Monitoring point location optimization method and apparatus integrating GIS technology and face recognition, and terminal

Abstract

The present application relates to a monitoring point location optimization method and apparatus integrating GIS technology and face recognition, and a terminal. In the method, the GIS technology and face recognition technology are adopted to realize grid management of a monitoring area; data is provided for identification of abnormal trajectory lines by means of device parameter information and monitoring data of monitoring devices; trajectory speeds and abnormal trajectory lines are analyzed on the basis of the monitoring data and snapshot data to identify monitoring blind areas in the monitoring area; and virtual point locations are constructed on the abnormal trajectory lines, recommended construction values are obtained, and a monitoring range map after accurate monitoring point location construction optimization is obtained. The coverage rate and monitoring efficiency of a monitoring network are significantly improved, the number of monitoring blind areas is effectively reduced, and the construction and operation cost of a monitoring system is reduced. The technical problems that traditional monitoring point location layout depends on manual experience and on-site investigation, the efficiency is low, and it is difficult to ensure that a monitoring network can comprehensively cover a key area, resulting in waste of resources are solved.

Description

Methods, devices, and terminals for optimizing monitoring points by integrating GIS technology and facial recognition Technical Field

[0001] This application relates to the field of intelligent monitoring technology, and in particular to a method, device and terminal for optimizing monitoring points by integrating GIS technology and facial recognition. Background Technology

[0002] With rapid urbanization, the importance of public safety monitoring is becoming increasingly prominent. However, traditional monitoring point layout mainly relies on manual experience and on-site surveys. This method is not only inefficient but also fails to ensure that the monitoring network can fully cover key areas and effectively capture important facial information. This leads to frequent monitoring blind spots and unnecessary waste of monitoring resources.

[0003] To address these issues and improve the efficiency and coverage of surveillance systems, there is an urgent need to adopt data analysis-based scientific methods to optimize the layout of surveillance points. Advances in Geographic Information Systems (GIS) and computer vision technologies have made this possible, enabling more precise and efficient construction of surveillance points. Summary of the Invention

[0004] This application provides a method, device, and terminal for optimizing monitoring points by integrating GIS technology and facial recognition. It is used to solve the technical problems of traditional monitoring point layout relying on manual experience and on-site surveys, which is inefficient and makes it difficult to ensure that the monitoring network can fully cover key areas, resulting in resource waste.

[0005] To achieve the above objectives, this application provides the following technical solution:

[0006] On the one hand, a method for optimizing monitoring points by integrating GIS technology and facial recognition is provided, including the following steps:

[0007] Obtain map data of the monitored area and device parameter information of each monitoring device in the monitored area. Based on all the device parameter information, use GIS technology to sequentially perform regional gridding and device location labeling on the monitored area to obtain the monitoring range area of ​​each monitoring device.

[0008] The monitoring data of each monitoring device is acquired in each of the monitoring range areas. Data of the same person is filtered from all the monitoring data and sorted by time to obtain the capture data of the same person. The monitoring data includes the captured image, the capture time, and the location of the person corresponding to the captured image and the means of transportation used by the person.

[0009] The distance data and time difference between any two adjacent captured images are obtained from the captured data, and the normal speed of the vehicle used by the person is obtained. The trajectory speed is calculated based on the distance data and the time difference. The trajectory speed and the normal speed are used to determine whether the trajectory line of the two adjacent captured images is an abnormal trajectory line.

[0010] If the trajectory lines of two adjacent captured images are abnormal trajectory lines, it is determined whether the abnormal trajectory lines in the monitoring range area are within the monitoring range of the monitoring device corresponding to the captured images; if not, virtual points are constructed on the abnormal trajectory lines in the monitoring range area and recommended construction values ​​are obtained to obtain a monitoring range map with optimized monitoring points.

[0011] Preferably, virtual monitoring points are constructed along the abnormal trajectory lines within the monitoring range area, and recommended construction values ​​are obtained to obtain an optimized monitoring range map, including:

[0012] Multiple virtual points are constructed on each of the abnormal trajectory lines in the monitoring range area. The corresponding monitoring devices are obtained from the grid of the monitoring range area where each virtual point is located, and a device dataset is obtained.

[0013] Obtain the angle between each monitoring device and the corresponding virtual point in the device dataset, and determine whether the virtual point is within the field of view of the corresponding monitoring device by comparing the angle with the field of view of the device parameter information in the corresponding monitoring device.

[0014] If the virtual point is within the field of view of the corresponding monitoring device, the recommended construction value of the virtual point is incremented by 1 until the virtual point is obtained by traversing all the monitoring devices in the device dataset.

[0015] Using the GIS technology, all abnormal trajectory lines, along with all corresponding virtual points and recommended construction values, are overlaid and displayed on the monitoring range area to obtain a monitoring range map with optimized monitoring points.

[0016] Preferably, the monitoring point optimization method integrating GIS technology and facial recognition includes using computer vision algorithms to acquire monitoring data from each of the monitoring devices within the monitoring range area.

