Human body tracking method, human body tracking device, storage medium and electronic equipment

Abstract

The invention provides a human body tracking method, a human body tracking device, a storage medium and electronic equipment. The method comprises the following steps: acquiring real-time video data of a target human body through a video monitoring system; processing the real-time video data to extract dynamic features of the target human body to obtain target features; position information, sent by the Beidou satellite positioning system, of the target human body is received, and the position information at least comprises the longitude, the latitude and the height of the target human body; and performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result so as to realize real-time tracking of the target human body. The method solves the problem of how to improve the accuracy and efficiency of human body tracking in the prior art.

Description

Technical Field

[0001] The present application relates to the technical field of target tracking, and in particular to a human body tracking method, a human body tracking device, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the rapid development of science and technology, human tracking technology has penetrated into all aspects of life, especially in the fields of security monitoring, intelligent transportation, etc., its application has become increasingly important.

[0003] However, traditional human tracking methods, such as video surveillance or single positioning technology, often appear to be incapable in complex environments and wide areas. For example, in environments with large light changes and many obstructions, the accuracy of video surveillance will be greatly reduced. And single positioning technology, such as GPS, although it performs well in open areas, in densely built or indoor environments, the signal is often severely interfered, resulting in reduced positioning accuracy.

[0004] Therefore, there is an urgent need for a method to improve the accuracy and efficiency of human body tracking. Summary of the invention

[0005] The main purpose of the present application is to provide a human body tracking method, a human body tracking device, a computer-readable storage medium and an electronic device, so as to at least solve the problem of how to improve the accuracy and efficiency of human body tracking in the prior art.

[0006] According to one aspect of the present application, a human body tracking method is provided, comprising: acquiring real-time video data of a target human body through a video surveillance system; processing the real-time video data to extract dynamic features of the target human body to obtain target features; receiving position information of the target human body sent by a Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target human body; performing synchronous matching processing on the target features and the position information to obtain synchronous matching results to achieve real-time tracking of the target human body.

[0007] Optionally, real-time video data of a target human body is obtained through a video surveillance system, including: using a target detection algorithm to obtain a human body within a surveillance area of ​​the video surveillance system to obtain the target human body; obtaining original video data of the target human body; compressing the original video data to obtain first video data; performing adaptive illumination compensation processing on the first video data to obtain second video data; and performing background elimination processing on the second video data to obtain the real-time video data.

[0008] Optionally, the real-time video data is processed to extract dynamic features of the target human body to obtain target features, including: using a computer vision algorithm to obtain the motion trajectory of the target human body, the speed of the target human body and the acceleration of the target human body; performing multimodal data fusion on the motion trajectory, the speed and the acceleration to obtain the target features.

[0009] Optionally, the synchronous matching result includes a matching result and a synchronization result, and the target feature and the position information are synchronously matched to obtain a synchronous matching result to achieve real-time tracking of the target human body, including: matching the target feature and the position information to obtain the matching result; synchronously processing the target feature and the position information to obtain the synchronization result.

[0010] Optionally, the matching result includes matching location information, and matching processing is performed on the target feature and the location information to obtain the matching result, including: calculating the time difference between the target feature and the location information, the speed difference between the target feature and the location information, and the direction difference between the target feature and the location information; determining whether the time difference is less than a time difference threshold, whether the speed difference is less than a speed difference threshold, and whether the direction difference is less than a direction difference threshold; when the time difference is less than the time difference threshold, the speed difference is less than the speed difference threshold, and the direction difference is less than the direction difference threshold, determining that the corresponding location information is the matching location information.

[0011] Optionally, performing synchronization processing on the target feature and the location information to obtain the synchronization result includes: performing timestamp synchronization processing on the target feature and the location information to obtain the synchronization result, wherein the timestamps corresponding to the target feature and the location information acquired at the same time are the same.

[0012] Optionally, after performing synchronous matching processing on the target features and the position information to obtain synchronous matching results to achieve real-time tracking of the target human body, the method also includes: displaying the synchronous matching results on an electronic map, wherein the synchronous matching results include the position of the target human body and the dynamic trajectory of the target human body.

[0013] According to another aspect of the present application, a human body tracking device is provided, including: an acquisition unit, used to acquire real-time video data of a target human body through a video surveillance system; a first processing unit, used to process the real-time video data to extract dynamic features of the target human body and obtain target features; a receiving unit, used to receive position information of the target human body sent by a Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target human body; and a second processing unit, used to perform synchronous matching processing on the target features and the position information to obtain a synchronous matching result to achieve real-time tracking of the target human body.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0016] By applying the technical solution of the present application, a human body tracking method is provided. First, real-time video data of a target human body is obtained through a video surveillance system; then, the real-time video data is processed to extract the dynamic features of the target human body and obtain the target features; then, the position information of the target human body sent by the Beidou satellite positioning system is received, wherein the position information at least includes the longitude, latitude and altitude of the target human body; finally, the target features and the position information are synchronously matched to obtain a synchronous matching result to achieve real-time tracking of the target human body. By combining the accuracy of video surveillance and the wide coverage of Beidou satellite positioning technology, a more accurate and real-time human body tracking solution can be provided. The present invention can significantly improve the accuracy and real-time performance of human body tracking. Especially in complex environments and wide-area spaces, the present invention can provide a more reliable tracking effect to meet the needs of various application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a human body tracking method provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic diagram of a human body tracking method provided according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram of a process of receiving location information of a target human body sent by a Beidou satellite positioning system according to an embodiment of the present application is shown;

