Pet movement track monitoring system

Abstract

The invention relates to the technical field of pet activity monitoring, in particular to a pet activity track monitoring system, which comprises a city data acquisition module for acquiring regional map information and road monitoring information of residential areas in a city; the map processing module is used for constructing a regional grayscale image and analyzing the monitoring coverage area; the pet data acquisition module is used for acquiring activity information of a pet in real time; the video analysis module is used for extracting pet areas according to the road monitoring information and marking user pet areas in the pet areas; the area analysis module is used for analyzing the video driving path according to the pet area; the path analysis module is used for analyzing and adjusting the pet position state and the pet movement track; and the track output module is used for outputting the pet position state and the pet movement track to the user. According to the invention, the movement track of the pet can be accurately monitored.

Description

Technical Field

[0001] The present invention relates to the technical field of pet activity monitoring, and in particular to a pet activity track monitoring system. Background Art

[0002] With the continuous expansion of the pet market, the application of smart wearable devices in the pet field is gradually increasing. By integrating GPS modules and Bluetooth communication technology, the pet positioning system can monitor and transmit the location information of pets in real time, providing owners with accurate activity tracks. This not only improves the convenience of pet management, but also enhances the safety of pets. In addition, cloud-based data processing and analysis technology makes the monitoring of pet activity tracks more intelligent and accurate.

[0003] Chinese Patent Publication No.: CN110751022A discloses a method for monitoring the activity trajectory of urban pets based on image recognition and related equipment, including: obtaining pet images collected by a preset image acquisition device; identifying the pet category in the pet image; when the pet category is the target category, identifying the pet posture in the pet image; extracting the feature vector in the pet image according to the feature extraction algorithm corresponding to the pet posture; using the optical flow algorithm to correct the feature vector to obtain the target feature vector; comparing the target feature vector with the feature vector in the preset database for consistency; when the comparison is consistent, associating the identification information of the stored pet image with the collection information of the preset image acquisition device; obtaining the collection information corresponding to the pet image with the same identification information; and determining the activity trajectory of the pet according to the collection information. This invention realizes the recognition of the pet posture in the image acquisition to determine the activity trajectory of the pet, but does not realize the comprehensive analysis of the pet activity data, positioning data and monitoring data, and has the problems of low efficiency in analyzing the pet activity data and inaccurate monitoring of the pet activity trajectory. Summary of the invention

[0004] The object of the present invention is to provide a pet activity track monitoring system to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A pet activity trajectory monitoring system, comprising: The city data acquisition module is used to obtain regional map information and road monitoring information of residential areas in the city; A map processing module is used to construct a regional grayscale image according to the regional map information, and is also used to mark the pixel points of the regional grayscale image according to the road monitoring information to obtain monitoring pixel points, and analyze the monitoring coverage area according to the monitoring pixel points, the regional map information and the road monitoring information; A pet data acquisition module is used to obtain pet activity information in real time; A video analysis module, used to extract the pet area according to the road monitoring information, and also used to mark the user's pet area in the pet area; The regional analysis module is used to analyze the video driving path according to the pet area; A path analysis module, which is used to analyze the pet's position status and pet's activity trajectory based on the regional grayscale image and the pet's activity information, and is also used to adjust the analysis process of the pet's activity trajectory based on the monitoring coverage area, the pet area, the user's pet area and the video driving path; The track output module is used to output the pet's location status and pet's activity track to the user.

[0006] Furthermore, the map processing module is provided with an image construction unit, which is used to create an image with the same resolution as the regional map as the regional grayscale image, so that the regional grayscale image corresponds to the pixels in the regional map one by one, and the grayscale value of each pixel in the regional grayscale image is set, and the grayscale value of the pixel in the regional grayscale image corresponding to the white pixel in the regional image is set to A1, the grayscale value of the pixel in the regional grayscale image corresponding to the green pixel in the regional image is set to A2, the grayscale value of the pixel in the regional grayscale image corresponding to the gray pixel in the regional image is set to A3, and the grayscale value of the pixel in the regional grayscale image corresponding to the blue pixel in the regional image is set to A4, wherein A1 represents the first grayscale parameter, A2 represents the second grayscale parameter, A3 represents the third grayscale parameter, and A4 represents the fourth grayscale parameter.

