention and care. A Chinese invention patent, filed on March 20, 2024, with publication number CN118283533B, entitled "A Pet Tracking Method, Device, Equipment, and Medium Combining UWB Positioning and Vision," controls a pet cart to track a pet in real time based on the pet cart's location information, the pet's location information, the cart's motion parameters, and the pet's target detection results. This solves the problem of existing technologies being unable to accurately and continuously locate and track pets in all directions. This method is applicable both indoors and outdoors and can achieve real-time pet positioning and tracking. However, when a pet is in a new environment, it is easily stimulated and may experience stress. Visual measurement technology can further accurately assess the pet's behavior and physiological responses. Pets under stress are abnormally sensitive to changes in their surroundings. If the pet cart continues to track the pet in this state, it can easily cause continuous contraction of blood vessels in the pet's abdominal cavity, increased heart rate, and prolonged severe stress, which may even lead to sudden death in the pet. Summary of the Invention

[0003] The purpose of this invention is to propose an intelligent management system for pet vehicles that integrates positioning and health data collection, in order to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.

[0004] To achieve the above objectives, according to one aspect of the present invention, a pet vehicle intelligent management system integrating positioning and health data collection is provided, the pet vehicle intelligent management system integrating positioning and health data collection comprising the following modules:

[0005] The image monitoring module is used to monitor the pet's activity trajectory information in real time and acquire multiple real-time images of the pet;

[0006] The target labeling module is used to perform target detection and tracking on multiple real-time images to obtain a sequence of pet target images.

[0007] The image processing module is used to preprocess the pet target image sequence to obtain a preprocessed image;

[0008] The feature analysis module is used to obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information;

[0009] The danger warning module is used to make behavioral judgments about pets based on the danger coefficient of characteristic information and issue care reminders;

[0010] Furthermore, it also includes IoT terminal modules that monitor data by controlling sensors.

[0011] Furthermore, the IoT terminal module is connected to the image monitoring module, target marking module, image processing module, feature analysis module, and hazard warning module.

[0012] Furthermore, the data monitoring module includes a user data acquisition unit, a satellite positioning unit, and a monitoring unit;

[0013] The user data acquisition unit is used to acquire data information of pet owners;

[0014] The satellite positioning unit is used to obtain the pet's activity location information;

[0015] The monitoring unit is used to monitor pet activities in real time through pre-installed monitoring devices;

[0016] The output of the monitoring unit is connected to the input of the user data acquisition unit and the satellite positioning unit.

[0017] Furthermore, the IoT terminal module includes a status detection unit, a data transmission unit, and a network control unit;

[0018] The status detection unit is used to acquire the pet's position and speed information through sensors;

[0019] The data transmission unit is used to receive and transmit data according to the executed command;

[0020] The network control unit is used to ensure that data is transmitted while the network connection is normal.

[0021] The output of the control unit is connected to the input of the pressure detection unit and the data transmission unit.

[0022] A smart pet stroller management method integrating location tracking and health data collection, characterized by the following steps:

[0023] S1, monitors the pet's activity trajectory information in real time and acquires multiple real-time images of the pet;

[0024] S2, perform target detection and tracking on multiple real-time images to obtain a pet target image sequence;

[0025] S3, preprocess the pet target image sequence to obtain the preprocessed image;

[0026] S4, Obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information;

[0027] S5 makes behavioral judgments about pets based on the risk coefficient of the characteristic information and issues care reminders.

[0028] Furthermore, in S1, the specific method for real-time monitoring of the pet's activity trajectory information and obtaining multi-frame real-time images of the pet is as follows: real-time activity video of the pet is captured by a camera preset in the pet's activity scene, and the real-time activity video is decomposed into multi-frame real-time images. The multi-frame real-time images include the pet's location information, which includes the pet's location information and the pet vehicle's location information.

[0029] Furthermore, in S2, the specific method for obtaining the pet target image sequence by performing target detection and tracking on multiple frames of real-time images is as follows: a pre-trained pet target detection model is used, specifically a base pet detection model is adopted. The detection model extracts and classifies features from the images, outputs bounding boxes containing pets, types, and confidence scores, and uses a preset target tracking algorithm to track pet targets in each frame of real-time images, outputting the pet target image sequence and the pet target box position sequence as the target image sequence.

