Real-time high-speed target identification tracking scheme based on localized artificial intelligence framework

Abstract

According to the real-time high-speed target identification and tracking scheme based on the localization artificial intelligence framework, rapid target detection and accurate tracking are achieved by combining target identification and tracking technologies, a system can automatically restart an identification network for repositioning when a target is lost, a user is supported to manually select target tracking, and the tracking efficiency is improved. A self-developed long-time tracking algorithm is adopted, the method is not limited by target categories, multi-channel videos are processed at the front end, the use of computing resources is optimized, hardware vision preprocessing and network reasoning parts are optimized, and the processing speed and efficiency are improved. The system provides a flexible output mode and is suitable for various application scenes.

Description

Technical Field

[0001] The present invention relates to the field of computer vision and artificial intelligence technology, and specifically to a real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework. Background Art

[0002] Artificial intelligence target recognition and tracking technology is one of the important research directions in the field of modern computer vision. With the rapid development of deep learning and big data technology, AI has made significant progress in image and video processing. Target recognition and tracking technology aims to automatically detect, identify and continuously track specific targets in videos or image sequences through computer vision algorithms. Traditional target recognition and tracking methods rely on manually designed feature extraction and classifiers, which often perform poorly when dealing with complex scenes and changing environments. In recent years, models such as convolutional neural networks and recurrent neural networks based on deep learning have demonstrated excellent performance in target recognition and tracking tasks. By training large-scale neural network models, AI systems can automatically learn features in images and achieve high-precision target detection and classification. In terms of target tracking, deep learning combines multi-target tracking and single-target tracking technology, which can maintain continuous tracking of targets in complex backgrounds and occlusions. Common tracking algorithms include correlation filters, twin networks, and neural networks. Network and reinforcement learning-based tracking methods. These algorithms ensure accurate tracking of targets in dynamic environments by continuously updating the target's location information. AI target recognition and tracking technology has broad application prospects in many fields. For example, in intelligent monitoring systems, it can detect and track suspicious people or objects in real time to improve public safety. In the field of autonomous driving, it can identify and track dynamic targets such as pedestrians and vehicles on the road to improve driving safety. In drone navigation and robot vision, it can achieve autonomous obstacle avoidance and target tracking, and enhance autonomy and intelligence. In summary, artificial intelligence target recognition and tracking technology is continuously promoting the development of computer vision technology by combining advanced deep learning algorithms and big data analysis, and is playing an increasingly important role in all walks of life.

[0003] However, the existing target recognition and tracking system framework has the following problems: the target detection speed cannot meet the requirements and the target tracking accuracy is poor. In addition, when the system target is lost, it usually requires manual repositioning, the degree of automation is low, and it is easily restricted by the target category. Therefore, it is necessary to design corresponding technical solutions to solve the existing technical problems. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework, which solves the technical problems that the target detection speed cannot meet the requirements and the target tracking accuracy is poor. In addition, when the system target is lost, manual repositioning is usually required, the degree of automation is low, and it is easily restricted by the target category.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework, including two network frameworks of target recognition and target tracking. The working logic is to use the recognition network to trigger the tracking network. When the recognition network recognizes a trusted target, it quickly switches to the tracking network to lock the target and subsequently accurately track and predict the track. When the target is lost from the field of view, the tracking stops. At this time, the recognition network is reactivated to search for suspected targets in the field of view, manually select the target in the field of view, activate the tracking network to lock the target and subsequently accurately track and predict the track. When the target is lost from the field of view, the tracking stops to prevent mistracking. A self-developed long-term tracking algorithm is used. The long-term tracker will During the tracking process, the target is deeply extracted for features. When the target disappears and re-enters the field of view, it has a persistent and controllable re-capture capability. After the front-end multi-channel video image input, the target recognition and target tracking networks are switched in time, activated and scheduled with each other, and the hardware visual preprocessing core VPC is called to complete the operations of cutout, scaling, overlay, splicing, histogram statistics, color remapping, format conversion, Remap transformation, and filtering image processing. The preprocessed data is sent to the memory buffer of the NPU for subsequent reasoning. In the network reasoning part, after the reasoning is completed, it is output in two forms, which are the coordinates of the center point of the identified target and the coordinate sequence of the identification box range. The system superimposes the reasoning results into the video stream encoding output.