[0021] Figure 4 A structural block diagram of a human body tracking device provided according to an embodiment of the present application is shown.

[0022] The above drawings include the following reference numerals:

[0023] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] As introduced in the background technology, how to improve the accuracy and efficiency of human body tracking in the prior art, to solve the above problems, the embodiments of the present application provide a human body tracking method, a human body tracking device, a computer-readable storage medium and an electronic device.

[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a human body tracking method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the human body tracking method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a human body tracking method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 2 FIG. 1 is a flow chart of a human body tracking method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0033] Step S201, obtaining real-time video data of a target human body through a video monitoring system;

[0034] Specifically, the real-time video data can be collected by cameras or other video acquisition devices installed in the monitoring area. These devices use image sensors to continuously capture activities in the monitoring area and use high-speed data transmission technology to transmit the video stream to the processing center through the network.

[0035] Step S202, processing the above-mentioned real-time video data to extract the dynamic features of the above-mentioned target human body to obtain target features;

[0036] Specifically, when extracting dynamic features, a variety of algorithms can be used, such as optical flow method, background subtraction method, etc., to capture the motion trajectory and speed changes of the human body. At the same time, functions in computer vision libraries (such as OpenCV) can also be used to achieve more advanced feature extraction.

[0037] Step S203, receiving the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0038] Specifically, in complex environments, such as urban canyons and tunnels, Beidou satellite signals may be interfered with or blocked. In these cases, more reliance can be placed on dynamic features captured by the camera for positioning. At the same time, data from other sensors (such as IMU, radar, etc.) can also be combined to improve positioning accuracy and stability. Figure 3 As shown, the steps of receiving the location information sent by the Beidou satellite positioning system are as follows: input the start and end time of a day, set the first start and end time period, clear the original location information record table, increase the time period in units of 30 minutes, and determine whether the end point of the time period is greater than the input end time point. If so, end the loop, query the record with the largest amount of positioning data, and obtain the location information; otherwise, query the positioning data and insert it into the record table, and repeat the steps of increasing the time period and judging until the end point of the time period is greater than the input end time point.

[0039] Step S204, performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0040] Specifically, the purpose of the above synchronous matching is to maintain the consistency of target features and position information in time and space. This method can be applied to multi-target tracking scenarios, can track multiple target human bodies at the same time, and analyze and display each target independently.

[0041] Through this embodiment, a human body tracking method is provided. First, real-time video data of a target human body is obtained through a video surveillance system; then, the real-time video data is processed to extract the dynamic features of the target human body and obtain the target features; then, the position information of the target human body sent by the Beidou satellite positioning system is received, wherein the position information at least includes the longitude, latitude and altitude of the target human body; finally, the target features and the position information are synchronously matched to obtain a synchronous matching result to achieve real-time tracking of the target human body. By combining the accuracy of video surveillance and the wide coverage of Beidou satellite positioning technology, a more accurate and real-time human body tracking solution can be provided. The present invention can significantly improve the accuracy and real-time performance of human body tracking. Especially in complex environments and wide-area spaces, the present invention can provide a more reliable tracking effect to meet the needs of various application scenarios.

[0042] In the specific implementation process, the above step S201 can be implemented by the following steps: step S2011, using the target detection algorithm to obtain the human body in the monitoring area of ​​the above video monitoring system to obtain the above target human body; step S2012, obtaining the original video data of the above target human body; step S2013, compressing the above original video data to obtain the first video data; step S2014, performing adaptive illumination compensation processing on the above first video data to obtain the second video data; step S2015, performing background elimination processing on the above second video data to obtain the above real-time video data. This method can further improve the accuracy of the above real-time video data obtained.