[0007] Furthermore, the map processing module is also provided with a monitoring analysis unit, which is used to analyze the first monitoring pixel point according to the monitoring pixel point, map scale, preset monitoring parameters and shooting direction. The monitoring analysis unit extracts the pixel point that is α pixels away from the current analysis monitoring pixel point in the shooting direction of the current analysis monitoring pixel point in the regional grayscale image as the end pixel point, and draws a line connecting the current analysis monitoring pixel point and the end pixel point, and uses the pixel point on the line as the first monitoring pixel point.

[0008] Furthermore, the monitoring analysis unit analyzes the range distance parameter according to the first monitoring pixel point and the preset monitoring parameter, sets the range distance parameter to P, and sets , and extract the pixel points satisfying P≤M2 / η in the regional grayscale image as the second monitoring pixel points, where P represents the range distance parameter, (x, y) represents the coordinates of each pixel point in the regional grayscale image, (x1, y1) represents the first monitoring pixel point, and M2 represents the second preset monitoring parameter.

[0009] Furthermore, the monitoring and analysis unit analyzes the monitoring coverage area according to the first monitoring pixel and the second monitoring pixel. If L(x1, y1)<A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the covering pixel. If L(x1, y1)≥A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the masking pixel. If L(x2, y2)<A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the covering pixel. If L(x2, y2)≥A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the masking pixel. The monitoring and analysis unit uses the area formed by the covering pixels as the monitoring coverage area, wherein L(x1, y1) represents the grayscale value of the first monitoring pixel in the regional grayscale image, and L(x2, y2) represents the grayscale value of the second monitoring pixel in the regional grayscale image.

[0010] Further, the video analysis module is provided with a region extraction unit, which is used to input the road monitoring video into the target detection model to extract the pet region in the road monitoring video; The video analysis module is also provided with an extraction optimization unit, which is used to input the pet image as a user pet data set into the target detection model for model training, optimize the extraction of the pet area, and when the ROL area of ​​the extracted pet area comes from the user pet data set, mark the pet area as the user pet area.

[0011] Furthermore, the regional analysis module analyzes the pet monitoring position according to the pet area, sets the pet monitoring position to S(t)=(u(t),v(t)), sets u(t)=∑x3(t) / N3(t), v(t)=∑y3(t) / N3(t), where S(t) represents the pet monitoring position, t represents the time number, u(t) represents the horizontal coordinate mean parameter, v(t) represents the vertical coordinate mean parameter, x3(t) represents the horizontal coordinate of the pixel point in the pet area, y3(t) represents the vertical coordinate of the pixel point in the pet area, N3(t) represents the number of pixels in the pet area, and the regional analysis module uses the set of pet monitoring positions as the video driving path.

[0012] Furthermore, the path analysis module is provided with a path analysis unit, which is used to analyze the pet activity trajectory according to the regional grayscale image and the pet position. If there is any k∈N and k∈[0,300], satisfying L(X(tk),Y(tk))≥A4, the path analysis unit determines that the pet position status is indoor activity and does not analyze the pet activity trajectory. Otherwise, the path analysis unit determines that the pet position status is outdoor activity, and takes the pet position satisfying L(X(tk),Y(tk))<A4 as the activity coordinate point, and takes the set of activity coordinate points as the pet activity trajectory, wherein k represents the time range parameter, L(X(t),Y(t)) represents the grayscale value of the pixel point corresponding to the pet position in the regional grayscale image, and (X(t),Y(t)) represents the coordinates of the pixel point corresponding to the pet position in the regional grayscale image.

[0013] Furthermore, the path analysis module is also provided with a position analysis unit, which is used to adjust the analysis process of the pet's activity trajectory according to the monitoring coverage area, the pet's position and the video driving path, wherein: When (X(t), Y(t))∈U, if the pet area is marked as the user pet area, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)); if the pet area is not marked as the user pet area and |D1(t)-X(t)|+|D2(t)-Y(t)|≤β / η, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)); Otherwise, the position analysis unit does not adjust the active coordinate point.

[0014] Furthermore, the path analysis module is also provided with a pet analysis unit, which is used to optimize the adjustment process of the pet's activity trajectory according to the pet's position and the pet's heart rate. If H(t)>h, the pet analysis unit determines that the pet's heart rate does not meet the threshold, and optimizes the adjustment process of the activity coordinate point. The optimized activity coordinate point is (X2(t), Y2(t)); if H(t)≤h, the pet analysis unit determines that the pet's heart rate meets the threshold, and does not optimize the adjustment process of the activity coordinate point; wherein H(t) represents the pet's heart rate, and h represents the heart rate threshold.