[0006] As a preferred embodiment of the present invention, the target recognition and target tracking networks are in a time-sharing serial working mode, and the resources and time of each working module network are independent. After the pre-processing is completed, they are sent to the NPU for model reasoning.

[0007] As a preferred embodiment of the present invention, the software execution process of the target identification and tracking solution is that the UART / ETH control thread continuously monitors the serial port and network port data, and is responsible for processing the sending and receiving tasks of the serial port or network port. When the UART / ETH control thread receives the instruction, it will automatically parse the instruction, convert the instruction information into the corresponding tracker working status and synchronize it to the Decoder module. The subsequent video processing related modules perform corresponding processing according to the status information. When the detector and tracker report the detection and tracking information to the UART / ETH control thread, the UART / ETH control thread will process the reported information according to the instruction protocol and send it to the external master control immediately after processing.

[0008] As a preferred embodiment of the present invention, the target recognition and tracking algorithm, first, the Decoder module will decode the input video in a single frame, the decoded image will be identified, tracked or directly output according to the main control instruction, the processed image will be superimposed with display information according to the protocol requirements, the OSD module outputs the image and sends it to the encoder for image encoding and sends it to the external main control through the rtsp network video stream.

[0009] As a preferred embodiment of the present invention, the target recognition thread algorithm includes two threads: recognition pre-processing, target recognition and recognition post-processing. The target recognition thread performs pre-processing on the input current frame image to meet the requirements of the recognition network input, and sends it to the recognition thread for model reasoning to obtain image output. The recognition post-processing thread is responsible for matching the target ID, determining the target category, and outputting the target recognition accuracy based on the network output and the timeline information. If the target is lost and re-enters the field of view within 3 seconds, the previous ID can be automatically matched, and it also has the function of counting the number of targets of different categories.

[0010] As a preferred embodiment of the present invention, the tracking algorithm thread is responsible for processing the template extraction and calculating the search area after the tracking instruction is issued. After determining the tracking template, the template and the search area are sent to the tracking network for model reasoning, and the position of the tracking target and the confidence of the tracking target are output.

[0011] As a preferred embodiment of the present invention, the tracking post-processing thread function is to judge the current tracker state and dynamically update the tracking template, and its main logic is: if the tracking output confidence is greater than the set threshold, the tracking is considered normal; if the tracking output confidence is less than the set threshold, the target is considered lost or blocked.

[0012] As a preferred embodiment of the present invention, the specific states of the algorithm execution logic during tracking are divided into the following three states: normal tracking, tracking occlusion and tracking loss.

[0013] Compared with the prior art, the present invention has the following beneficial effects:

[0014] 1. The present invention provides a real-time, high-speed target recognition and tracking solution based on a domestic artificial intelligence framework, including an artificial intelligence-based target recognition function, a target tracking function, and an automatic target recognition and tracking function. The deployment method is fully designed and optimized during the terminal-side deployment. Combined with the optimization of the Ascend CANN parallel asynchronous bus computing architecture in parallel computing, in the implementation process, the three different levels of the underlying API interfaces based on the Ascend MindSpore framework are deeply implemented to implement the time-sharing switching deployment and scheduling of the two processes of target recognition and tracking. The algorithm network is strictly trained and reasoned, mixed-progress training, and tuning and debugging are performed through the high-level API to control the execution process of the entire network and realize the training and reasoning of the neural network. Secondly, the neural network is flexibly constructed and the execution process is controlled through the middle-level API, the model algorithm logic is quickly realized, and the network ontology, LOSS function, and Optimizer interface are used to add loss functions and optimization methods to the neural network model. Finally, mathematical and logical operations such as tensor definition, operator calculation, and self-differentiation are implemented through the underlying API, which greatly improves the intelligence of target recognition and tracking.