[0043] Specifically, the target detection algorithm can be trained through machine learning technology, which can identify and lock specific targets from complex backgrounds. In this process, a human target model can be pre-defined, which learns and extracts human features such as shape, outline and movement pattern from a large amount of human image data. In actual operation, the algorithm analyzes the video stream captured by the surveillance camera in real time. It compares each frame of the image with the preset human target model to find the target that matches the model. This process involves complex image processing techniques, including but not limited to color recognition, edge detection, shape matching, etc. Once the algorithm detects a target that matches the preset model in the image, it will immediately lock it and continue to track this target in subsequent video streams. This locking mechanism is achieved by calculating the position change of the target between consecutive frames, ensuring that the target can be accurately locked and tracked even when the target moves or the camera's perspective changes. In addition, the algorithm can automatically lock the target in the monitoring area mainly due to its strong learning and recognition capabilities. Through a large amount of training data, the algorithm can learn how to accurately identify human targets under various environmental conditions and can lock and track them at the first time. This automated locking mechanism not only improves the efficiency of the monitoring system, but also greatly reduces the need for manual intervention. For example, the pedestrian re-identification algorithm (Person Re-identification, referred to as ReID) is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence. It is widely used in the field of security for rapid suspect queries. In ReID technology, feature extraction is a key step. Deep learning models, such as convolutional neural networks, are usually used to extract the features of pedestrians. These features include color, texture, shape, etc., which are used to distinguish different pedestrians. After extracting the features, a similarity matching algorithm is needed to find the image that is most similar to the target pedestrian. Commonly used similarity measurement methods include cosine similarity, Euclidean distance, etc. By setting a suitable threshold, images that are highly similar to the target pedestrian can be screened out.

[0044] Subsequently, the captured video data is encoded in real time using efficient video compression technology to reduce data transmission delays and storage space usage. To cope with light changes and interference from obstructions, adaptive lighting compensation and background elimination technologies are used to ensure that clear and accurate target human video data can be stably captured in various environments. Furthermore, to prevent data loss or damage, data redundancy storage and error recovery mechanisms can be used.

[0045] In order to further improve the accuracy of the extracted target features, the above-mentioned step S202 of the present application can be implemented by the following steps: step S2021, using a computer vision algorithm to obtain the motion trajectory of the above-mentioned target human body, the speed of the above-mentioned target human body and the acceleration of the above-mentioned target human body; step S2022, performing multimodal data fusion on the above-mentioned motion trajectory, the above-mentioned speed and the above-mentioned acceleration to obtain the above-mentioned target features.

[0046] In practical applications, in the process of extracting dynamic features, we may face problems such as light changes, obstructions, and the diversity of human postures. We can use adaptive thresholds, multimodal data fusion and other technical means to deal with the above problems. In order to improve accuracy and stability, we can combine multiple data sources (such as infrared sensors, sound data, etc.) for multimodal data fusion to more comprehensively describe the dynamic characteristics of the human body. In addition, the accuracy of feature extraction can also be improved through continuous learning and optimization. For example, deep learning technology can be used to train the model so that it can more accurately identify and extract the dynamic characteristics of the human body. At the same time, the model is regularly updated and optimized to adapt to changes in different scenarios and environments.

[0047] The above-mentioned synchronous matching result includes a matching result and a synchronization result. The above-mentioned step S204 can also be implemented in other ways, for example: step S2041, matching the above-mentioned target features and the above-mentioned location information to obtain the above-mentioned matching result; step S2042, synchronizing the above-mentioned target features and the above-mentioned location information to obtain the above-mentioned synchronization result. By combining the dynamic features captured by the camera with the precise positioning information provided by the Beidou satellite, the system can achieve more accurate and real-time target tracking and positioning. This can not only improve the accuracy of positioning, but also help to achieve more efficient navigation and obstacle avoidance, thereby further improving driving safety and efficiency.

[0048] In some embodiments, the above-mentioned matching result includes matching location information, and the above-mentioned step S2041 can be specifically implemented by the following steps: step S20411, calculating the time difference between the above-mentioned target feature and the above-mentioned location information, the speed difference between the above-mentioned target feature and the above-mentioned location information, and the direction difference between the above-mentioned target feature and the above-mentioned location information; step S20412, determining whether the above-mentioned time difference is less than the time difference threshold, whether the above-mentioned speed difference is less than the speed difference threshold, and whether the above-mentioned direction difference is less than the direction difference threshold; step S20413, when the above-mentioned time difference is less than the above-mentioned time difference threshold, the above-mentioned speed difference is less than the above-mentioned speed difference threshold, and the above-mentioned direction difference is less than the above-mentioned direction difference threshold, determining that the corresponding above-mentioned location information is the matching location information. This method can further improve the matching accuracy between the above-mentioned target feature and the above-mentioned location information.

[0049] Specifically, the matching algorithm compares and associates the target features and the location information. In practical applications, the best matching point can be found by calculating factors such as the time difference, speed difference, and direction difference between the target captured by the camera and the satellite positioning information.

[0050] In another embodiment, step S2042 can be implemented by the following steps: Step S20421, performing timestamp synchronization processing on the target feature and the location information to obtain the synchronization result, wherein the timestamps corresponding to the target feature and the location information obtained at the same time are the same. This method can further improve the synchronization accuracy between the target feature and the location information.