[0017] Preferably, calculating the trajectory speed based on the distance data and the time difference includes: calculating the trajectory speed by dividing the distance data and the time difference.

[0018] Preferably, determining whether the abnormal trajectory line in the monitored area is within the monitoring range of the monitoring device corresponding to the captured image includes:

[0019] The two ends of the abnormal trajectory line are recorded as abnormal monitoring points, and the monitoring device corresponding to each abnormal monitoring point is obtained;

[0020] Obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device, and determine whether the abnormal monitoring point of the abnormal trajectory line is within the monitoring range of the monitoring device corresponding to the captured image by comparing the monitoring angle with the field of view of the device parameter information in the corresponding monitoring device.

[0021] If the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to optimize the monitoring range area.

[0022] On the other hand, a monitoring point optimization device integrating GIS technology and facial recognition is provided, including an area determination module, a data acquisition module, an anomaly judgment module, and a monitoring optimization module;

[0023] The area determination module is used to acquire map data of the monitoring area and equipment parameter information of each monitoring device in the monitoring area, and to use GIS technology to perform area gridding and equipment location labeling on the monitoring area according to all the equipment parameter information, so as to obtain the monitoring range area of ​​each monitoring device.

[0024] The data acquisition module is used to acquire monitoring data from each monitoring device in each monitoring range area, filter data of the same person from all the monitoring data and sort the data by time to obtain the capture data of the same person; the monitoring data includes the captured image, the capture time, and the location of the person corresponding to the captured image and the means of transportation used by the person;

[0025] The anomaly detection module is used to obtain the distance data and time difference between any two adjacent captured images from the captured data, as well as the normal speed of the vehicle used by the person, calculate the trajectory speed based on the distance data and the time difference, and determine whether the trajectory line of the two adjacent captured images is an abnormal trajectory line based on the trajectory speed and the normal speed.

[0026] The monitoring optimization module is used to determine whether the abnormal trajectory lines in the monitoring range area are within the monitoring range of the monitoring device corresponding to the captured images, based on whether the trajectory lines of two adjacent captured images are abnormal trajectory lines; if not, virtual points are constructed on the abnormal trajectory lines in the monitoring range area and recommended construction values ​​are obtained to obtain a monitoring range map with optimized monitoring points.

[0027] Preferably, the monitoring optimization module includes a construction submodule, a judgment submodule, a calculation submodule, and an optimization submodule;

[0028] The construction submodule is used to construct multiple virtual points on each abnormal trajectory line in the monitoring range area, and obtain the corresponding monitoring device in the grid of the monitoring range area according to the location of each virtual point to obtain the device dataset.

[0029] The judgment submodule is used to obtain the angle between each monitoring device and the corresponding virtual point in the device dataset, and to determine whether the virtual point is within the field of view of the corresponding monitoring device by comparing the angle with the field of view of the device parameter information in the corresponding monitoring device.

[0030] The calculation submodule is used to increment the construction recommendation value of the virtual point by 1 according to the field of view of the corresponding monitoring device, until the virtual point is obtained by traversing all the monitoring devices in the device dataset.

[0031] The optimization submodule is used to overlay and display all abnormal trajectory lines, along with all corresponding virtual points and recommended construction values, on the monitoring range area using the GIS technology, to obtain a monitoring range map with optimized monitoring points.

[0032] Preferably, the data acquisition module is further configured to acquire monitoring data of each of the monitoring devices using computer vision algorithms within the monitoring range area.

[0033] Preferably, the monitoring optimization module is further configured to record both ends of the abnormal trajectory line as abnormal monitoring points and obtain the monitoring device corresponding to each abnormal monitoring point; obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device; and determine whether the abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image by comparing the monitoring angle with the field of view of the device parameter information in the corresponding monitoring device; if the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to perform monitoring optimization on the monitoring range area.

[0034] On the other hand, a terminal device is provided, including a processor and a memory;

[0035] The memory is used to store program code and transmit the program code to the processor;

[0036] The processor is used to execute the above-described method for optimizing monitoring points by integrating GIS technology and facial recognition, according to the instructions in the program code.

[0037] This invention relates to a monitoring point optimization method, device, and terminal integrating GIS technology and facial recognition. The method includes acquiring map data of the monitoring area and equipment parameter information of each monitoring device within that area; using GIS technology to sequentially perform area gridding and device location labeling on the monitoring area based on all equipment parameter information to obtain the monitoring range of each monitoring device; acquiring monitoring data from each monitoring device within each monitoring range; filtering data for the same person from all monitoring data and sorting the data by time to obtain the captured data for that person; the monitoring data includes captured images, capture time, and the person corresponding to the captured image. The system identifies the location of personnel and the means of transportation they use. It retrieves the distance and time difference between any two adjacent captured images, along with the normal speed of the vehicle used. The trajectory speed is calculated based on the distance and time difference. The system then determines whether the trajectory lines of the two adjacent captured images are abnormal. If they are abnormal, the system checks whether the abnormal trajectory lines within the monitoring area are within the monitoring range of the corresponding monitoring equipment. If not, it constructs virtual points along the abnormal trajectory lines within the monitoring area and obtains recommended values, resulting in an optimized monitoring range map.