[0015] 2. This solution realizes the concurrent and independent operation modes of the recognition network and the tracking network through the fast scheduling of multi-threaded asynchronous neural networks. It has low inference time and is suitable for rapid deployment. It can process multiple video streams of different spectral images at the same time, and perform recognition and tracking network inference on each video stream at the same time. It can automatically identify targets according to user needs and automatically switch to the continuous tracking process of the current target without the intervention of additional operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is the overall architecture diagram of the solution of the present invention;

[0017] Figure 2 This is a schematic diagram of multi-threaded pipeline scheduling of the present invention;

[0018] Figure 3 It is a schematic diagram of the software execution flow of the present invention;

[0019] Figure 4 This is a logic diagram of the automatic identification and tracking function flow of the present invention;

[0020] Figure 5 It is the effect diagram of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1-5 The present invention provides a real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework. The technical solution is as follows: The AI ​​calculation of the present invention includes two network frameworks: target recognition and target tracking. The core working logic is as follows: 1. Use the recognition network to trigger the tracking network. When the recognition network recognizes a trusted target, it quickly switches to the tracking network to lock the target and subsequently accurately track it, predict the track, etc. When the target is lost from the field of view, the tracking stops to prevent mistracking. At this time, the recognition network is reactivated to search for suspected targets in the field of view; 2. Manually select the target in the field of view, activate the tracking network to lock the target and subsequently accurately track it, predict the track, etc. When the target is lost from the field of view, the tracking stops to prevent mistracking; 3. Self-developed long-term tracking algorithm, with powerful anti-loss and re-capture functions, without any restrictions on target categories, truly achieving that everything can be tracked, the long-term tracker will perform deep feature extraction on the target during the tracking process, and has a persistent and controllable re-capture capability when the target disappears and re-enters the field of view, making up for the defect that the recognition algorithm can only re-capture targets of specific categories.

[0023] After the front-end multi-channel video images are input, they are switched in time by the target recognition and target tracking networks, which activate and schedule each other, saving computing resources and the power consumption of the network always running in the foreground. Calling the powerful hardware visual preprocessing core can quickly complete image processing operations such as cutout, scaling, overlay, splicing, histogram statistics, color remapping, format conversion, Remap transformation, filtering, etc. (the maximum resolution supported is 8192*8192, and the maximum processing time of a single operation at the maximum resolution is 5ms), which greatly reduces the time consumption of the preprocessing stage (the actual measurement is that 1080P simultaneously performs cutout, scaling, filling and format conversion in only 3ms). The preprocessed data is sent to the memory buffer of the NPU for subsequent reasoning. For the network reasoning part, this solution has specially optimized the training framework and underlying scheduling at the training layer and scheduling layer. The reasoning time is reduced by 20% compared with the unoptimized one. The time consumption of the model is as follows (small model: 3-4ms, medium model: 7-8ms, large model: 12-13ms). The small model of the recognition algorithm of this solution has 3 times the parameters of the mainstream model used in HiSilicon 3599 / 3403, and the reasoning time is only 50% of that, which has a huge advantage in reasoning speed. After the reasoning is completed, it is output in two forms. Users can choose to directly transmit the reasoning results to the backend according to the needs of the backend platform, that is, the coordinates of the center point of the identified target and the coordinate sequence of the recognition frame range (not time-consuming), or the system can superimpose the reasoning results into the video stream encoding output (1ms). Therefore, the maximum total time consumption of the recognition network is 18ms, thanks to the pipeline scheduling of software threads, such as Figure 2 As shown, theoretically, when using a small model, it can meet the real-time reasoning process at a single-channel 1080P 50Hz (using a large model) -200Hz (using a small model) frame rate.