[0030] Furthermore, the pet detection model can be any one of YOLO8S (You Only Look Once), SSD (Single Shot MultiBox Detector), or Faster R-CNN.

[0031] Preferably, the pet detection model is YOLO8S.

[0032] The YoloV8s model is characterized by its ability to directly output the location and category information of a target in a single forward propagation without requiring multiple image scans. This results in high computational efficiency, enabling faster detection of pet targets. The detection results include the bounding box coordinates, category label, and confidence score of the pet target in the image. This pet target detection process allows the system to identify and locate pets in a scene in real time, providing pet owners with crucial information. This is a key function for pet care systems, providing users with a convenient and practical monitoring and tracking tool to ensure the health and safety of pets.

[0033] Furthermore, in S3, the specific method for preprocessing the pet target image sequence to obtain the preprocessed image is as follows: the target image sequence is processed by image filtering to obtain the preprocessed image, wherein the image filtering process includes Gaussian filtering to remove Gaussian noise, median filtering to remove salt and pepper noise, the image sequence after image filtering is processed by deduplication to remove duplicate images, and the preprocessed image is output.

[0034] Further, in S4, the pet's feature information in the preprocessed image is obtained and the risk coefficient of the feature information is calculated. The position information in the processed image is obtained as feature information. The pet's position information is recorded as P(i) and the pet vehicle's position information is recorded as Q(i). The straight-line distance between the pet's position information and the pet vehicle's position information is calculated as D(i). If D(i) exceeds the preset threshold Th1, the direction and distance that the vehicle needs to travel are calculated based on the pet vehicle's position information and the pet's position information, so as to determine the vehicle's motion parameters, such as speed, direction of travel and turning angle. In this way, the pet vehicle can automatically navigate and move along the optimal path to approach the pet's position.

[0035] Let ST be the time when the pet stroller starts moving and ED be the time when it stops moving. The pet's electrocardiogram (ECG) waveform between ST and ED is acquired using an ECG sensor worn on the pet's collar. The signal strength of the ECG waveform is denoted as E(i). The entire ECG waveform is processed using high-pass and low-pass filters to remove electromyographic interference and baseline drift. Wavelet transform is then used to remove subtle signal interference, ensuring a smooth, glitch-free waveform. The Pan-Tompkins algorithm is used to mark the R-waves, and the peaks of all R-waves are denoted as PK(j). The time interval between PK(j) and PK(j+1) is denoted as T(j), where j is the index of the time interval. All time intervals T(j) are iterated through according to the formula... Calculate the risk coefficient. M is the number of time intervals. If RK(j + 1) - RK(j) > RK(j) - RK(j - 1) and T(j) > T(j + 1), or RK(j + 1) - RK(j) < RK(j) - RK(j - 1) and T(j) < T(j + 1), record the time corresponding to PK(j) as the stress moment and control the pet car to stop moving.

[0036] Currently, many pet monitoring technologies are basically based on static behavior pattern recognition. By setting fixed parameter thresholds to judge the stress state, when the parameters never reach the thresholds, the judgment system often does not respond all the time, resulting in delays and misjudgments in obtaining the stress moment. However, the above method provides more sensitive and real-time stress detection by dynamically calculating the risk coefficient and the change trend of the electrocardiogram waveform, and can capture the subtle fluctuations of the heart rate change within a short time, so as to more accurately judge the stress moment of the pet.

[0037] When the pet is out for activities, if the pet car continuously tracks the movement of the pet, it may cause stress reactions in the pet. Due to the continuous tracking behavior of the pet car and being close to the pet's activity trajectory, the pet will feel a sense of oppression or threat, thus triggering anxiety or panic emotions. The change of this emotion will activate the sympathetic nervous system, which in turn causes the heart rate to accelerate. On the electrocardiogram waveform, it is usually manifested as a sudden shortening of the RR wave peak, indicating an abnormal increase in the heart rate, and the heart rate shows irregularity. The above method accurately controls the tracking behavior of the pet car by marking the time point when the stress reaction occurs, and stops tracking in time when the pet has a stress reaction, which can effectively relieve the pet's anxiety, help prevent the accumulation of psychological hazards, and reduce the long-term negative impact on the pet's physical and mental health. However, when the pet is in an excited state, a similar RR wave peak mutation phenomenon will also occur on the electrocardiogram waveform in a short time. The above method cannot effectively distinguish the anxiety and excitement states of the pet by observing the instantaneous heart rate change of the pet, resulting in the phenomenon that the pet car loses track and is prone to pet loss. To solve the above problems, the present invention proposes the following method to distinguish whether the pet is in an excited state or a stress state by calculating the heart rate change within a continuous time period, so as to accurately control the movement of the pet car:

