Portable posture detection and gait analysis method and system

Abstract

The invention relates to the technical field of human body posture detection and gait analysis, and discloses a portable posture detection and gait analysis method and system. The method comprises the steps that a hardware system is built, the hardware system comprises an embedded visual module, a data processing module and an interaction module, and human body motion video streams are collected through the embedded visual module; performing dynamic foreground extraction on the acquired video stream by adopting a background difference method and a self-adaptive illumination compensation algorithm, and outputting an illumination compensation image; according to the output illumination compensation image, the data processing module is used for increasing time sequence constraint loss on the basis of a YoLoV8 model, positioning key points of a human body and constructing a three-dimensional skeleton motion model; according to the method, a dynamic shielding processing engine and a multi-target decoupling mechanism are utilized, the constructed three-dimensional skeleton motion model is tracked based on a hierarchical association degree measurement function, human body motion data can be collected in real time, and accurate evaluation of postures and accurate extraction of gait features in multiple scenes are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of human posture detection and gait analysis, and in particular to a portable posture detection and gait analysis method and system. Background Art

[0002] In the existing posture detection and gait analysis systems, a relatively bulky equipment architecture is usually adopted, such as using traditional servers or large computers as data processing modules, and using ordinary cameras for data collection. The existing technology has the following objective disadvantages in posture detection and gait analysis: (1) The test environment is demanding. For example, there can only be one tester in the field of view of the camera, and no other people. There are also strict requirements on lighting conditions, and strong light is not allowed. In actual use, it is difficult to find a venue that meets such conditions. During large-scale screening, if other people appear in the field of view, data errors may occur. This is because the existing technology lacks effective target recognition and environmental adaptability, and cannot accurately distinguish between the tester and other people, nor can it cope with the impact of light changes on detection accuracy.

[0003] (2) There are deficiencies in target tracking and recognition. When occlusion occurs, the target is easily lost and the tester's motion trajectory cannot be accurately tracked. In multi-target scenarios, different testers cannot be effectively distinguished. ID switching errors are prone to occur, leading to data confusion. This is because the target tracking algorithm of the existing technology is relatively simple and lacks a deep understanding and analysis of the target, and cannot maintain a stable tracking effect in complex situations.

[0004] (3) Existing technologies are usually bulky and inconvenient to carry and use, which limits their application in different scenarios. At the same time, they cannot automatically adapt to different test distances and angles and require manual adjustment, which increases the complexity and workload of the operation. In addition, when faced with different environmental interference factors, such as reflections, existing technologies also lack effective suppression measures, which affects the accuracy of the test results.

[0005] (4) The use of traditional CPUs for data processing has low efficiency when running complex posture detection and gait analysis algorithms, resulting in slow processing speed of the entire system and difficulty in achieving real-time analysis. When processing high-definition video streams, there may be freezes and analysis results cannot be given in a timely manner, affecting user experience and actual application effects.

[0006] (5) The feedback method is relatively simple, usually only displaying the analysis results through simple text or charts, lacking intuitive visualization effects. Moreover, it is impossible to automatically generate detailed reports based on the analysis results. Doctors or researchers need to manually record and organize data, which increases the workload and the risk of errors.

[0007] Therefore, the present invention provides a portable posture detection and gait analysis method and system. Summary of the invention

[0008] The present application provides a portable posture detection and gait analysis method and system for real-time collection of human motion data, and for achieving accurate posture assessment and gait feature extraction in multiple scenarios.

[0009] In a first aspect, the present application provides a portable posture detection and gait analysis method, the method comprising: Step S1, building a hardware system, wherein the hardware system includes an embedded vision module, a data processing module and an interaction module, and collecting a human motion video stream through the embedded vision module; Step S2, extracting dynamic foreground from the collected video stream using background difference method and adaptive illumination compensation algorithm, and outputting illumination compensation image; Step S3, according to the output illumination compensation image, using the data processing module, adding the timing constraint loss on the basis of the YoLoV8 model, locating the key points of the human body, and constructing a three-dimensional skeletal motion model; Step S4, using the dynamic occlusion processing engine and the multi-target decoupling mechanism, based on the hierarchical association metric function, the constructed three-dimensional skeletal motion model is tracked to obtain posture data, and the tracked posture data is analyzed using the Graph-TCN hybrid network to obtain the displacement of key points between consecutive frames and calculate the gait data; Step S5: Based on the acquired posture data and gait data, the posture assessment score and correction suggestions are displayed in real time through the interactive module, and an analysis report including a gait parameter trend graph and a risk assessment matrix is ​​generated.