[0051] Specifically, since the data update frequencies of the camera and Beidou satellite may be different, there may be a problem of data asynchrony. The problem of data asynchrony is solved by introducing a timestamp synchronization mechanism and data buffering technology. At the same time, the algorithm can also be optimized to reduce processing delays.

[0052] After step S204, the method further includes: step S205, displaying the synchronization matching result on an electronic map, wherein the synchronization matching result includes the position of the target human body and the dynamic track of the target human body. This method can further improve the visibility of human body tracking.

[0053] Specifically, first, the system will integrate the matched and synchronized dynamic features with the Beidou satellite positioning information. This means combining the dynamic data of the target human body captured by the camera with the geographic location data provided by the satellite to form a comprehensive and real-time target information set. Based on the integrated data, the system will perform trajectory prediction. The algorithm analyzes the historical motion trajectory and current speed, direction and other information of the target to predict its possible future motion path. At the same time, the system will continuously receive and process new data to update the position and status of the target in real time. Based on the results of trajectory prediction, the system will continue to track the position of the target human body. This includes marking the position of the target in real time in the video stream, and displaying the real-time trajectory and motion status of the target through the interface. During the tracking process, the system will continuously receive and process feedback from the user. For example, if the user finds that the tracking is deviated or wrong, manual adjustments can be made in time. The system will also optimize and adjust itself based on these feedbacks to improve the accuracy and stability of tracking. When the dynamic features or location information of the target human body triggers the preset conditions, an early warning signal will be automatically issued.

[0054] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the human body tracking method of the present application will be described in detail below in conjunction with specific embodiments.

[0055] Example 1

[0056] This embodiment relates to a human body tracking method based on a COCO format dataset, comprising the following steps:

[0057] Step S11: Dataset conversion, using the CrowdHuman dataset, which is a widely used human detection dataset containing more than 15,000 images annotated with human instances. First, this dataset needs to be converted to COCO format to facilitate subsequent training and detection. The conversion process includes defining conversion functions, processing images and annotation data, and generating json files that meet the COCO format requirements.

[0058] Step S12: Human body detection algorithm. On the converted data set, a deep learning algorithm can be used for human body detection. These algorithms are usually based on convolutional neural networks and learn the human body features in the image through training. During the training process, the network will continuously adjust its parameters to minimize the difference between the predicted results and the actual annotations.

[0059] Step S13: Detection effect evaluation, using standard evaluation indicators (such as accuracy, recall, F1 score, etc.) to evaluate the detection effect. These indicators help to understand the performance of the algorithm and guide subsequent algorithm optimization.

[0060] Example 2

[0061] This embodiment relates to a human body tracking method based on Camshift and Kalman filter algorithm, comprising the following steps:

[0062] Step S21: Moving human body detection, first, detecting moving human bodies in the input video image. This can be achieved by background subtraction, frame difference method, etc. These methods can extract dynamic areas in the video frame, that is, moving human bodies.

[0063] Step S22: Camshift algorithm: After detecting a moving human body, the Camshift algorithm is used for tracking. The Camshift algorithm is an extension of the Mean-Shift algorithm and can adaptively adjust the size and position of the tracking window to adapt to the size and position changes of the target human body.

[0064] Step S23: In order to further improve the tracking stability, the Kalman filter algorithm can be used to smooth the tracking results. Kalman filter is an algorithm for linear dynamic system state estimation, which can predict the target position of the current frame based on the tracking results of the previous frame and the observation data of the current frame.

[0065] Embodiment 3:

[0066] This embodiment relates to a human body tracking system based on multi-dimensional information, including:

[0067] Multi-dimensional information collection module: The system tracks based on different dimensional information such as human skeleton, facial features, human behavior and color features. By collecting these multi-dimensional information, the characteristics of the target human body can be more comprehensively described, improving the accuracy of tracking.

[0068] Feature fusion and processing module: fuses and processes the collected multi-dimensional information. For example, the movement direction and posture information of the human body can be extracted using the skeleton data; the identity of the target person can be identified through the facial features; and more accurate tracking can be performed by combining the human behavior and color feature information.

[0069] Efficient auxiliary tracking shooting module: Based on the processed multi-dimensional information, the system can achieve efficient auxiliary tracking shooting. Whether in a static or moving environment, the system can accurately lock the target human body and perform continuous tracking shooting.

[0070] The embodiment of the present application also provides a human body tracking device. It should be noted that the human body tracking device of the embodiment of the present application can be used to execute the human body tracking method provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0071] The human body tracking device provided in the embodiments of the present application is introduced below.

[0072] Figure 4 Schematic diagram of a human body tracking device according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0073] An acquisition unit 10 is used to acquire real-time video data of a target human body through a video monitoring system;

[0074] Specifically, the real-time video data can be collected by cameras or other video acquisition devices installed in the monitoring area. These devices use image sensors to continuously capture activities in the monitoring area and use high-speed data transmission technology to transmit the video stream to the processing center through the network.