[0038] Traverse all time intervals T(j), calculate the difference between T(j + 1) and T(j) as TO(j) in turn, and traverse all the differences TO(j) in turn. If TO(j + 1) > TO(j) and TO(j) < TO(j - 1), mark T(j) as the starting point of the fluctuation time. Retrieve the remaining R wave peaks backward along the electrocardiogram waveform from the R wave peak value corresponding to T(j), and calculate the difference between the remaining R wave peaks and the R wave peak corresponding to the time starting point as DIF(k), where k represents the serial number of the R wave peak retrieved backward along the electrocardiogram waveform from the R wave peak value corresponding to T(j). Through the formula Calculate the risk factor, where N is the number of R-wave peaks retrieved from the peak value of the R-wave corresponding to T(j) along the ECG waveform, DIF_max represents the maximum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j), and DIF_min represents the minimum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j). If RK(j) is less than zero, the pet is considered to be in an excited state, and the pet cart is controlled to continue tracking to prevent the pet from getting lost; otherwise, the pet is considered to be in a stressed state, and the pet cart is controlled to stop tracking to prevent the pet from being stressed.

[0039] The beneficial effects of the above steps are as follows: By analyzing the variation law of the RR interval (R-RInterval) in the electrocardiogram during the duration, it is possible to effectively distinguish between the excited state and the stressed state of the pet. In the excited state, the pet's autonomic nervous system mainly shows that the sympathetic nervous system is briefly active, the heart rate is increased, and the RR interval is shortened, but then it shows a stable trend. In the above formula... Partially to the left Therefore, RK(j) is less than zero in the excited state, while in the stressed state, due to the disordered regulation of the sympathetic-parasympathetic nervous system, the RR interval fluctuates greatly, and abnormal electrophysiological phenomena such as T wave inversion, ST segment elevation or depression appear in the electrocardiogram. (This is reflected in the above formula.) Some are significantly larger This is because the peak instability leads to pseudo-R waves (including abnormally high T waves, superimposed P waves, or strong electromyographic interference due to stress), causing the difference between adjacent R wave peaks to be much greater than the normal range. Therefore, RK(j) is greater than zero under stress. The above method, through the RR dynamic monitoring algorithm constructed over a duration, avoids the misidentification of the pet's state in instantaneous detection, reduces the risk of the pet getting lost, and also avoids the psychological problems caused to the pet due to continuous tracking of the pet cart when the pet is under stress.

[0040] Furthermore, in S5, the specific method for making behavioral judgments about pets and issuing care reminders based on the risk coefficient of the feature information is as follows: calculate the risk coefficient RK(j) based on the feature information. If RK(j) is less than zero, it is considered that the pet is in a state of stress. Control the pet cart to stop tracking to prevent the pet from being stressed, and issue a care alarm to remind the owner to take good care of the pet.

[0041] Beneficial Effects: This invention continuously collects the pet's electrocardiogram (ECG) data during pet tracking in a pet stroller. Based on a multi-dimensional filtering algorithm and a temporal fluctuation assessment model, it dynamically calculates the pet's risk coefficient using RR interval variation. This effectively suppresses local ECG abnormalities caused by short-term excitement, movement, or other non-continuous behaviors, preventing misjudgments of overall emotional state due to momentary emotional fluctuations. Through trend analysis of ECG waveforms and emotional state modeling, the system can accurately identify the pet's current psychological state (such as excitement or stress) and link it with the pet stroller's control logic. When the system identifies a high risk of stress or persistent emotional instability in the pet, it can proactively adjust or pause the tracking behavior, thereby avoiding continuous movement that induces or aggravates the pet's psychological burden and reducing irreversible psychological damage caused by prolonged high-pressure states. This significantly improves the intelligence and safety of the pet stroller in automatic tracking mode, achieving emotionally friendly and precise control for the pet, and helping to improve the pet's comfort and compliance during interaction. Attached Figure Description

[0042] Figure 1 shows a flowchart of the intelligent management system for pet vehicles that integrates positioning and health data collection. Detailed Implementation

[0043] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0044] Example 1:

[0045] Figure 1 shows a flowchart of the intelligent management system for pet vehicles that integrates positioning and health data collection.