[0010] In combination with the first aspect, in a first implementation of the first aspect of the present application, the portable posture detection and gait analysis method includes: the hardware system is further configured with an environment adaptation module, and the environment adaptation module includes: Multi-scale feature fusion network: used for adaptive detection distance; Anti-occlusion compensation algorithm: used to complete the data by predicting the motion trajectory when part of the limb is occluded during the tracking of the three-dimensional skeletal motion model in step S4; Reflection suppression unit: A solution combining polarizing filters and software is used to reduce the impact of reflections on detection.

[0011] In combination with the first aspect, in the second implementation method of the first aspect of the present application, the portable posture detection and gait analysis method includes: the embedded vision module integrates a retractable multi-spectral camera array, the multi-spectral camera array is a wide-angle camera group with an adjustable angle, and the embedded vision module adopts a mode of fusion of a visible light camera and an infrared ToF depth sensor, and automatically switches according to ambient lighting conditions.

[0012] In combination with the first aspect, in a third implementation of the first aspect of the present application, the data processing module is equipped with an Nvidia Jetson Nano computing module, adopts an NPU+GPU dual-core heterogeneous architecture, and the visual processing core and the motion analysis core work in parallel.

[0013] In combination with the first aspect, in a fourth implementation of the first aspect of the present application, the data processing module adopts a dynamic model clipping strategy for automatically switching between the full network and clipped network modes according to the complexity of the scene; The interactive module uses a touch screen for interface display.

[0014] In combination with the first aspect, in a fifth implementation of the first aspect of the present application, the portable posture detection and gait analysis method includes: in step S3: The timing constraint loss function is: Among them, J is the number of key points, T is the length of the time window; is: the coordinates of the jth key point in the tth frame.

[0015] In combination with the first aspect, in a sixth implementation of the first aspect of the present application, the portable posture detection and gait analysis method includes: in step S4: The hierarchical association metric function is: Among them, S IoU is the intersection-union similarity; is the motion similarity; is the appearance similarity, and α, β, and γ are weight coefficients.

[0016] The motion similarity Smotion introduces an improved Social-LSTM interaction model.

[0017] In combination with the first aspect, in a seventh implementation of the first aspect of the present application, in step S5: The Graph-TCN hybrid network satisfies: Among them, A is the adjacency matrix of the skeleton connection graph; is the feature matrix of the lth layer; is the weight matrix of the graph convolution layer; It is a temporal convolutional network; is the activation function.

[0018] In combination with the first aspect, in the eighth implementation of the first aspect of the present application, the portable posture detection and gait analysis method includes: the dynamic occlusion processing engine includes a mask predictor based on spatiotemporal attention, and through the mask predictor, a motion probability heat map is constructed using historical trajectories. When occlusion occurs, the LSTM-based trajectory prediction module maintains continuous tracking of less than or equal to frames, and the position prediction error is less than or equal to 7.2 pixels.

[0019] In a second aspect, the present application provides a portable posture detection and gait analysis system, the system comprising: A hardware module is used to build a hardware system, wherein the hardware system includes an embedded vision module, a data processing module and an interaction module, and collects a human motion video stream through the embedded vision module; The dynamic foreground extraction module is used to extract the dynamic foreground from the collected video stream using the background difference method and the adaptive illumination compensation algorithm, and output an illumination compensated image; A skeleton model building module is used to add a timing constraint loss based on the YoLoV8 model, locate the key points of the human body, and build a three-dimensional skeleton motion model by using the data processing module according to the output illumination compensation image; Tracking module, which uses the dynamic occlusion processing engine and multi-target decoupling mechanism to track the constructed three-dimensional skeletal motion model based on the hierarchical correlation metric function, obtains posture data, uses the Graph-TCN hybrid network to analyze the tracked posture data, obtains the displacement of key points between consecutive frames, and calculates gait data; The feedback module is used to display the posture assessment score and correction suggestions in real time through the interactive module according to the acquired posture data and gait data, and generate an analysis report including a gait parameter trend graph and a risk assessment matrix.