[0075] The first processing unit 20 is used to process the real-time video data to extract the dynamic features of the target human body and obtain the target features;

[0076] Specifically, when extracting dynamic features, a variety of algorithms can be used, such as optical flow method, background subtraction method, etc., to capture the motion trajectory and speed changes of the human body. At the same time, functions in computer vision libraries (such as OpenCV) can also be used to achieve more advanced feature extraction.

[0077] The receiving unit 30 is used to receive the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0078] Specifically, in complex environments, such as urban canyons and tunnels, Beidou satellite signals may be interfered with or blocked. In these cases, more reliance can be placed on dynamic features captured by the camera for positioning. At the same time, data from other sensors (such as IMU, radar, etc.) can also be combined to improve positioning accuracy and stability. Figure 3 As shown, the steps of receiving the location information sent by the Beidou satellite positioning system are as follows: input the start and end time of a day, set the first start and end time period, clear the original location information record table, increase the time period in units of 30 minutes, and determine whether the end point of the time period is greater than the input end time point. If so, end the loop, query the record with the largest amount of positioning data, and obtain the location information; otherwise, query the positioning data and insert it into the record table, and repeat the steps of increasing the time period and judging until the end point of the time period is greater than the input end time point.

[0079] The second processing unit 40 is used to perform synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0080] Specifically, the purpose of the above synchronous matching is to maintain the consistency of target features and position information in time and space. This method can be applied to multi-target tracking scenarios, can track multiple target human bodies at the same time, and analyze and display each target independently.

[0081] Through this embodiment, a human body tracking device is provided, wherein an acquisition unit acquires real-time video data of a target human body through a video surveillance system; a first processing unit processes the real-time video data to extract dynamic features of the target human body and obtain target features; a receiving unit receives the position information of the target human body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target human body; a second processing unit performs synchronous matching processing on the target features and the position information to obtain a synchronous matching result to achieve real-time tracking of the target human body. By combining the accuracy of video surveillance and the wide coverage of Beidou satellite positioning technology, a more accurate and real-time human body tracking solution can be provided. The present invention can significantly improve the accuracy and real-time performance of human body tracking. Especially in complex environments and wide-area spaces, the present invention can provide a more reliable tracking effect to meet the needs of various application scenarios.

[0082] In the specific implementation process, the acquisition unit includes a first acquisition module, a second acquisition module, a first processing module, a second processing module and a third processing module, wherein the first acquisition module is used to use a target detection algorithm to acquire a human body in the monitoring area of ​​the video surveillance system to obtain the target human body; the second acquisition module is used to acquire the original video data of the target human body; the first processing module is used to compress the original video data to obtain the first video data; the second processing module is used to perform adaptive illumination compensation processing on the first video data to obtain the second video data; the third processing module is used to perform background elimination processing on the second video data to obtain the real-time video data. The device can further improve the accuracy of the acquired real-time video data.

[0083] Specifically, the target detection algorithm can be trained through machine learning technology, which can identify and lock specific targets from complex backgrounds. In this process, a human target model can be pre-defined, which learns and extracts human features such as shape, outline and movement pattern from a large amount of human image data. In actual operation, the algorithm analyzes the video stream captured by the surveillance camera in real time. It compares each frame of the image with the preset human target model to find the target that matches the model. This process involves complex image processing techniques, including but not limited to color recognition, edge detection, shape matching, etc. Once the algorithm detects a target that matches the preset model in the image, it will immediately lock it and continue to track this target in subsequent video streams. This locking mechanism is achieved by calculating the position change of the target between consecutive frames, ensuring that the target can be accurately locked and tracked even when the target moves or the camera's perspective changes. In addition, the algorithm can automatically lock the target in the monitoring area mainly due to its strong learning and recognition capabilities. Through a large amount of training data, the algorithm can learn how to accurately identify human targets under various environmental conditions and can lock and track them at the first time. This automated locking mechanism not only improves the efficiency of the monitoring system, but also greatly reduces the need for manual intervention. For example, the pedestrian re-identification algorithm (Person Re-identification, referred to as ReID) is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence. It is widely used in the field of security for rapid suspect queries. In ReID technology, feature extraction is a key step. Deep learning models, such as convolutional neural networks, are usually used to extract the features of pedestrians. These features include color, texture, shape, etc., which are used to distinguish different pedestrians. After extracting the features, a similarity matching algorithm is needed to find the image that is most similar to the target pedestrian. Commonly used similarity measurement methods include cosine similarity, Euclidean distance, etc. By setting a suitable threshold, images that are highly similar to the target pedestrian can be screened out.