[0046] Referring to Figure 1, this invention proposes an intelligent management system for pet vehicles that integrates positioning and health data collection. The system includes the following modules:

[0047] The image monitoring module is used to monitor the pet's activity trajectory information in real time and acquire multiple real-time images of the pet;

[0048] The target labeling module is used to perform target detection and tracking on multiple real-time images to obtain a sequence of pet target images.

[0049] The image processing module is used to preprocess the pet target image sequence to obtain a preprocessed image;

[0050] The feature analysis module is used to obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information;

[0051] The danger warning module is used to make behavioral judgments about pets based on the danger coefficient of characteristic information and issue care reminders;

[0052] Furthermore, the IoT terminal module monitors the pet's electrocardiogram waveform using the PetPace sensor.

[0053] Furthermore, the IoT terminal module monitors the pet's electrocardiogram waveform using a Tractive GPS 4 sensor.

[0054] Furthermore, the IoT terminal module is connected to the image monitoring module, target marking module, image processing module, feature analysis module, and hazard warning module.

[0055] Furthermore, the data monitoring module includes a user data acquisition unit, a satellite positioning unit, and a monitoring unit;

[0056] The user data acquisition unit is used to acquire data information of pet owners;

[0057] The satellite positioning unit is used to obtain the pet's activity location information;

[0058] The monitoring unit is used to monitor the pet's activities in real time via a monitoring device on a pre-worn Whistle GO Explore smart collar;

[0059] The output of the monitoring unit is connected to the input of the user data acquisition unit and the satellite positioning unit.

[0060] Furthermore, the IoT terminal module includes a status detection unit, a data transmission unit, and a network control unit;

[0061] The status detection unit is used to acquire the pet's position and speed information through sensors;

[0062] The data transmission unit is used to receive and transmit data according to the executed command;

[0063] The network control unit is used to ensure that data is transmitted while the network connection is normal.

[0064] The output of the control unit is connected to the input of the pressure detection unit and the data transmission unit.

[0065] A smart pet stroller management method integrating location tracking and health data collection, characterized by the following steps:

[0066] S1, monitors the pet's activity trajectory information in real time and acquires multiple real-time images of the pet;

[0067] S2, perform target detection and tracking on multiple real-time images to obtain a pet target image sequence;

[0068] S3, preprocess the pet target image sequence to obtain the preprocessed image;

[0069] S4, Obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information;

[0070] S5 makes behavioral judgments about pets based on the risk coefficient of the characteristic information and issues care reminders.

[0071] Furthermore, in S1, the specific method for real-time monitoring of the pet's activity trajectory information and obtaining multi-frame real-time images of the pet is as follows: real-time activity video of the pet is captured by a camera preset in the pet's activity scene, and the real-time activity video is decomposed into multi-frame real-time images. The multi-frame real-time images include the pet's location information, which includes the pet's location information and the pet vehicle's location information.

[0072] Furthermore, in S2, the specific method for obtaining the pet target image sequence by performing target detection and tracking on multiple frames of real-time images is as follows: a pre-trained pet target detection model is used, specifically a base pet detection model is adopted. The detection model extracts and classifies features from the images, outputs bounding boxes containing pets, types, and confidence scores, and uses a preset target tracking algorithm to track pet targets in each frame of real-time images, outputting the pet target image sequence and the pet target box position sequence as the target image sequence.

[0073] Preferably, the pet detection model is YOLO8S.

[0074] The YoloV8s model is characterized by its ability to directly output the location and category information of a target in a single forward propagation without requiring multiple image scans. This results in high computational efficiency, enabling faster detection of pet targets. The detection results include the bounding box coordinates, category label, and confidence score of the pet target in the image. This pet target detection process allows the system to identify and locate pets in a scene in real time, providing pet owners with crucial information. This is a key function for pet care systems, providing users with a convenient and practical monitoring and tracking tool to ensure the health and safety of pets.