[0015] The beneficial effects of the present invention are as follows: through the acquisition of regional map information, road monitoring information and pet activity information by the city acquisition module and the pet data acquisition module, and the comprehensive analysis of the acquired data by other modules, the pet activity data, monitoring data and positioning data are integrated to determine the pet activity trajectory, ensure the accuracy of the pet positioning data, thereby improving the system's analysis efficiency of the pet activity data and improving the accuracy of the pet activity trajectory monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 Schematic diagram of the structure of the pet activity trajectory monitoring system of this embodiment.

[0018] Figure 2 Schematic diagram of the structure of the map processing module of this embodiment.

[0019] Figure 3 Schematic diagram of the structure of the video analysis module of this embodiment.

[0020] Figure 4 Schematic diagram of the structure of the path analysis module of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, the pet activity track monitoring system of this embodiment includes: A city data acquisition module, used to obtain regional map information and road monitoring information of residential areas in the city, wherein the regional map information includes a regional map, a map scale and a map resolution, wherein the map scale is the ratio of the actual area of ​​the area corresponding to the regional map to the map resolution, wherein the map resolution is the product of the number of horizontal and vertical pixels in the regional map, wherein the regional map is a city plan that has been specially colored, wherein the white areas in the regional map represent roads, the green areas represent green areas, the blue areas represent rivers, and the gray areas represent buildings, wherein the buildings include residential buildings, shopping malls and other buildings, wherein the regional map information can be obtained through map software, or can be obtained by manually marking a satellite remote sensing map of the city, wherein the road monitoring information includes a road monitoring video, a road monitoring position and a shooting direction angle, wherein the road monitoring position is the position of a camera for shooting a road monitoring video on the regional map, wherein the shooting direction angle is the angle between the camera shooting direction and the clockwise direction of due north, and wherein the road monitoring video is a video shot by a camera installed in a residential area for shooting and monitoring roads; The map processing module is used to construct a regional grayscale image based on the regional map information, and is also used to mark the pixel points of the regional grayscale image according to the road monitoring information to obtain the monitoring pixel points, and analyze the monitoring coverage area according to the monitoring pixel points, the regional map information and the road monitoring information. The map processing module is connected to the map data acquisition module.

[0024] Specifically, when analyzing the regional map, the map processing module described in this embodiment takes the pixel point in the lower left corner of the regional map as the coordinate origin, the edge passing through the coordinate origin in the east direction as the x-axis, and the edge passing through the coordinate origin in the north direction as the y-axis. The unit length is 1 pixel, and a plane rectangular coordinate system is established, using coordinate points to represent the position of each pixel point in the regional map.

[0025] Specifically, this embodiment is applied to the cloud of user smart devices to monitor the movement trajectory data of medium-sized dogs raised by users in urban residential areas, ensuring that users can monitor the activities of their pets in real time.

[0026] See also Figure 2 As shown, the map processing module includes: The image construction unit is used to construct a regional grayscale image, and use the regional grayscale image to represent the building conditions of different areas in the map, so that the regional map is represented in grayscale, ensuring the accuracy of the system's analysis of each area in the regional map.

[0027] Specifically, the image construction unit in this embodiment creates an image with the same resolution as the regional map as the regional grayscale image, so that the regional grayscale image corresponds to the pixels in the regional map one by one, and sets the grayscale value of each pixel in the regional grayscale image, and sets the grayscale value of the pixel of the regional grayscale image corresponding to the white pixel in the regional image to A1, sets the grayscale value of the pixel of the regional grayscale image corresponding to the green pixel in the regional image to A2, sets the grayscale value of the pixel of the regional grayscale image corresponding to the gray pixel in the regional image to A3, and sets the grayscale value of the pixel of the regional grayscale image corresponding to the blue pixel in the regional image to A4, wherein A1 represents the first grayscale parameter, 0≤A1≤32, and A2 represents the second grayscale parameter. A1 represents a grayscale parameter, 64≤A2≤96, A3 represents a third grayscale parameter, 128≤A3≤160, A4 represents a fourth grayscale parameter, 192≤A4≤224; the image construction unit creates an image identical to the regional map as a regional grayscale image to ensure that the regional grayscale image constructed and analyzed by the system is consistent with the data in the regional map, so that the system's analysis of the constructed data corresponds one-to-one with the analysis of the map data, thereby improving the system's analysis efficiency of the pet's activity data and improving the accuracy of pet activity trajectory monitoring; it can be understood that in this embodiment, the value of the grayscale parameter is not specifically limited, and the technicians in this field can set it freely, as long as the construction of the regional grayscale image is satisfied. The optimal values ​​of the grayscale parameters are: A1=0, A2=64, A3=128, A4=192.