[0038] As can be seen from the above technical solutions, this application has the following advantages: This monitoring point optimization method integrating GIS technology and facial recognition uses GIS technology and facial recognition technology to achieve grid-based management of the monitoring area; then, it provides data for abnormal trajectory line identification through the equipment parameter information and monitoring data of the monitoring equipment; based on the analysis of trajectory speed and abnormal trajectory lines according to the monitoring data and capture data, it identifies monitoring blind spots in the monitoring area, constructs virtual points along the abnormal trajectory lines and obtains recommended construction values, and obtains a monitoring range map after the precise construction and optimization of monitoring points, which significantly improves the coverage and monitoring efficiency of the monitoring network, effectively reduces monitoring blind spots, and reduces the construction and operation costs of the monitoring system. It solves the technical problem that the traditional monitoring point layout relies on manual experience and on-site surveys, which is inefficient and makes it difficult to ensure that the monitoring network can fully cover key areas, resulting in resource waste.

[0039] This monitoring point optimization device, integrating GIS technology and facial recognition, achieves precise data analysis and intelligent optimization strategies through modules for area determination, data acquisition, anomaly detection, and monitoring optimization, enabling the scientific layout of monitoring points. This device will significantly improve the coverage and efficiency of the monitoring network, effectively reduce blind spots, and lower the construction and operation costs of the monitoring system. Simultaneously, it will provide strong scientific decision-making support for city managers, enhance public safety management capabilities, and ensure urban safety and order. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, 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.

[0041] Figure 1 is a flowchart of the steps of the monitoring point optimization method integrating GIS technology and face recognition described in the embodiment of this application;

[0042] Figure 2 is a schematic diagram of the monitoring point optimization device that integrates GIS technology and face recognition as described in the embodiment of this application;

[0043] Figure 3 is a schematic diagram of the terminal device described in an embodiment of this application. Detailed Implementation

[0044] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] In the description of the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0046] In the embodiments of this application, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application according to the specific circumstances.

[0047] Patent terminology:

[0048] Video Image Analysis: The process of deeply analyzing and processing the content of video images using computer image vision analysis technology.

[0049] Face recognition: quickly locates photos of the same person in a large database.

[0050] Face clustering refers to the process of classifying and grouping faces in different images, so that facial images of the same person are grouped together, while facial images of different people are separated.

[0051] GIS stands for Geographic Information System, which is a technological system for collecting, storing, querying, analyzing, and displaying geospatial data.

[0052] Face capture: The process of capturing, recognizing, and recording facial images of pedestrians using computer vision technology.

[0053] Field of view (FOV): The maximum angle range that a camera can capture.

[0054] Abnormal trajectories: Trajectories of pedestrians or vehicles within the monitored area that do not conform to normal behavioral patterns in terms of speed, direction, etc.

[0055] Virtual camera location setting: Simulates the setting of new camera locations on a map to evaluate the best installation location.

[0056] This application provides a method, device, and terminal for optimizing monitoring points by integrating GIS technology and facial recognition. It solves the technical problems of traditional monitoring point layout relying on manual experience and on-site surveys, which is inefficient and makes it difficult to ensure that the monitoring network can fully cover key areas, resulting in resource waste.

[0057] Example 1:

[0058] Figure 1 is a flowchart of the steps of the monitoring point optimization method integrating GIS technology and face recognition described in the embodiments of this application.

[0059] As shown in Figure 1, this application embodiment provides a monitoring point optimization method integrating GIS technology and face recognition, including the following steps:

[0060] S1. Obtain map data of the monitored area and equipment parameter information of each monitoring device in the monitored area. Based on all equipment parameter information and map data, use GIS technology to perform regional gridding and equipment location labeling on the monitored area in sequence to obtain the monitoring range area of ​​each monitoring device.

[0061] It should be noted that in step S1, after acquiring the map data of the monitoring area, regional gridding is performed to obtain the monitoring range area, providing data for subsequent optimization of monitoring points. In this embodiment, the map data includes geographic coordinates and terrain features. Device parameters include the height, focal length, and field of view (FOV) of the monitoring equipment. Step S1 can be understood as first acquiring the map data of the monitoring area, then using GIS technology to divide the area to be monitored into multiple grids. The area of ​​each grid can be set according to the actual situation, such as: 100m*100m, 200m*200m, 500m*500m grids. Finally, the locations of existing monitoring equipment are marked on the map of the monitoring area, and the monitoring range of the corresponding monitoring equipment is drawn according to the equipment parameter information of the monitoring equipment, resulting in the monitoring range area composed of the monitoring ranges of each monitoring equipment. The monitoring equipment can be a camera or other terminals with monitoring functions. The process of drawing the monitoring range of a monitoring device based on its equipment parameter information can be understood as follows: based on the equipment parameter information of the monitoring device, the approximate monitoring range can be known, and finally, an approximate monitoring range of the monitoring device locations can be displayed on the map of the monitoring area. Then, this data is imported into the GIS and calculated to determine the monitoring range of the planar map and displayed on the map of the monitoring area.