[0075] Furthermore, in S3, the specific method for preprocessing the pet target image sequence to obtain the preprocessed image is as follows: the target image sequence is processed by image filtering to obtain the preprocessed image, wherein the image filtering process includes Gaussian filtering to remove Gaussian noise, median filtering to remove salt and pepper noise, the image sequence after image filtering is processed by deduplication to remove duplicate images, and the preprocessed image is output.

[0076] Further, in S4, obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information. Obtain the position information in the processed image as the feature information. Denote the pet position information as P(i), denote the pet car position information as Q(i), and calculate the straight-line distance between the pet position information and the pet car position information as D(i). If D(i) exceeds the preset threshold Th1, calculate the direction and distance that the car needs to travel based on the pet car position information and the pet position information, so as to determine the motion parameters of the car, such as speed, traveling direction, and steering angle. In this way, the pet car can automatically navigate and move along the optimal path to approach the position of the pet;

[0077] Denote the moment when the pet car starts to move as ST, and denote the moment when the pet car stops moving as ED. Obtain the electrocardiogram waveform of the pet from ST to ED through the electrocardiogram sensor worn on the pet collar. Denote the signal intensity of the electrocardiogram waveform as E(i). Traverse the entire electrocardiogram waveform, remove the electromyogram interference and baseline drift of the entire electrocardiogram waveform through high-pass and low-pass filters, and then remove the small signal interference through wavelet transform to ensure that the processed electrocardiogram waveform is smooth and free of burrs. Use the Pan-Tompkins algorithm to mark the R wave. Denote the peaks of all R waves as PK(j), and denote the time interval between PK(j) and PK(j + 1) as T(j). j is the serial number of the time interval. Traverse all time intervals T(j), and according to the formula Calculate the risk coefficient. M is the number of time intervals. If RK(j + 1) - RK(j) > RK(j) - RK(j - 1) and T(j) > T(j + 1), or RK(j + 1) - RK(j) < RK(j) - RK(j - 1) and T(j) < T(j + 1), record the time corresponding to PK(j) as the stress moment, and control the pet car to stop moving;

[0078] Further, in S5, the specific method for making a behavior judgment on the pet according to the risk coefficient of the feature information and issuing a care reminder is as follows: According to the calculated risk coefficient RK(j) of the feature information, if RK(j) is less than zero, it is considered that the pet is in a stress state, control the pet car to stop tracking to prevent the pet from being stressed, and issue a care alarm to remind the owner to take good care of the pet.

[0079] Embodiment 2

[0080] In this Embodiment 2, the method of obtaining the feature information of the pet in the preprocessed image and calculating the risk coefficient of the feature information in Embodiment 1 is replaced. Specifically:

[0081] Traverse all time intervals T(j), and calculate the difference between T(j+1) and T(j) as TO(j) in sequence. Traverse all the differences TO(j) in sequence. If TO(j+1)>TO(j) and TO(j)<TO(j-1), then mark T(j) as the starting point of the fluctuation time. Retrieve the remaining R-wave peaks backward along the electrocardiogram waveform from the R-wave peak corresponding to T(j), and calculate the difference between the remaining R-wave peaks and the R-wave peak corresponding to the starting point of time as DIF(k), where k represents the serial number of the R-wave peak retrieved backward along the electrocardiogram waveform from the R-wave peak corresponding to T(j). Through the formula Calculate the risk coefficient, where N is the number of R-wave peaks retrieved backward along the electrocardiogram waveform from the R-wave peak corresponding to T(j), DIF_max represents the maximum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j), and DIF_min represents the minimum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j). If RK(j) is less than zero, it is considered that the current pet is in an excited state, and the pet car is controlled to continue tracking to prevent the pet from getting lost. Otherwise, it is considered that the pet is in a stress state, and the pet car is controlled to stop tracking to prevent the pet from being stressed.