[0024] The complexity of the tracking network is higher than that of the recognition network. However, since the working logic of the present invention is that the recognition network activates the tracking network, the two networks are in a time-sharing serial working mode. The resources and time of each working module network are independent. The current pre-processing time of the tracking network is basically the same as that of the recognition network. After the pre-processing is completed, it is sent to the NPU for model inference. The present invention has a variety of inference algorithms. The algorithm time fluctuates according to the template size. The specific time consumption is as follows: 1. High-precision short-time tracking algorithm (small model: 1-3ms, large model: 8ms-10ms, when the target is lost, it can only rely on the recognition module to recapture a specific category), 2. Long-time tracking algorithm (small model: 1-3ms, medium model: 4-6ms, large model 8-10ms, with Lost recapture capability, does not rely on recognition algorithms, and can recapture any category). At the same time, both algorithms can automatically update the target template during the tracking process (it takes 1-2ms to enable the update), and have the function of adaptively selecting the target template. After the tracking reasoning is completed, it is output in two forms. Users can choose to directly transmit the reasoning results to the backend according to the needs of the backend platform, that is, the coordinates of the center point of the tracked target and the coordinate sequence of the tracking frame range (not time-consuming), or they can superimpose the reasoning results into the video stream encoding output (1ms) by this solution. Therefore, the total processing time of the tracking network is a maximum of 18ms, which can meet the real-time reasoning process at a frame rate of 50Hz (using a large model) -200Hz (using a small model) at a resolution of 1080P.

[0025] The software execution process of this solution is as follows Figure 3 As shown, the UART / ETH control thread continuously monitors the serial port and network port data, and is responsible for processing the sending and receiving tasks of the serial port or network port. The working logic of this module is as follows: 1. When the UART / ETH control thread receives the instruction, it will automatically parse the instruction, convert the instruction information into the corresponding tracker working status and synchronize it to the Decoder module. The subsequent video processing related modules perform corresponding processing according to the status information; 2. When the detector and tracker report the detection and tracking information to the UART / ETH control thread, the UART / ETH control thread will process the reported information according to the instruction protocol and send it to the external master immediately after processing.

[0026] The main thread of the recognition and tracking algorithm has different algorithm flow according to the different enabled functions. First, the Decoder module will decode the input video frame by frame. The decoded image will be recognized, tracked or directly output according to the main control instructions. The processed image will be superimposed with display information according to the protocol requirements. The OSD module outputs the image and sends it to the encoder for image encoding and sends it to the external main control through the rtsp network video stream.

[0027] The target recognition thread algorithm mainly includes two threads: recognition pre-processing, target recognition and recognition post-processing. The target recognition thread pre-processes the input current frame image to meet the requirements of the recognition network input, and sends it to the recognition thread for model inference to obtain image output. The recognition post-processing thread is responsible for matching target IDs, determining target categories, and outputting target recognition accuracy based on the network output and combined with timeline and other information. If the target is lost and re-enters the field of view within 3 seconds, it can automatically match the previous ID. It also has the function of counting the number of targets of different categories.

[0028] The tracking algorithm thread is mainly responsible for processing the template extraction and calculation of the search area after the tracking instruction is issued (which can be issued by the external master control or by the recognition module). After determining the tracking template, the template and the search area are sent to the tracking network for model reasoning, and the position of the tracked target and the confidence of the tracked target are output. The main function of the tracking post-processing thread is to judge the current tracker state and dynamically update the tracking template. Its main logic is: if the tracking output confidence is greater than the set threshold, the tracking is considered normal; if the tracking output confidence is less than the set threshold, the target is considered lost or occluded. The occlusion loss processing logic is as follows:

[0029] 1. Occlusion

[0030] Trigger condition: The tracking confidence is less than the set threshold, and the tracking of the previous frame is normal, and the target coordinates are not at the edge of the image. At this time, it is considered to enter the target occlusion state;

[0031] Search strategy: When the target is occluded, the system will continue to track and search at the occlusion point until the target reappears, and then enter the normal tracking mode. If the occlusion duration is set manually, if the target does not appear after the occlusion duration, the system will automatically enter the target lost state, triggering the target lost search strategy.