[0062] S2. Acquire monitoring data from each monitoring device within each monitoring area. Filter data for the same person from all monitoring data and sort the data by time to obtain snapshot data for the same person. The monitoring data includes the snapshot image, the snapshot time, and the location of the person corresponding to the snapshot image and the means of transportation used by the person. Computer vision algorithms are used to acquire monitoring data from each monitoring device within the monitoring area.

[0063] It should be noted that in step S2, the monitoring range area is formed by the monitoring range of each monitoring device in the monitoring area obtained in step S1. Within this monitoring range area, monitoring data from each monitoring device is acquired, and data of the same person is filtered from the monitoring data and sorted by time to obtain the captured data of the same person. In this embodiment, the monitoring data can be obtained by the monitoring devices using computer vision algorithms to capture face and pedestrian data within their monitoring range. The vehicles used by pedestrians are then identified or updated based on the real-time captured images. Computer vision algorithms are a relatively mature face recognition technology in this field; the specific details of the computer vision algorithm are not elaborated in this embodiment. Capturing images is performed using the constructed monitoring devices. This can be understood as either face data captured by the monitoring devices themselves, or face data extracted from the image obtained by the monitoring devices using face algorithms.

[0064] In this embodiment of the application, in the computer vision algorithm, if the similarity of the people in two captured images reaches 92%, they are considered to be the same person. That is, each captured record has a unique identifier for a person, which is used to determine whether they are the same person.

[0065] It should be noted that the monitoring data can be analyzed by randomly selecting the trajectory maps of 100 people from each monitoring device, and the number of random samplings can be adjusted. Then, the monitoring data for the corresponding sampled personnel for one week is statistically analyzed and sorted in ascending chronological order to obtain the captured data for subsequent analysis.

[0066] S3. Obtain the distance data and time difference between any two adjacent captured images from the captured data, as well as the normal speed of the vehicle used by the person. Calculate the trajectory speed based on the distance data and time difference. Determine whether the trajectory lines of the two adjacent captured images are abnormal based on the trajectory speed and the normal speed. The trajectory speed is calculated by dividing the distance data by the time difference.

[0067] It should be noted that in step S3, the trajectory speed is calculated based on the distance data and time difference between any two adjacent captured images obtained in step S2. Then, by comparing the normal speed of the vehicle used by the pedestrian with the trajectory speed, it is determined whether the trajectory of the two adjacent captured images is an abnormal trajectory. In this embodiment, the distance data between any two adjacent captured images refers to records of the same person being captured in two consecutive images. These could be two records captured by the same monitoring device, or records captured by two different monitoring devices. This can be understood as finding N capture records for this person, each record having a corresponding monitoring device location (with latitude and longitude) and capture time. These records are then sorted by time, and the time taken for records 1-2 is calculated, then 2-3, 3-4, and so on until N-1 to N.

[0068] In this embodiment of the application, determining whether the trajectory lines of two adjacent captured images are abnormal based on the trajectory speed and normal speed includes: if the trajectory speed is greater than the normal speed, then the trajectory lines of the two adjacent captured images are determined to be abnormal; if the trajectory speed is not greater than the normal speed, then the trajectory lines of the two adjacent captured images are determined to be normal.

[0069] It should be noted that if the vehicle is a motorcycle, the normal speed limit of 60 kilometers per hour in the city shall be used as the standard. If the trajectory speed is greater than 60 kilometers per hour, the trajectory lines of two adjacent captured images shall be marked as abnormal trajectory lines.

[0070] S4. If the trajectory lines of two adjacent captured images are abnormal trajectory lines, determine whether the abnormal trajectory lines in the monitoring area are within the monitoring range of the monitoring device corresponding to the captured images; if not, construct virtual points on the abnormal trajectory lines in the monitoring area and obtain recommended construction values ​​to obtain a monitoring range map with optimized monitoring points.

[0071] It should be noted that in step S4, based on the determination of abnormal trajectory lines in step S3, an abnormal trajectory layer is overlaid on the monitoring layer of the corresponding monitoring equipment using GIS technology. Then, it is first determined whether the abnormal trajectory line is within the monitoring range of the monitoring equipment. If not, virtual points are constructed on the abnormal trajectory line, and recommended values ​​for virtual point construction are displayed. Based on the recommended values ​​of the virtual points, data is provided to the user to select the optimal monitoring equipment for the abnormal trajectory line. In this embodiment, the monitoring point optimization method integrating GIS technology and facial recognition achieves precise data analysis and intelligent optimization strategies through steps S1 to S4, realizing the scientific layout of monitoring points. This monitoring point optimization method integrating GIS technology and facial recognition will significantly improve the coverage and efficiency of the monitoring network, effectively reduce monitoring blind spots, and lower the construction and operation costs of the monitoring system. Simultaneously, it will provide strong scientific decision-making support for city managers, enhance public safety management capabilities, and ensure urban safety and order.