[0082] The intelligent management system of the pet car integrating positioning and health data collection can run on computing devices such as desktop mini-computers, notebooks, palm computers, and cloud servers. The intelligent management system of the pet car integrating positioning and health data collection, the operable system may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above examples are only examples of the intelligent management system of the pet car integrating positioning and health data collection, and do not constitute a limitation on the intelligent management system of the pet car integrating positioning and health data collection. It may include more or fewer components than the examples, or combine some components, or different components. For example, the intelligent management system of the pet car integrating positioning and health data collection may also include input / output devices, network access devices, buses, etc.

[0083] The processor can be a Central Processing Unit (CPU), or 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. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the pet vehicle intelligent management system that integrates positioning and health data acquisition, connecting various parts of the system via various interfaces and lines.

[0084] The memory can be used to store the computer programs and / or modules. The processor, by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, realizes various functions of the pet vehicle intelligent management system that integrates positioning and health data collection. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0085] Although the invention has been described in considerable detail and particularly with regard to several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.

Claims

1. A pet stroller intelligent management system integrating location and health data collection, characterized in that: The system includes the following modules: an image monitoring module, used to monitor the pet's activity trajectory information in real time and acquire multiple real-time images of the pet; The target labeling module is used to perform target detection and tracking on multiple real-time images to obtain a sequence of pet target images. The image processing module is used to preprocess the pet target image sequence to obtain a preprocessed image; The feature analysis module is used to acquire the pet's feature information in the preprocessed image and calculate the risk coefficient of the feature information. The method for acquiring the pet's feature information in the preprocessed image and calculating the risk coefficient of the feature information is as follows: the position information in the processed image is acquired as the feature information, the pet's position information is denoted as P(i), the pet cart's position information is denoted as Q(i), and the straight-line distance between the pet's position information and the pet cart's position information is calculated as D(i). If D(i) exceeds a preset threshold Th1, based on the pet cart's position information and the pet's position information, the direction and distance that the cart needs to travel are calculated in order to determine the cart's motion parameters, such as speed, direction of travel, and turning angle. In this way, the pet cart can navigate automatically. The system moves along the optimal path to approach the pet's location. The time when the pet cart starts moving is denoted as ST, and the time when it stops moving is denoted as ED. The ECG waveform of the pet is acquired from ST to ED using an ECG sensor worn on the pet's collar, and the signal strength of the ECG waveform is denoted as E(i). The entire ECG waveform is iterated through, and high-pass and low-pass filters are used to remove electromyographic interference and baseline drift. Wavelet transform is then used to remove subtle signal interference, ensuring a smooth and glitch-free processed ECG waveform. The Pan-Tompkins algorithm is used to mark the R-waves, and all R-wave peaks are denoted as PK(j). The time interval between PK(j) and PK(j+1) is denoted as T(j). All time intervals T(j) are iterated through, and the results are processed according to the formula... Calculate the risk coefficient, where RK represents the risk coefficient, M is the number of time intervals. If RK(j + 1) - RK(j) > RK(j) - RK(j - 1) and T(j) > T(j + 1), or if RK(j + 1) - RK(j) < RK(j) - RK(j - 1) and T(j) < T(j + 1), record the time corresponding to PK(j) as the stress moment and control the pet car to stop moving; a danger warning module for making a behavioral judgment on the pet based on the risk coefficient of the feature information and issuing a care reminder; the Internet of Things terminal module monitors data by controlling sensors; the Internet of Things terminal module is connected to the image monitoring module, the target marking module, the image processing module, the feature analysis module, and the danger warning module.

2. The intelligent pet stroller management system integrating positioning and health data collection according to claim 1, characterized in that, The image monitoring module includes a user data acquisition unit, a satellite positioning unit, and a monitoring unit; the user data acquisition unit is used to acquire data information of the pet owner; the satellite positioning unit is used to acquire the pet's activity location information; the monitoring unit is used to monitor the pet's activities in real time through a pre-installed monitoring device; the output end of the monitoring unit is connected to the input ends of the user data acquisition unit and the satellite positioning unit.

3. The intelligent pet stroller management system integrating positioning and health data collection according to claim 1, characterized in that, The IoT terminal module includes a status detection unit, a data transmission unit, and a network control unit. The status detection unit is used to acquire the pet's location and speed information through sensors. The data transmission unit is used to receive and transmit data according to executed commands. The network control unit is used to ensure that data is transmitted under normal network connectivity. The output of the control unit is connected to the input of the pressure detection unit and the data transmission unit.