[0084] Subsequently, the captured video data is encoded in real time using efficient video compression technology to reduce data transmission delays and storage space usage. To cope with light changes and interference from obstructions, adaptive lighting compensation and background elimination technologies are used to ensure that clear and accurate target human video data can be stably captured in various environments. Furthermore, to prevent data loss or damage, data redundancy storage and error recovery mechanisms can be used.

[0085] In order to further improve the accuracy of the extracted target features, the above-mentioned first processing unit of the present application includes a third acquisition module and a fourth processing module, wherein the third acquisition module is used to adopt a computer vision algorithm to obtain the motion trajectory of the above-mentioned target human body, the speed of the above-mentioned target human body and the acceleration of the above-mentioned target human body; the fourth processing module is used to perform multimodal data fusion on the above-mentioned motion trajectory, the above-mentioned speed and the above-mentioned acceleration to obtain the above-mentioned target features.

[0086] In practical applications, in the process of extracting dynamic features, we may face problems such as light changes, obstructions, and the diversity of human postures. We can use adaptive thresholds, multimodal data fusion and other technical means to deal with the above problems. In order to improve accuracy and stability, we can combine multiple data sources (such as infrared sensors, sound data, etc.) for multimodal data fusion to more comprehensively describe the dynamic characteristics of the human body. In addition, the accuracy of feature extraction can also be improved through continuous learning and optimization. For example, deep learning technology can be used to train the model so that it can more accurately identify and extract the dynamic characteristics of the human body. At the same time, the model is regularly updated and optimized to adapt to changes in different scenarios and environments.

[0087] The above-mentioned synchronous matching result includes a matching result and a synchronization result, and the above-mentioned second processing unit includes a fifth processing module and a sixth processing module, wherein the fifth processing module is used to match the above-mentioned target features and the above-mentioned position information to obtain the above-mentioned matching result; the sixth processing module is used to synchronize the above-mentioned target features and the above-mentioned position information to obtain the above-mentioned synchronization result. By combining the dynamic features captured by the camera with the precise positioning information provided by the Beidou satellite, the system can achieve more accurate and real-time target tracking and positioning. This can not only improve the accuracy of positioning, but also help to achieve more efficient navigation and obstacle avoidance, thereby further improving driving safety and efficiency.

[0088] In some embodiments, the matching result includes matching location information, and the fifth processing module includes a calculation submodule, a first determination submodule, and a second determination submodule, wherein the calculation submodule is used to calculate the time difference between the target feature and the location information, the speed difference between the target feature and the location information, and the direction difference between the target feature and the location information; the first determination submodule is used to determine whether the time difference is less than the time difference threshold, whether the speed difference is less than the speed difference threshold, and whether the direction difference is less than the direction difference threshold; the second determination submodule is used to determine that the corresponding location information is the matching location information when the time difference is less than the time difference threshold, the speed difference is less than the speed difference threshold, and the direction difference is less than the direction difference threshold. The device can further improve the matching accuracy between the target feature and the location information.

[0089] Specifically, the matching algorithm compares and associates the target features and the location information. In practical applications, the best matching point can be found by calculating factors such as the time difference, speed difference, and direction difference between the target captured by the camera and the satellite positioning information.

[0090] In another embodiment, the sixth processing module includes a processing submodule for performing timestamp synchronization processing on the target feature and the location information to obtain the synchronization result, wherein the timestamps corresponding to the target feature and the location information obtained at the same time are the same. The device can further improve the synchronization accuracy between the target feature and the location information.

[0091] Specifically, since the data update frequencies of the camera and Beidou satellite may be different, there may be a problem of data asynchrony. The problem of data asynchrony is solved by introducing a timestamp synchronization mechanism and data buffering technology. At the same time, the algorithm can also be optimized to reduce processing delays.

[0092] The device further includes a display unit for displaying the synchronization matching result on an electronic map, wherein the synchronization matching result includes the position of the target human body and the dynamic track of the target human body. The device can further improve the visibility of human body tracking.

[0093] Specifically, first, the system will integrate the matched and synchronized dynamic features with the Beidou satellite positioning information. This means combining the dynamic data of the target human body captured by the camera with the geographic location data provided by the satellite to form a comprehensive and real-time target information set. Based on the integrated data, the system will perform trajectory prediction. The algorithm analyzes the historical motion trajectory and current speed, direction and other information of the target to predict its possible future motion path. At the same time, the system will continuously receive and process new data to update the position and status of the target in real time. Based on the results of trajectory prediction, the system will continue to track the position of the target human body. This includes marking the position of the target in real time in the video stream, and displaying the real-time trajectory and motion status of the target through the interface. During the tracking process, the system will continuously receive and process feedback from the user. For example, if the user finds that the tracking is deviated or wrong, manual adjustments can be made in time. The system will also optimize and adjust itself based on these feedbacks to improve the accuracy and stability of tracking. When the dynamic features or location information of the target human body triggers the preset conditions, an early warning signal will be automatically issued.