[0072] In this embodiment, users can directly observe the recommended virtual locations for installing monitoring equipment and the recommended data through the monitoring range map obtained by the monitoring point optimization method that integrates GIS technology and facial recognition. Users can then select the corresponding virtual location for construction. If the recommended virtual locations are unsatisfactory, users can also construct monitoring points for abnormal trajectory lines according to the logic of the monitoring system. Finally, after the monitoring points are constructed, users can observe whether the abnormal trajectory lines on the monitoring points have disappeared to verify whether the monitoring points have been constructed reasonably.

[0073] This application provides a monitoring point optimization method integrating GIS technology and facial recognition. The method includes acquiring map data of the monitoring area and equipment parameter information of each monitoring device in the monitoring area; using GIS technology to sequentially perform area gridding and equipment location labeling on the monitoring area based on all equipment parameter information to obtain the monitoring range of each monitoring device; acquiring monitoring data from each monitoring device within each monitoring range; filtering data for the same person from all monitoring data and sorting the data by time to obtain the captured data of the same person; the monitoring data includes captured images, capture time, and the location and device used by the person corresponding to the captured image. The system detects the vehicles used by individuals; it obtains the distance and time difference between any two adjacent captured images from the captured data, as well as the normal speed of the vehicles used by the individuals. Based on the distance and time difference, it calculates the trajectory speed and determines whether the trajectory lines of the two adjacent captured images are abnormal. If the trajectory lines of the two adjacent captured images are abnormal, it checks whether the abnormal trajectory lines within the monitoring area are within the monitoring range of the corresponding monitoring equipment. If not, it constructs virtual points on the abnormal trajectory lines within the monitoring area and obtains recommended construction values, resulting in an optimized monitoring range map of the monitoring points. This monitoring point optimization method, integrating GIS and facial recognition technologies, uses these technologies to achieve grid-based management of the monitored area. It then uses equipment parameter information and monitoring data to provide data for identifying abnormal trajectory lines. Based on the analysis of trajectory speed and abnormal trajectory lines using monitoring and snapshot data, it identifies monitoring blind spots within the monitored area, constructs virtual monitoring points along abnormal trajectory lines, and obtains recommended construction values. This results in a map of the optimized monitoring range, significantly improving the coverage and efficiency of the monitoring network, effectively reducing monitoring blind spots, and lowering the construction and operation costs of the monitoring system. It solves the technical problems of traditional monitoring point layout relying on manual experience and on-site surveys, which is inefficient and makes it difficult to ensure comprehensive coverage of key areas, leading to resource waste.

[0074] It should be noted that this monitoring point optimization method integrating GIS technology and facial recognition utilizes GIS technology to visualize virtual monitoring points and abnormal trajectory lines. In this embodiment, the monitoring area is optimized through this method, enhancing the coverage and efficiency of the monitoring area, reducing blind spots, improving urban safety management, supporting scientific decision-making in urban management, and optimizing resource allocation. The visual interface simplifies the identification and decision-making process for monitoring points, improves the scientific nature and accuracy of monitoring point layout, reduces costs, and enhances the overall efficiency and coverage of the monitoring area.

[0075] In one embodiment of this application, virtual monitoring points are constructed along abnormal trajectory lines within the monitoring range area, and recommended construction values ​​are obtained to generate an optimized monitoring range map, including:

[0076] Multiple virtual points are constructed on each abnormal trajectory line in the monitoring range area. The corresponding monitoring devices are obtained from the grid of the monitoring range area where each virtual point is located, and the device dataset is obtained.

[0077] Obtain the angle between each monitoring device and its corresponding virtual point in the device dataset. Based on the angle and the field of view of the device parameter information in the corresponding monitoring device, determine whether the virtual point is within the field of view of the corresponding monitoring device.

[0078] If the virtual point is within the field of view of the corresponding monitoring device, the recommended construction value of the corresponding virtual point is incremented by 1 until the virtual point is obtained by traversing all monitoring devices in the device dataset.

[0079] Using GIS technology, all abnormal trajectory lines, along with their corresponding virtual points and recommended construction values, are overlaid and displayed on the monitoring area to obtain a monitoring range map with optimized monitoring points.

[0080] It should be noted that in step S3, all abnormal trajectory lines in the monitoring range area are obtained. For each abnormal trajectory line, multiple virtual points are first constructed (e.g., 12). Then, based on the monitoring range area divided by the grid in step S1, all monitoring devices within the grid of each virtual point are obtained, resulting in a device dataset. Next, the angle between each monitoring device and its corresponding virtual point in the device dataset is obtained. This angle is compared with the field of view of the corresponding monitoring device's parameter information to determine if the virtual point is within the field of view of the corresponding monitoring device. If so, the recommended construction value is incremented by 1. This process continues until all monitoring devices in the device dataset are traversed to obtain the corresponding recommended construction value for the virtual point. The locations of all virtual points and their corresponding recommended construction values ​​are overlaid on the map of the monitoring range area using GIS technology to obtain a monitoring range map. This monitoring range map displays the locations of monitoring devices in the area grid, the monitoring range of the monitoring devices, abnormal trajectory lines, recommended virtual points, and the recommended construction values ​​for the corresponding recommended points. The initial value of the recommended construction value is 0.