[0028] Please continue reading Figure 2 As shown, the map processing module also includes: A monitoring marking unit, used to mark the regional grayscale image according to the road monitoring information, so as to mark the location of the road monitoring camera in the regional grayscale image, so as to facilitate the analysis of the monitored area. The monitoring marking unit is connected to the image construction unit; The monitoring marking unit marks the pixel points corresponding to the road monitoring positions in the regional grayscale image as monitoring pixel points.

[0029] Please continue reading Figure 2 As shown, the map processing module also includes: The monitoring analysis unit is used to analyze the monitoring coverage area, and the monitoring coverage area is used to represent the area range that can be photographed by the road monitoring camera, so as to improve the accuracy of the system's analysis of monitoring video data. The monitoring analysis unit is connected to the monitoring marking unit.

[0030] Specifically, the monitoring and analysis unit in this embodiment analyzes the first monitoring pixel point according to the monitoring pixel point, the map scale, the preset monitoring parameter and the shooting direction. The monitoring and analysis unit extracts the pixel point α pixels away from the current analysis monitoring pixel point in the shooting direction of the current analysis monitoring pixel point in the regional grayscale image as the end pixel point, and draws a line connecting the current analysis monitoring pixel point and the end pixel point, and takes the pixel point on the line as the first monitoring pixel point, wherein α represents the shooting distance parameter, and α=M1 / η is set, M1 represents the first preset monitoring parameter, 50≤M1≤150, and η represents the map scale. It can be understood that in this embodiment, the value of the first preset monitoring parameter is not specifically limited, and those skilled in the art can freely set it, as long as it satisfies the analysis of the first monitoring pixel point. The optimal value of the first preset monitoring parameter is: M1=60.

[0031] Specifically, the monitoring analysis unit in this embodiment analyzes the range distance parameter according to the first monitoring pixel point and the preset monitoring parameter, sets the range distance parameter to P, and sets , and extract the pixel points satisfying P≤M2 / η in the regional grayscale image as the second monitoring pixel points, where P represents the range distance parameter, (x, y) represents the coordinates of each pixel point in the regional grayscale image, (x1, y1) represents the first monitoring pixel point, M2 represents the second preset monitoring parameter, and 5≤M2≤10. It can be understood that the value of the second preset monitoring parameter is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the extraction of the second monitoring pixel point is satisfied. The optimal value of the second preset monitoring parameter is: M2=6.

[0032] Specifically, the monitoring and analysis unit in this embodiment analyzes the monitoring coverage area according to the first monitoring pixel and the second monitoring pixel. If L(x1, y1) < A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the covering pixel. If L(x1, y1) ≥ A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the masking pixel. If L(x2, y2) < A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the covering pixel. If L(x2, y2) ≥ A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the masking pixel. The monitoring and analysis unit uses the area formed by the covering pixels as the monitoring coverage area, wherein L(x1, y1) represents the grayscale value of the first monitoring pixel in the regional grayscale image, and L(x2, y2) represents the grayscale value of the second monitoring pixel in the regional grayscale image. The monitoring analysis unit analyzes the monitoring pixels and the shooting direction to extract the pixels in the monitoring shooting direction in the regional grayscale image as the main path pixels of the monitoring shooting area, calculates the distance between each pixel and the pixel, and determines the pixel that meets the monitoring horizontal shooting angle. The grayscale value of the extracted and determined pixel is compared with the set pixel grayscale value in the constructed regional grayscale image, and the pixel that meets the threshold is extracted as the monitoring coverage area, thereby improving the system's analysis efficiency of pet activity data and improving the accuracy of pet activity trajectory monitoring.