[0094] The human body tracking device includes a processor and a memory. The acquisition unit, the first processing unit, the receiving unit, and the second processing unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0095] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and human body tracking can be performed by adjusting kernel parameters.

[0096] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0097] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the human body tracking method.

[0098] Specifically, the human body tracking method includes:

[0099] Step S201, obtaining real-time video data of a target human body through a video monitoring system;

[0100] Specifically, the real-time video data can be collected by cameras or other video acquisition devices installed in the monitoring area. These devices use image sensors to continuously capture activities in the monitoring area and use high-speed data transmission technology to transmit the video stream to the processing center through the network.

[0101] Step S202, processing the above-mentioned real-time video data to extract the dynamic features of the above-mentioned target human body to obtain target features;

[0102] Specifically, when extracting dynamic features, a variety of algorithms can be used, such as optical flow method, background subtraction method, etc., to capture the motion trajectory and speed changes of the human body. At the same time, functions in computer vision libraries (such as OpenCV) can also be used to achieve more advanced feature extraction.

[0103] Step S203, receiving the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0104] Specifically, in complex environments, such as urban canyons and tunnels, Beidou satellite signals may be interfered with or blocked. In these cases, more reliance can be placed on dynamic features captured by the camera for positioning. At the same time, data from other sensors (such as IMU, radar, etc.) can also be combined to improve positioning accuracy and stability. Figure 3 As shown, the steps of receiving the location information sent by the Beidou satellite positioning system are as follows: input the start and end time of a day, set a start and end time period, clear the original location information record table, increase the time period in units of 30 minutes, and judge whether the end point of the time period is greater than the input end time point. If so, end the loop, query the record with the largest amount of positioning data, and obtain the location information; otherwise, query the positioning data and insert it into the record table, and repeat the steps of increasing the time period and judging until the end point of the time period is greater than the input end time point.

[0105] Step S204, performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0106] Specifically, the purpose of the above synchronous matching is to maintain the consistency of target features and position information in time and space. This method can be applied to multi-target tracking scenarios, can track multiple target human bodies at the same time, and analyze and display each target independently.

[0107] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the human body tracking method is executed when the program is run.

[0108] Specifically, the human body tracking method includes:

[0109] Step S201, obtaining real-time video data of a target human body through a video monitoring system;

[0110] Specifically, the real-time video data can be collected by cameras or other video acquisition devices installed in the monitoring area. These devices use image sensors to continuously capture activities in the monitoring area and use high-speed data transmission technology to transmit the video stream to the processing center through the network.

[0111] Step S202, processing the above-mentioned real-time video data to extract the dynamic features of the above-mentioned target human body to obtain target features;

[0112] Specifically, when extracting dynamic features, a variety of algorithms can be used, such as optical flow method, background subtraction method, etc., to capture the motion trajectory and speed changes of the human body. At the same time, functions in computer vision libraries (such as OpenCV) can also be used to achieve more advanced feature extraction.

[0113] Step S203, receiving the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0114] Specifically, in complex environments, such as urban canyons and tunnels, Beidou satellite signals may be interfered with or blocked. In these cases, more reliance can be placed on dynamic features captured by the camera for positioning. At the same time, data from other sensors (such as IMU, radar, etc.) can also be combined to improve positioning accuracy and stability. Figure 3 As shown, the steps of receiving the location information sent by the Beidou satellite positioning system are as follows: input the start and end time of a day, set a start and end time period, clear the original location information record table, increase the time period in units of 30 minutes, and judge whether the end point of the time period is greater than the input end time point. If so, end the loop, query the record with the largest amount of positioning data, and obtain the location information; otherwise, query the positioning data and insert it into the record table, and repeat the steps of increasing the time period and judging until the end point of the time period is greater than the input end time point.

[0115] Step S204, performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0116] Specifically, the purpose of the above synchronous matching is to maintain the consistency of target features and position information in time and space. This method can be applied to multi-target tracking scenarios, can track multiple target human bodies at the same time, and analyze and display each target independently.

[0117] An embodiment of the present invention provides a device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0118] Step S201, obtaining real-time video data of a target human body through a video monitoring system;

[0119] Step S202, processing the above-mentioned real-time video data to extract the dynamic features of the above-mentioned target human body to obtain target features;

[0120] Step S203, receiving the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0121] Step S204, performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0122] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0123] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0124] Step S201, obtaining real-time video data of a target human body through a video monitoring system;

[0125] Step S202, processing the above-mentioned real-time video data to extract the dynamic features of the above-mentioned target human body to obtain target features;

[0126] Step S203, receiving the position information of the target body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target body;

[0127] Step S204, performing synchronous matching processing on the target features and the position information to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