[0081] In this embodiment of the application, obtaining the angle between each monitoring device and its corresponding virtual point in the device dataset includes: taking the horizontal orientation of the monitoring device as the positive x-axis, the direction vector of the monitoring device can be denoted as... The vector from the virtual point P to the monitoring device is denoted as . The angle θ between the monitoring device and the corresponding virtual point is calculated using the dot product formula. If the angle θ is not greater than half the field of view (FOV) of the monitoring device (2 / 2), then the virtual point P is within the field of view of the corresponding monitoring device. If the angle θ is greater than half the field of view (FOV) of the monitoring device (2 / 2), then the virtual point P is not within the field of view of the corresponding monitoring device.

[0082] It should be noted that the dot product formula is:

[0083] In one embodiment of this application, determining whether an abnormal trajectory line within the monitored area is within the monitoring range of the monitoring device corresponding to the captured image includes:

[0084] Record both ends of the abnormal trajectory line as abnormal monitoring points and obtain the monitoring equipment corresponding to each abnormal monitoring point;

[0085] Obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device. Based on the comparison between the monitoring angle and the field of view of the device parameter information in the corresponding monitoring device, determine whether the abnormal monitoring point of the abnormal trajectory line is within the monitoring range of the monitoring device corresponding to the captured image.

[0086] If the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to optimize the monitoring range area.

[0087] It should be noted that the monitoring angle between each abnormal monitoring point and its corresponding monitoring device can be calculated using the dot product formula mentioned above. Determining whether an abnormal trajectory is within the monitoring range of the monitoring device corresponding to the captured image can be understood as follows: if the monitoring angle is no greater than half the field of view (FOV) of the monitoring device, then the abnormal monitoring point of the abnormal trajectory is within the monitoring range of the monitoring device corresponding to the captured image. If the monitoring angle is greater than half the FOV of the monitoring device, then the abnormal monitoring point of the abnormal trajectory is not within the monitoring range of the monitoring device corresponding to the captured image.

[0088] Example 2:

[0089] Figure 2 is a schematic diagram of the monitoring point optimization device that integrates GIS technology and face recognition as described in the embodiment of this application.

[0090] As shown in Figure 2, this application embodiment provides a monitoring point optimization device that integrates GIS technology and face recognition, including a region determination module 10, a data acquisition module 20, an anomaly judgment module 30, and a monitoring optimization module 40;

[0091] The area determination module 10 is used to obtain map data of the monitoring area and equipment parameter information of each monitoring device in the monitoring area. Based on all equipment parameter information, GIS technology is used to perform area gridding and equipment location labeling on the monitoring area in sequence to obtain the monitoring range area of ​​each monitoring device.

[0092] The data acquisition module 20 is used to acquire monitoring data from various monitoring devices in various monitoring range areas, filter data of the same person from all monitoring data and sort the data by time to obtain the capture data of the same person; the monitoring data includes the captured image, the capture time, and the location of the person corresponding to the captured image and the means of transportation used by the person;

[0093] The anomaly detection module 30 is used to obtain the distance data and time difference between any two adjacent captured images from the captured data, as well as the normal speed of the vehicle used by the person. The trajectory speed is calculated based on the distance data and time difference, and the trajectory speed and normal speed are used to determine whether the trajectory line of the two adjacent captured images is an abnormal trajectory line.

[0094] The monitoring optimization module 40 is used to determine whether the abnormal trajectory lines in the monitoring range area are within the monitoring range of the monitoring device corresponding to the captured images, based on whether the trajectory lines of two adjacent captured images are abnormal trajectory lines. If not, virtual points are constructed on the abnormal trajectory lines in the monitoring range area and recommended construction values ​​are obtained to obtain a monitoring range map with optimized monitoring points.

[0095] It should be noted that the module content of this monitoring point optimization device integrating GIS technology and facial recognition corresponds to the steps in the method of Embodiment 1. Embodiment 1 has already described the steps of the monitoring point optimization method integrating GIS technology and facial recognition in detail, and this embodiment will not repeat the description of the module content of the monitoring point optimization device integrating GIS technology and facial recognition. This monitoring point optimization device integrating GIS technology and facial recognition achieves accurate data analysis and intelligent optimization strategies through the area determination module 10, data acquisition module 20, anomaly judgment module 30, and monitoring optimization module 40, realizing the scientific layout of monitoring points. This monitoring point optimization device integrating GIS technology and facial recognition will significantly improve the coverage and efficiency of the monitoring network, effectively reduce monitoring blind spots, and reduce the construction and operation costs of the monitoring system. At the same time, it will provide strong scientific decision support for city managers, enhance public safety management capabilities, and ensure the safety and order of the city.