[0033] Please continue reading Figure 1 As shown, the pet activity trajectory monitoring system also includes: A pet data acquisition module is used to acquire the activity information of the pet in real time, and the activity information includes the pet position, pet heart rate and pet image. The pet position is the position of the pet on the regional map. The pet position and pet heart rate are acquired by uploading the smart collar worn by the pet. The pet image is an image of the pet taken and uploaded by the user. In this embodiment, no specific restrictions are made on the requirements of the pet image. The user can upload it according to the actual situation. The pet image should at least include the front and side standing photos and the front and side crawling photos of the pet. The number of pet images uploaded by the user is related to the accuracy of the system's monitoring and analysis of the pet's activity trajectory. Increasing the number of uploaded pet images can improve the accuracy of the system's monitoring and analysis of the pet's activity trajectory. The video analysis module is used to extract the pet area according to the road monitoring information and to mark the user pet area in the pet area. The video analysis module is connected with the pet data acquisition module and the map processing module.

[0034] Specifically, when the video analysis module described in this embodiment analyzes the road surveillance video, the pixel point in the lower left corner of each frame image in the road surveillance video is used as the coordinate origin, and the two sides adjacent to the coordinate origin are used as the x-axis and y-axis respectively. The x-axis increases from left to right, and the y-axis increases from bottom to top. The unit length is 1 pixel. A plane rectangular coordinate system is established, and the coordinate points are used to represent the position of each pixel point in the road surveillance video.

[0035] See also Figure 3 As shown, the video analysis module includes: The area extraction unit is used to extract the pet area in the road monitoring video to realize the target positioning in the road monitoring video, and the area of ​​the target area that matches the pet training set is used as the pet area to improve the accuracy of pet positioning in the video.

[0036] Specifically, the region extraction unit in this embodiment inputs the road surveillance video into the target detection model based on YOLOv8 to extract the pet region in the road surveillance video; The region extraction unit extracts one frame of monitoring image per second from the road monitoring video, and uses the pet region in the currently extracted monitoring image as the pet region in the monitoring video of this second; The YOLOv8-based target detection model is an open source target detection algorithm that can be run using Python. The Oxford-IIIT Pet pet dataset is used to train the YOLOv8-based target detection model to extract the pet area in the road surveillance video.

[0037] Please continue reading Figure 3 As shown, the video analysis module also includes: The extraction optimization unit is used to mark the pet area according to the pet information and the road monitoring video, and the extraction optimization unit is connected to the area extraction unit.

[0038] Specifically, the extraction optimization unit in this embodiment inputs the pet image as the user pet data set into the target detection model based on YOLOv8 for model training, optimizes the extraction of the pet area, and marks the pet area as the user pet area when the ROL area of ​​the extracted pet area comes from the user pet data set. Through the analysis of the pet image by the extraction optimization unit, the user pet area in the pet area is marked, and the recognition and extraction of the user pet in the road monitoring video is realized, thereby improving the system's analysis efficiency of the pet activity data and improving the accuracy of the pet activity trajectory monitoring.

[0039] Please continue reading Figure 1 As shown, the pet activity trajectory monitoring system also includes: The regional analysis module is used to analyze the video driving path according to the pet area, and use the video driving path to represent the driving path of the pet in the road monitoring video, thereby increasing the accuracy of the system's analysis of the road monitoring video. The regional analysis module is connected to the video analysis module.

[0040] Specifically, the regional analysis module in this embodiment analyzes the pet monitoring position according to the pet area, sets the pet monitoring position to S(t)=(u(t),v(t)), sets u(t)=∑x3(t) / N3(t), v(t)=∑y3(t) / N3(t), where S(t) represents the pet monitoring position, t represents the time number, u(t) represents the horizontal coordinate mean parameter, v(t) represents the vertical coordinate mean parameter, x3(t) represents the horizontal coordinate of the pixel point in the pet area, y3(t) represents the vertical coordinate of the pixel point in the pet area, N3(t) represents the number of pixels in the pet area, and the regional analysis module uses the set of pet monitoring positions as the video driving path. The time number is a number indicating the second in which the pet area is located in the road monitoring video, and is used to distinguish the data analyzed every second in the road monitoring video; the pet area is analyzed by the regional analysis module to analyze the pet monitoring position, and the pet monitoring position is used to represent the position of the pixel point of the pet in the road monitoring video. The pet monitoring positions in each second are arranged in sequence to obtain the video driving path, thereby improving the system's analysis efficiency of pet activity data and improving the accuracy of pet activity trajectory monitoring.