[0128] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0134] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0135] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0137] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0138] 1) The human body tracking method of the present application first obtains real-time video data of the target human body through a video surveillance system; then processes the real-time video data to extract the dynamic features of the target human body and obtain the target features; then receives the location information of the target human body sent by the Beidou satellite positioning system, wherein the location information at least includes the longitude, latitude and altitude of the target human body; finally, performs synchronous matching processing on the target features and the location information to obtain a synchronous matching result to achieve real-time tracking of the target human body. By combining the accuracy of video surveillance and the wide coverage of Beidou satellite positioning technology, a more accurate and real-time human body tracking solution can be provided. The present invention can significantly improve the accuracy and real-time performance of human body tracking. Especially in complex environments and wide-area spaces, the present invention can provide a more reliable tracking effect to meet the needs of various application scenarios.

[0139] 2) In the human body tracking device of the present application, the acquisition unit acquires the real-time video data of the target human body through the video monitoring system; the first processing unit processes the real-time video data to extract the dynamic features of the target human body and obtain the target features; the receiving unit receives the position information of the target human body sent by the Beidou satellite positioning system, wherein the position information at least includes the longitude, latitude and altitude of the target human body; the second processing unit performs synchronous matching processing on the target features and the position information to obtain the synchronous matching results to achieve real-time tracking of the target human body. By combining the accuracy of video monitoring and the wide coverage of Beidou satellite positioning technology, a more accurate and real-time human body tracking solution can be provided. The present invention can significantly improve the accuracy and real-time performance of human body tracking. Especially in complex environments and wide-area spaces, the present invention can provide a more reliable tracking effect to meet the needs of various application scenarios.

[0140] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A human body tracking method, characterized in that: include: Acquire real-time video data of the target human body through a video surveillance system; Processing the real-time video data to extract dynamic features of the target human body to obtain target features; Receiving the location information of the target human body sent by the Beidou satellite positioning system, wherein the location information at least includes the longitude, latitude and altitude of the target human body; The target feature and the position information are synchronously matched to obtain a synchronous matching result, so as to achieve real-time tracking of the target human body.

2. The method according to claim 1, characterized in that The real-time video data of the target human body is obtained through the video surveillance system, including: A target detection algorithm is used to obtain a human body within a monitoring area of ​​the video monitoring system to obtain the target human body; Acquire original video data of the target human body; Compressing the original video data to obtain first video data; Performing adaptive illumination compensation processing on the first video data to obtain second video data; Background elimination processing is performed on the second video data to obtain the real-time video data.

3. The method according to claim 1, characterized in that Processing the real-time video data to extract dynamic features of the target human body to obtain target features includes: Using a computer vision algorithm to obtain the motion trajectory of the target human body, the speed of the target human body, and the acceleration of the target human body; Multimodal data fusion is performed on the motion trajectory, the speed, and the acceleration to obtain the target feature.

4. The method according to claim 1, characterized in that: The synchronous matching result includes a matching result and a synchronization result. The target feature and the position information are synchronously matched to obtain a synchronous matching result to achieve real-time tracking of the target human body, including: Performing matching processing on the target feature and the location information to obtain the matching result; The target feature and the position information are synchronously processed to obtain the synchronization result.

5. The method according to claim 4, characterized in that The matching result includes matching position information, and matching processing is performed on the target feature and the position information to obtain the matching result, including: Calculating a time difference between the target feature and the position information, a speed difference between the target feature and the position information, and a direction difference between the target feature and the position information; determining whether the time difference is less than a time difference threshold, whether the speed difference is less than a speed difference threshold, and whether the direction difference is less than a direction difference threshold; When the time difference is smaller than the time difference threshold, the speed difference is smaller than the speed difference threshold, and the direction difference is smaller than the direction difference threshold, the corresponding position information is determined to be matching position information.

6. The method according to claim 4, characterized in that The target feature and the position information are synchronously processed to obtain the synchronization result, including: The target feature and the location information are synchronized by timestamps to obtain the synchronization result, wherein the target feature and the location information acquired at the same time have the same timestamp.

7. The method according to claim 1, characterized in that After performing synchronous matching processing on the target feature and the position information to obtain a synchronous matching result to achieve real-time tracking of the target human body, the method further includes: The synchronous matching result is displayed on an electronic map, wherein the synchronous matching result includes the position of the target human body and the dynamic trajectory of the target human body.

8. A human body tracking device, characterized in that: include: An acquisition unit, used for acquiring real-time video data of a target human body through a video monitoring system; A first processing unit is used to process the real-time video data to extract dynamic features of the target human body to obtain target features; A receiving unit, configured to receive the location information of the target human body sent by the Beidou satellite positioning system, wherein the location information at least includes the longitude, latitude and altitude of the target human body; The second processing unit is used to perform synchronous matching processing on the target feature and the position information to obtain a synchronous matching result to achieve real-time tracking of the target human body.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images