[0096] In this embodiment, the monitoring optimization module 40 includes a construction submodule, a judgment submodule, a calculation submodule, and an optimization submodule;

[0097] The construction submodule is used to build multiple virtual points on each abnormal trajectory line in the monitoring range area, and obtain the corresponding monitoring devices in the grid of the monitoring range area where each virtual point is located to obtain the device dataset.

[0098] The judgment submodule is used to obtain the angle between each monitoring device and the corresponding virtual point in the device dataset, and to determine whether the virtual point is within the field of view of the corresponding monitoring device by comparing the angle with the field of view of the device parameter information in the corresponding monitoring device.

[0099] The calculation submodule is used to increment the construction recommendation value of the corresponding virtual point by 1 based on whether the virtual point is within the field of view of the corresponding monitoring device, until the virtual point is obtained by traversing all monitoring devices in the device dataset.

[0100] The optimization submodule uses GIS technology to overlay and display all abnormal trajectory lines, corresponding virtual points, and recommended construction values ​​on the monitoring range area, resulting in an optimized monitoring range map of the monitoring points.

[0101] In this embodiment of the application, the data acquisition module 10 is also used to acquire monitoring data of each monitoring device in the monitoring range area using computer vision algorithms.

[0102] In this embodiment, the monitoring optimization module 40 is further configured to record the two ends of the abnormal trajectory line as abnormal monitoring points and obtain the monitoring device corresponding to each abnormal monitoring point; obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device; and determine whether the abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image by comparing the monitoring angle with the field of view of the device parameter information in the corresponding monitoring device; if the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to perform monitoring optimization on the monitoring range area.

[0103] Example 3:

[0104] Figure 3 is a schematic diagram of the terminal device described in an embodiment of this application.

[0105] As shown in Figure 3, this application embodiment provides a terminal device, including a processor and a memory;

[0106] Memory is used to store program code and transfer the program code to the processor;

[0107] The processor is used to execute the aforementioned method for optimizing monitoring points by integrating GIS technology and facial recognition, based on instructions in the program code.

[0108] It should be noted that the processor is used to execute the steps in the above-described embodiment of a monitoring point optimization method integrating GIS technology and facial recognition, according to the instructions in the program code. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described system / device embodiments.

[0109] For example, a computer program can be divided into one or more modules / units, one or more of which are stored in memory and executed by a processor to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0110] Terminal devices can be computing devices such as desktop computers, laptops, handheld computers, and cloud servers. Terminal devices may include, but are not limited to, processors and memory. Those skilled in the art will understand that this does not constitute a limitation on the terminal device, which may include more or fewer components than illustrated, or combinations of certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.

[0111] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (dSICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor, etc.

[0112] Memory can be an internal storage unit of a terminal device, such as a hard drive or RAM. Memory can also be an external storage device, such as a plug-in hard drive, smart memory card (SMC), secure digital card (SD) card, or flash card. Furthermore, memory can include both internal and external storage units. Memory is used to store computer programs and other programs and data required by the terminal device. Memory can also be used to temporarily store data that has been output or will be output.

[0113] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0114] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0115] 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.

[0116] Furthermore, the functional units in the various embodiments of this application 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.

[0117] 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, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] The above-described 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.

Claims

1. A monitoring point optimization method combining GIS technology and face recognition, characterized in that, Includes the following steps: Obtain map data of the monitored area and device parameter information of each monitoring device in the monitored area. Based on all the device parameter information, use GIS technology to sequentially perform regional gridding and device location labeling on the monitored area to obtain the monitoring range area of ​​each monitoring device. The monitoring data of each monitoring device is acquired in each of the monitoring range areas. Data of the same person is filtered from all the monitoring data and sorted by time to obtain the capture data of the same person. The monitoring data includes the captured image, the capture time, and the location of the person corresponding to the captured image and the means of transportation used by the person. The distance data and time difference between any two adjacent captured images are obtained from the captured data, and the normal speed of the vehicle used by the person is obtained. The trajectory speed is calculated based on the distance data and the time difference. The trajectory speed and the normal speed are used to determine whether the trajectory line of the two adjacent captured images is an abnormal trajectory line. If the trajectory of two adjacent captured images is an abnormal trajectory, it is determined whether the abnormal trajectory in the monitored area is within the monitoring range of the monitoring device corresponding to the captured image. If not, virtual points are constructed on the abnormal trajectory line within the monitoring range area, and recommended construction values ​​are obtained to obtain a monitoring range map with optimized monitoring points. 2.The method of claim 1, wherein, Virtual monitoring points are constructed along the abnormal trajectory lines within the monitored area, and recommended construction values ​​are obtained to generate an optimized monitoring range map, including: Multiple virtual points are constructed on each of the abnormal trajectory lines in the monitoring range area. The corresponding monitoring devices are obtained from the grid of the monitoring range area where each virtual point is located, and a device dataset is obtained. Obtain the angle between each monitoring device and the corresponding virtual point in the device dataset, and determine whether the virtual point is within the field of view of the corresponding monitoring device by comparing the angle with the field of view of the device parameter information in the corresponding monitoring device. If the virtual point is within the field of view of the corresponding monitoring device, the recommended construction value of the virtual point is incremented by 1 until the virtual point is obtained by traversing all the monitoring devices in the device dataset. Using the GIS technology, all abnormal trajectory lines, along with all corresponding virtual points and recommended construction values, are overlaid and displayed on the monitoring range area to obtain a monitoring range map with optimized monitoring points. 3.The method of claim 1, wherein, This includes using computer vision algorithms to acquire monitoring data from each of the monitoring devices within the monitored area. 4.The method of claim 1, wherein, The trajectory speed is calculated based on the distance data and the time difference, including: calculating the trajectory speed by dividing the distance data and the time difference. 5.The method of claim 1, wherein, Determining whether the abnormal trajectory line in the monitored area is within the monitoring range of the monitoring device corresponding to the captured image includes: The two ends of the abnormal trajectory line are recorded as abnormal monitoring points, and the monitoring device corresponding to each abnormal monitoring point is obtained; Obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device, and determine whether the abnormal monitoring point of the abnormal trajectory line is within the monitoring range of the monitoring device corresponding to the captured image by comparing the monitoring angle with the field of view of the device parameter information in the corresponding monitoring device. If the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to optimize the monitoring range area.