4. A method for intelligent management of pet vehicles integrating location and health data collection, applied to the intelligent management system for pet vehicles integrating location and health data collection as described in any one of claims 1-3, characterized in that, Includes the following steps: S1. Monitor the activity trajectory information of the pet in real time and obtain multiple frames of real-time images of the pet; S2. Perform object detection and tracking on the multiple frames of real-time images to obtain a pet target image sequence; S3. Preprocess the pet target image sequence to obtain a preprocessed image; S4. Obtain the feature information of the pet in the preprocessed image and calculate the risk coefficient of the feature information; S5. Make a behavior judgment on the pet according to the risk coefficient of the feature information and issue a care reminder.

5. The intelligent management method for pet vehicles integrating positioning and health data collection according to claim 4, characterized in that, In S1, the method for monitoring the activity trajectory information of the pet in real time and obtaining multiple frames of real-time images of the pet is as follows: Shoot the real-time activity video of the pet through a camera preset in the pet activity scene, and decompose the real-time activity video into multiple frames of real-time images. The multiple frames of real-time images include the position information of the pet, and the position information includes the pet position information and the pet car position information.

6. The intelligent management method for pet vehicles integrating positioning and health data collection according to claim 5, characterized in that, In S2, the method for performing object detection and tracking on the multiple frames of real-time images to obtain a pet target image sequence is as follows: Use a pre-trained pet object detection model, specifically a pet detection model based on a neural network. The detection model extracts features and classifies the image, and outputs the bounding box, category and confidence score containing the pet. Use a preset object tracking algorithm to track the pet target in each frame of real-time image, and output the pet target image sequence and the pet target box position sequence as the target image sequence.

7. The intelligent management method for pet vehicles integrating positioning and health data collection according to claim 6, characterized in that, In S3, the method for preprocessing the pet target image sequence to obtain a preprocessed image is as follows: Obtain the preprocessed image after the target image sequence is subjected to image filtering processing. The image filtering processing includes Gaussian filtering to remove Gaussian noise and median filtering to remove salt-and-pepper noise. The image sequence after image filtering processing is subjected to duplicate removal processing to remove duplicate images, and the preprocessed image is output.

8. The intelligent pet stroller management method integrating positioning and health data collection according to claim 4, characterized in that, Replace the method for obtaining the feature information of the pet in the preprocessed image and calculating the risk coefficient of the feature information with: Traverse all time intervals T(j), and calculate the difference between T(j + 1) and T(j) as TO(j) in turn. Traverse all the differences TO(j) in turn. If TO(j + 1)>TO(j) and TO(j)<TO(j - 1), then mark T(j) as the starting point of the fluctuation time. Retrieve the remaining R wave peaks backward along the electrocardiogram waveform from the R wave peak corresponding to T(j), and calculate the difference between the remaining R wave peaks and the R wave peak corresponding to the time starting point as DIF(k), where k represents the serial number of the R wave peak retrieved backward along the electrocardiogram waveform from the R wave peak corresponding to T(j). Through the formula Calculate the risk factor, where RK represents the risk factor, N is the number of R-wave peaks retrieved from the peak value of the R-wave corresponding to T(j) along the ECG waveform, DIF_max represents the maximum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j), and DIF_min represents the minimum difference between the retrieved R-wave peak and the R-wave peak corresponding to T(j). If RK(j) is less than zero, the pet is considered to be in an excited state, and the pet cart is controlled to continue tracking to prevent the pet from getting lost; otherwise, the pet is considered to be in a stressed state, and the pet cart is controlled to stop tracking to prevent the pet from being stressed.

9. The intelligent management method for pet vehicles integrating positioning and health data collection according to claim 8, characterized in that, In S5, the method for making a behavior judgment on the pet according to the risk coefficient of the feature information and issuing a care reminder is as follows: Calculate the risk coefficient RK(j) according to the feature information. If RK(j) is less than zero, it is considered that the pet is in a stress state, control the pet car to stop tracking to prevent the pet from being stressed, and issue a care alarm to remind the owner to take good care of the pet.

Images