[0032] 2. Lost

[0033] Trigger conditions: Tracking confidence is less than the set threshold, and the target tracking output coordinates of the previous frame are at the edge of the image, then the target is set to be lost; target occlusion timeout triggers the target lost state;

[0034] Search strategy: If the target is lost, the whole field of view will be searched for the target to determine whether the target reappears in the field of view. If the target reappears, the tracking will enter the normal state and continue to track the target. If the manually set target re-search time is exceeded, it is considered that the target will not appear again and the tracking will be automatically stopped;

[0035] After obtaining the tracking result, the tracking thread will immediately synchronize the miss amount information with the UART / ETH control thread. After synchronization, it will trigger the miss amount information output of the serial port and forward the miss amount information to the external master control. In addition, the tracking thread will send the tracking result to the post-processing thread, decide whether to update the template according to the user's instructions and tracking results, and further pass the result to the OSD module for information superposition. The OSD module is responsible for superimposing image frame sequence number, target identification related information, tracking miss amount information, turntable angle and other image display information; the video encoding and streaming thread is responsible for the h264 or h265 encoding of the display image and push it to the video streaming server.

[0036] Automatic tracking detection Real-time automatic tracking function, detect typical targets through recognition algorithm, automatically trigger the tracking function after the recognition algorithm successfully captures the typical target, realize the complete automatic tracking closed loop, realize the function logic as follows Figure 4 shown.

[0037] The real-time automatic tracking function triggers automatic tracking through the target detection network. First, the program will perform a status self-check after startup. After the self-check is completed, the recognition network will automatically start to identify the target in the picture. When the typical target appears in the picture, the recognition network will send the identified typical target coordinates to the tracking module. When the tracking module receives the target coordinates, it will start the tracking function.

[0038] The tracking algorithm execution logic of the present invention is as follows: after the tracker starts tracking, it will continue to judge the current tracking state. The specific tracking state is divided into the following three states:

[0039] ①Tracking is normal

[0040] When tracking is normal, the system will continue to track the target and output the tracking result miss amount in real time.

[0041] ②Tracking occlusion

[0042] When the tracked target is blocked by other targets, it enters the tracking blocked state, and the tracker will continue to memorize and track. The user can set the blocking timeout. When the set blocking timeout is exceeded, the tracker will enter the blocking lost state and switch to the blocking lost tracking logic. If the tracker recaptures the target within the set blocking timeout, it will enter the tracking normal state. The system will continue to track the target and output the tracking result miss amount in real time.

[0043] ③Tracking lost

[0044] When the tracked target enters the tracking loss state, the long-term tracking algorithm used by this system will globally recapture the target. If the recapture timeout is not set, the system will continue to recapture the target until it reappears in the field of view. When the user sets the recapture timeout, the system will continue to globally recapture the tracked target.

[0045] When the target is successfully recaptured, it will enter the normal tracking state. The system will continue to track the target and output the tracking result miss amount in real time.

[0046] When target recapture fails and the set recapture timeout period has not been exceeded, global recapture will continue.

[0047] When the target recapture fails and exceeds the set recapture timeout, the recognition network will be re-triggered to find a new typical target. When the typical target is recognized by the recognition network, the tracking logic will be re-entered.

[0048] In the description of the present invention, it is necessary to understand that the terms "coaxial", "bottom", "one end", "top", "middle", "the other end", "upper", "one side", "top", "inside", "front", "center", "both ends" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0049] In addition, the terms "first", "second", "third" and "fourth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first", "second", "third" and "fourth" may explicitly or implicitly include at least one of such features.

[0050] In the present invention, unless otherwise clearly stipulated and limited, the terms such as "installation", "setting", "connection", "fixation" and "screw-on" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. Unless otherwise clearly defined, ordinary technicians in this field can understand the specific meanings of the above terms in the present invention according to the specific circumstances.