6. A monitoring point position optimization device fusing GIS technology and face recognition, characterized in that, It includes a region determination module, a data acquisition module, an anomaly detection module, and a monitoring optimization module; The area determination module is used to acquire map data of the monitoring area and equipment parameter information of each monitoring device in the monitoring area, and to use GIS technology to perform area gridding and equipment location labeling on the monitoring area according to all the equipment parameter information, so as to obtain the monitoring range area of ​​each monitoring device. The data acquisition module is used to acquire monitoring data from each monitoring device in each monitoring range area, filter data of the same person from all the monitoring data and sort the data by time to obtain the capture data of the same person; the monitoring data includes the captured image, the capture time, and the location of the person corresponding to the captured image and the means of transportation used by the person; The anomaly detection module is used to obtain the distance data and time difference between any two adjacent captured images from the captured data, as well as the normal speed of the vehicle used by the person, calculate the trajectory speed based on the distance data and the time difference, and determine whether the trajectory line of the two adjacent captured images is an abnormal trajectory line based on the trajectory speed and the normal speed. The monitoring optimization module is used to determine whether the abnormal trajectory line in the monitoring range area is within the monitoring range of the monitoring device corresponding to the captured image, based on whether the trajectory line of two adjacent captured images is an abnormal trajectory line. If not, virtual points are constructed on the abnormal trajectory line within the monitoring range area, and recommended construction values ​​are obtained to obtain a monitoring range map with optimized monitoring points. 7.The monitoring point optimization device of fusing GIS technology and face recognition according to claim 6, characterized in that, The monitoring optimization module includes a construction submodule, a judgment submodule, a calculation submodule, and an optimization submodule; The construction submodule is used to construct multiple virtual points on each abnormal trajectory line in the monitoring range area, and obtain the corresponding monitoring device in the grid of the monitoring range area according to the location of each virtual point to obtain the device dataset. The judgment submodule is used to obtain the angle between each monitoring device and the corresponding virtual point in the device dataset, and to determine whether the virtual point is within the field of view of the corresponding monitoring device by comparing the angle with the field of view of the device parameter information in the corresponding monitoring device. The calculation submodule is used to increment the construction recommendation value of the virtual point by 1 according to the field of view of the corresponding monitoring device, until the virtual point is obtained by traversing all the monitoring devices in the device dataset. The optimization submodule is used to overlay and display all abnormal trajectory lines, along with all corresponding virtual points and construction recommendation values, on the monitoring range area using the GIS technology, to obtain a monitoring range map with optimized monitoring points. 8.The monitoring point optimization device of fusing GIS technology and face recognition according to claim 6, characterized in that, The data acquisition module is also used to acquire monitoring data of each monitoring device in the monitoring range area using computer vision algorithms. 9.The monitoring point optimization device of fusing GIS technology and face recognition according to claim 6, characterized in that, The monitoring optimization module is further configured to record both ends of the abnormal trajectory line as abnormal monitoring points and obtain the monitoring device corresponding to each abnormal monitoring point; obtain the monitoring angle between each abnormal monitoring point and the corresponding monitoring device; and determine whether the abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image by comparing the monitoring angle with the field of view of the device parameter information in the corresponding monitoring device; if the two abnormal monitoring points of the abnormal trajectory line are within the monitoring range of the monitoring device corresponding to the captured image, then there is no need to perform monitoring optimization on the monitoring range area.

10. A terminal device, comprising: Including the processor and memory; The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the monitoring point optimization method integrating GIS technology and face recognition as described in any one of claims 1-5, according to the instructions in the program code.

Images