[0020] Compared with the prior art, the beneficial effects of the present invention are at least as follows: In the technical solution provided in this application, the hardware adopts a foldable multi-spectral camera array and an embedded heterogeneous computing architecture (NPU+GPU collaboration), combined with a dynamic model clipping strategy, which reduces the computing load by 38% while ensuring detection accuracy (AP greater than or equal to 85%), and realizes lightweight and portable design (the volume after folding is less than or equal to 220mm×200mm×100mm) and high-performance computing (greater than or equal to 30fps real-time processing), solving the problems of bulkiness and high latency. Secondly, in response to complex environmental interference, the system integrates dual-channel sensor fusion technology (visible light + infrared ToF depth sensor) and an illumination invariant feature extraction network, decouples illumination and shadows through an adversarial generation network, and still maintains a detection accuracy of 92.4% in strong backlight scenes; at the same time, a spatiotemporal attention mask predictor is introduced. Together with the improved Social-LSTM model, it can achieve less than or equal to 15 frames of continuous tracking (with an error of less than or equal to 7.2 pixels) in occluded or multi-person scenes, effectively avoiding ID switching errors. In addition, based on the 3D skeletal motion modeling and Graph-TCN hybrid network of the improved YoLoV8 model, it can accurately extract parameters such as step length and joint angle, realize accurate posture assessment and gait feature extraction in multiple scenes, and generate visual reports (including gait trend graphs and risk assessment matrices) in real time through a multimodal interactive interface, providing high-value data support for medical diagnosis, rehabilitation training and other fields. These technologies work together to solve the pain points of the existing system, such as poor environmental adaptability, unstable target tracking and single feedback function, and are suitable for outdoor screening, dense crowd analysis, dynamic rehabilitation monitoring and other scene requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a portable posture detection and gait analysis method in an embodiment of the present application; Figure 2 It is a structural diagram of the portable posture detection and gait analysis system in the embodiment of the present application. DETAILED DESCRIPTION

[0023] Embodiments of the present application provide a portable posture detection and gait analysis method and system. The terms "first", "second", "third", "fourth", etc. (if any) 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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the portable posture detection and gait analysis method in the embodiment of the present application includes: Step S1, building a hardware system, the hardware system includes an embedded vision module, a data processing module and an interaction module, and collecting a human motion video stream through the embedded vision module.

[0025] Specifically, the embedded vision module is responsible for high-precision acquisition of human motion video streams and adapting to complex environments. The data processing module processes video stream data in real time, performs key point detection, three-dimensional modeling and gait analysis. The interactive module provides a user interface through a touch screen, provides real-time feedback on analysis results and generates reports, while also enabling real-time visualization through software.

[0026] Step S2: extract dynamic foreground from the collected video stream using background difference method and adaptive illumination compensation algorithm, and output illumination compensation image.

[0027] Specifically, the background difference method is used in combination with the adaptive illumination compensation algorithm to eliminate the influence of ambient illumination changes on detection accuracy. This combination can effectively improve the robustness of foreground extraction, especially in scenes with large illumination changes. For example, in a complex crowd environment, the test subject can be accurately identified and tracked, and even if other people appear in the camera's field of view, it will not interfere with the detection of the test subject. In the case of light changes, the illumination compensation parameters can be automatically adjusted to ensure image quality, thereby improving detection accuracy and reliability.

[0028] For the collected video stream, set each frame image to I t , the background model is B t , the image after illumination compensation is : Background modeling: The initial background model is the first frame image: in, is the initial background model; The first frame image.