[0041] Please continue reading Figure 1 As shown, the pet activity trajectory monitoring system also includes: The path analysis module is used to analyze the pet's position status and pet's activity trajectory based on the regional grayscale image and the pet's activity information, and is also used to adjust the analysis process of the pet's activity trajectory based on the monitoring coverage area, pet area, user pet area and video driving path. The path analysis module is connected to the regional analysis module.

[0042] See also Figure 4 As shown, the path analysis module includes: The path analysis unit is used to analyze the pet's position status and pet's activity trajectory based on the regional grayscale image and the pet's position. The pet's position status is used to indicate whether the pet is outdoors, and the pet's activity trajectory is used to indicate the pet's movement trajectory after being outdoors, thereby realizing the monitoring of the pet's activity trajectory.

[0043] Specifically, the path analysis unit in this embodiment analyzes the pet activity trajectory according to the regional grayscale image and the pet position. If there is any k∈N and k∈[0,300], satisfying L(X(tk),Y(tk))≥A4, the path analysis unit determines that the pet position status is indoor activity and does not analyze the pet activity trajectory. Otherwise, the path analysis unit determines that the pet position status is outdoor activity, and takes the pet position satisfying L(X(tk),Y(tk))<A4 as the activity coordinate point, and takes the set of activity coordinate points as the pet activity trajectory, wherein k represents the time range parameter, L(X(t),Y(t)) represents the grayscale value of the pixel point corresponding to the pet position in the regional grayscale image, and (X(t),Y(t)) represents the coordinates of the pixel point corresponding to the pet position in the regional grayscale image; the path analysis unit analyzes the regional grayscale image and the pet position to determine the pet position status and the pet activity trajectory, thereby improving the system's analysis efficiency of pet activity data and improving the accuracy of pet activity trajectory monitoring.

[0044] Please continue reading Figure 4 As shown, the path analysis module also includes: The position analysis unit is used to adjust the analysis process of the pet activity trajectory according to the monitoring coverage area, the pet position and the video driving path, so that the adjusted pet activity trajectory is related to the pet area extracted from the road monitoring video. The position analysis unit is connected to the path analysis unit.

[0045] Specifically, the position analysis unit in this embodiment adjusts the analysis process of the pet's activity trajectory according to the monitoring coverage area, the pet's position and the video driving path, wherein: When (X(t), Y(t))∈U, if the pet area is marked as the user pet area, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)), and X1(t)=D1(t), Y1(t)=D2(t); if the pet area is not marked as the user pet area and |D1(t)-X(t)|+|D2(t)-Y(t)|≤β / η, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)), and X1(t)=[X(t)+D1(t)] / 2, Y1(t)=[Y(t)+D2(t)] / 2; Otherwise, the position analysis unit does not adjust the active coordinate point; Wherein, U represents the monitoring coverage area, D1(t) represents the first corresponding parameter, and D1(t)=2×u(t)×M2×sinθ / (NSX×η), D2(t) represents the second corresponding parameter, and D2(t)=v(t)×M1×cosθ / (NSY×η), NSX represents the number of pixels in the x-axis direction of the road monitoring video, NSY represents the number of pixels in the y-axis direction of the road monitoring video, β represents the range comparison threshold, 1≤β≤3, and θ represents the shooting direction angle; the position analysis unit analyzes the monitoring coverage area, the pet position and the driving path to adjust the activity coordinate point, and judges whether the pet movement trajectory captured in the road monitoring video corresponds to the pet position, so as to correct the activity coordinate point, thereby improving the system's analysis efficiency of the pet activity data and improving the accuracy of the pet activity trajectory monitoring; it can be understood that in this embodiment, the value of the range comparison threshold is not specifically limited, and those skilled in the art can freely set it, as long as the adjustment of the pet activity trajectory is satisfied. The optimal value of the range comparison threshold is: β=2.