[0051] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework, characterized by: It includes two network frameworks: target recognition and target tracking. The working logic is to use the recognition network to trigger the tracking network. When the recognition network recognizes a trusted target, it quickly switches to the tracking network to lock the target and subsequently accurately track and predict the trajectory. When the target is lost from the field of view, the tracking stops. At this time, the recognition network is reactivated to search for suspected targets in the field of view. The target in the field of view is manually selected, and the tracking network is activated to lock the target and subsequently accurately track and predict the trajectory. When the target is lost from the field of view, the tracking stops to prevent mistracking. The self-developed long-term tracking algorithm is used. The long-term tracker will perform in-depth feature extraction on the target during the tracking process. When the target disappears, the tracking stops. After re-entering the field of view, it has a persistent and controllable re-capture capability. After the front-end multi-channel video image input, the target recognition and target tracking networks are switched in time, activated and scheduled with each other, and the hardware visual preprocessing core VPC is called to complete the operations of cutout, scaling, overlay, splicing, histogram statistics, color remapping, format conversion, Remap transformation, and filtering image processing. The preprocessed data is sent to the memory buffer of the NPU for subsequent reasoning. After the network reasoning is completed, it is output in two forms, which are the coordinates of the center point of the identified target and the coordinate sequence of the identification box range. The system superimposes the reasoning results into the video stream encoding output.

2. A real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1, characterized in that: The target recognition and target tracking networks are in a time-sharing serial working mode, and the resources and time of each working module network are independent. After the pre-processing is completed, they are sent to the NPU for model reasoning.

3. A real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1, characterized in that: The software execution process of the target recognition and tracking solution is that the UART / ETH control thread continuously monitors the serial port and network port data, and is responsible for processing the sending and receiving tasks of the serial port or network port. When the UART / ETH control thread receives the instruction, it will automatically parse the instruction, convert the instruction information into the corresponding tracker working status and synchronize it to the Decoder module. The subsequent video processing related modules perform corresponding processing according to the status information. When the detector and tracker report the detection and tracking information to the UART / ETH control thread, the UART / ETH control thread will process the reported information according to the instruction protocol and send it to the external master control immediately after processing.

4. A real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1, characterized in that: The target recognition and tracking algorithm first decodes the input video in a single frame in the Decoder module, and the decoded image is recognized, tracked or directly output according to the main control instruction. The processed image is superimposed with display information according to the protocol requirements. The OSD module outputs the image and sends it to the encoder for image encoding and sends it to the external main control through the rtsp network video stream.

5. A real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 4, characterized in that: The target recognition thread algorithm includes two threads: recognition pre-processing, target recognition and recognition post-processing. The target recognition thread performs pre-processing on the input current frame image to meet the requirements of the recognition network input, and sends it to the recognition thread for model reasoning to obtain image output. The recognition post-processing thread is responsible for matching the target ID, determining the target category, and outputting the target recognition accuracy based on the network output and the timeline information. If the target is lost and re-enters the field of view within 3 seconds, the previous ID can be automatically matched. At the same time, it has the function of counting the number of targets of different categories.

6. The real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1 is characterized in that: The tracking algorithm thread is responsible for processing the template extraction and calculating the search area after the tracking instruction is issued. After determining the tracking template issued, the template and the search area are sent to the tracking network for model reasoning, and the position of the tracking target and the confidence of the tracking target are output.

7. The real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1 is characterized in that: The tracking post-processing thread function is to judge the current tracker state and dynamically update the tracking template. Its main logic is: if the tracking output confidence is greater than the set threshold, the tracking is considered normal; if the tracking output confidence is less than the set threshold, the target is considered lost or blocked.

8. The real-time high-speed target recognition and tracking solution based on a domestic artificial intelligence framework according to claim 1 is characterized in that: The specific states of the algorithm execution logic during tracking are divided into the following three states: normal tracking, tracking occlusion, and tracking loss.

Images