[0046] Please continue reading Figure 4 As shown, the path analysis module also includes: The pet analysis unit is used to optimize the adjustment process of the pet's activity trajectory according to the pet's position and the pet's heart rate, so that the optimized pet's activity trajectory is related to the pet's position and the pet's heart rate, determine whether the pet is exercising at a high intensity, and reduce the impact of abnormal video shooting data on the pet's activity trajectory analysis. The pet analysis unit is connected to the position analysis unit.

[0047] Specifically, the pet analysis unit in this embodiment optimizes the adjustment process of the pet's activity trajectory according to the pet's position and the pet's heart rate. If H(t)>h, the pet analysis unit determines that the pet's heart rate does not meet the threshold, and optimizes the adjustment process of the activity coordinate point. The optimized activity coordinate point is (X2(t), Y2(t)), and X2(t)=X1(t)×log h H(t),Y2(t)=Y1(t)×log hH(t); if H(t)≤h, the pet analysis unit determines that the pet's heart rate meets the threshold and does not optimize the adjustment process of the activity coordinate points; wherein, H(t) represents the pet's heart rate, h represents the heart rate threshold, and 90≤h≤120; the pet analysis unit analyzes the pet's position and the pet's heart rate to optimize the adjustment process of the pet's activity trajectory. When the pet's running intensity is high, the activity coordinate points are optimized, thereby improving the system's analysis efficiency of the pet's activity data and improving the accuracy of the pet's activity trajectory monitoring; it can be understood that in this embodiment, the value of the heart rate threshold is not specifically limited, and technical personnel in this field can set it freely, as long as the optimization of the activity coordinate point adjustment process is satisfied. The optimal value of the heart rate threshold is: h=110.

[0048] Please continue reading Figure 1 As shown, the pet activity trajectory monitoring system also includes: The track output module is used to output the pet's position status and pet's activity track to the user, and the track output module is connected to the path analysis module.

[0049] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A pet activity trajectory monitoring system, characterized in that: include: The city data acquisition module is used to obtain regional map information and road monitoring information of residential areas in the city; A map processing module is used to construct a regional grayscale image according to the regional map information, and is also used to mark the pixel points of the regional grayscale image according to the road monitoring information to obtain monitoring pixel points, and analyze the monitoring coverage area according to the monitoring pixel points, the regional map information and the road monitoring information; A pet data acquisition module is used to obtain pet activity information in real time; A video analysis module, used to extract the pet area according to the road monitoring information, and also used to mark the user's pet area in the pet area; The regional analysis module is used to analyze the video driving path according to the pet area; A path analysis module, which is used to analyze the pet's position status and pet's activity trajectory based on the regional grayscale image and the pet's activity information, and is also used to adjust the analysis process of the pet's activity trajectory based on the monitoring coverage area, the pet area, the user's pet area and the video driving path; The track output module is used to output the pet's location status and pet's activity track to the user.

2. The pet activity trajectory monitoring system according to claim 1, characterized in that: The map processing module is provided with an image construction unit, which is used to create an image with the same resolution as the regional map as the regional grayscale image, so that the regional grayscale image corresponds to the pixels in the regional map one by one, and the grayscale value of each pixel in the regional grayscale image is set, and the grayscale value of the pixel of the regional grayscale image corresponding to the white pixel in the regional image is set to A1, the grayscale value of the pixel of the regional grayscale image corresponding to the green pixel in the regional image is set to A2, the grayscale value of the pixel of the regional grayscale image corresponding to the gray pixel in the regional image is set to A3, and the grayscale value of the pixel of the regional grayscale image corresponding to the blue pixel in the regional image is set to A4, wherein A1 represents the first grayscale parameter, A2 represents the second grayscale parameter, A3 represents the third grayscale parameter, and A4 represents the fourth grayscale parameter.

3. The pet activity trajectory monitoring system according to claim 2, characterized in that: The map processing module is also provided with a monitoring analysis unit, which is used to analyze the first monitoring pixel point according to the monitoring pixel point, map scale, preset monitoring parameters and shooting direction. The monitoring analysis unit extracts the pixel point α pixels away from the current analysis monitoring pixel point in the shooting direction of the current analysis monitoring pixel point in the regional grayscale image as the end pixel point, and draws a line connecting the current analysis monitoring pixel point and the end pixel point, and uses the pixel point on the line as the first monitoring pixel point.

4. The pet activity trajectory monitoring system according to claim 3, characterized in that: The monitoring analysis unit analyzes the range distance parameter according to the first monitoring pixel point and the preset monitoring parameter, sets the range distance parameter to P, and sets , and extract the pixel points satisfying P≤M2 / η in the regional grayscale image as the second monitoring pixel points, where P represents the range distance parameter, (x, y) represents the coordinates of each pixel point in the regional grayscale image, (x1, y1) represents the first monitoring pixel point, and M2 represents the second preset monitoring parameter.

5. The pet activity trajectory monitoring system according to claim 4, characterized in that: The monitoring and analysis unit analyzes the monitoring coverage area according to the first monitoring pixel and the second monitoring pixel. If L(x1, y1)<A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the covering pixel. If L(x1, y1)≥A4, the monitoring and analysis unit uses the first monitoring pixel currently being analyzed as the masking pixel. If L(x2, y2)<A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the covering pixel. If L(x2, y2)≥A4, the monitoring and analysis unit uses the second monitoring pixel currently being analyzed as the masking pixel. The monitoring and analysis unit uses the area formed by the covering pixels as the monitoring coverage area, wherein L(x1, y1) represents the grayscale value of the first monitoring pixel in the regional grayscale image, and L(x2, y2) represents the grayscale value of the second monitoring pixel in the regional grayscale image.

6. The pet activity trajectory monitoring system according to claim 5, characterized in that: The video analysis module is provided with a region extraction unit, which is used to input the road monitoring video into the target detection model to extract the pet region in the road monitoring video; The video analysis module is also provided with an extraction optimization unit, which is used to input the pet image as a user pet data set into the target detection model for model training, optimize the extraction of the pet area, and when the ROL area of ​​the extracted pet area comes from the user pet data set, mark the pet area as the user pet area.

7. The pet activity trajectory monitoring system according to claim 6, characterized in that: The regional analysis module analyzes the pet monitoring position according to the pet area, sets the pet monitoring position to S(t)=(u(t),v(t)), sets u(t)=∑x3(t) / N3(t), v(t)=∑y3(t) / N3(t), where S(t) represents the pet monitoring position, t represents the time number, u(t) represents the horizontal coordinate mean parameter, v(t) represents the vertical coordinate mean parameter, x3(t) represents the horizontal coordinate of the pixel point in the pet area, y3(t) represents the vertical coordinate of the pixel point in the pet area, N3(t) represents the number of pixels in the pet area, and the regional analysis module uses the set of pet monitoring positions as the video driving path.

8. The pet activity trajectory monitoring system according to claim 7, characterized in that: The path analysis module is provided with a path analysis unit, which is used to analyze the pet activity trajectory according to the regional grayscale image and the pet position. If there is any k∈N and k∈[0,300], satisfying L(X(tk),Y(tk))≥A4, the path analysis unit determines that the pet position status is indoor activity and does not analyze the pet activity trajectory. On the contrary, the path analysis unit determines that the pet position status is outdoor activity, and takes the pet position satisfying L(X(tk),Y(tk))<A4 as the activity coordinate point, and takes the set of activity coordinate points as the pet activity trajectory, wherein k represents the time range parameter, L(X(t),Y(t)) represents the grayscale value of the pixel point corresponding to the pet position in the regional grayscale image, and (X(t),Y(t)) represents the coordinates of the pixel point corresponding to the pet position in the regional grayscale image.

9. The pet activity trajectory monitoring system according to claim 8, characterized in that: The path analysis module is also provided with a position analysis unit, which is used to adjust the analysis process of the pet's activity trajectory according to the monitoring coverage area, the pet's position and the video driving path, wherein: When (X(t), Y(t))∈U, if the pet area is marked as the user pet area, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)); if the pet area is not marked as the user pet area and |D1(t)-X(t)|+|D2(t)-Y(t)|≤β / η, the position analysis unit adjusts the activity coordinate point, and the adjusted activity coordinate point is (X1(t), Y1(t)); Otherwise, the position analysis unit does not adjust the active coordinate point.

10. The pet activity trajectory monitoring system according to claim 9, characterized in that: The path analysis module is also provided with a pet analysis unit, which is used to compare the pet's heart rate H(t) with the heart rate threshold h. When the pet's heart rate does not meet the threshold, the adjustment process of the activity coordinate point is optimized, and the optimized activity coordinate point is (X2(t), Y2(t)).

Images