[0029] in, is the background model of the t-1th frame; is the weight coefficient.

[0030] Foreground Detection: in, is the difference image of the tth frame.

[0031] in, is the binary foreground mask, 255 is foreground and 0 is background; threshold means threshold; Introducing adaptive weight coefficients in spatiotemporal domain : in Represents the variance between the current frame and the background model; is the dynamic threshold; k is the adjustment factor; Multi-model background modeling: in, is the weight of the i-th background model at time t; is the ith background model.

[0032] The mixed Gaussian model and the color constancy model are used for parallel calculation, and the weights are dynamically adjusted through KL divergence. i ; Light compensation: in, is the original image of the tth frame; GammaCorrection is a two-dimensional gamma correction function that uses the illumination component and the adaptive target mean for adjustment; Light compensation enhancement solution: in, is the reflection component; Γ is the adaptive gamma correction function; Separation of illumination components via dual-domain filtering.

[0033] Deep learning assisted compensation: Build a lightweight U-Net network, input the original image and HSV spatial features, and output the illumination compensated image: .

[0034] in, Light compensation image predicted by U-Net; Compensate images for real lighting; and is the weight coefficient of the loss function; SSIM is a structural similarity index that measures the consistency of image structure.

[0035] Step S3: Based on the output illumination compensation image, the data processing module is used to add the timing constraint loss on the basis of the YoLoV8 model, locate the key points of the human body, and construct a three-dimensional skeletal motion model.

[0036] Specifically, the YoLoV8 model is improved to locate the key points of the human body and build a three-dimensional skeletal motion model. Based on this model, human posture can be evaluated more accurately and gait features can be extracted. For example, when analyzing the gait cycle, common gait parameters such as step length, step frequency, and toe height can be determined more accurately, providing a more reliable data basis for subsequent gait analysis and diagnosis.

[0037] Step S4, using the dynamic occlusion processing engine and the multi-target decoupling mechanism, based on the hierarchical association metric function, the constructed three-dimensional skeletal motion model is tracked to obtain posture data, and the tracked posture data is analyzed using the Graph-TCN hybrid network to obtain the key point displacement between consecutive frames and calculate the gait data.

[0038] Specifically, the dynamic occlusion processing engine and multi-target decoupling mechanism ensure the reliability of target tracking. The multi-target decoupling mechanism is based on the hierarchical association measurement function. The motion similarity Smotion introduces an improved Social-LSTM interaction model to solve the ID switching problem in dense crowds. During large-scale screening, multiple testers may appear in the camera field of view at the same time. The multi-target decoupling mechanism can accurately distinguish different testers and avoid ID confusion. For example, when conducting gait screening in crowded places such as schools or enterprises, each tester can be accurately identified and tracked to ensure that the gait data of each tester can be accurately recorded and analyzed.

[0039] Step S5: Based on the acquired posture data and gait data, the posture assessment score and correction suggestions are displayed in real time through the interactive module, and an analysis report including a gait parameter trend graph and a risk assessment matrix is ​​generated.

[0040] Specifically, the interactive module provides a multimodal interactive interface, calculates the posture stability score in real time based on indicators such as key point offset and joint range of motion, and displays the real-time posture assessment score and correction suggestions on a visual interface. It generates a PDF analysis report that includes a gait parameter trend graph and a risk assessment matrix. These functions enable users to intuitively understand their gait conditions and to perform targeted corrections and training based on the analysis report. For example, for rehabilitation patients, by viewing the gait parameter trend graph, they can clearly understand the progress of their gait recovery, and doctors can also adjust the treatment plan in a timely manner based on the risk assessment matrix.

[0041] In a specific embodiment: the hardware system is further configured with an environment adaptation module, and the environment adaptation module includes: Multi-scale feature fusion network: used for adaptive detection distance, automatically adapting to the detection distance of 1-5 meters (usually the test distance is less than 3 meters); Anti-occlusion compensation algorithm: used to complete the data by predicting the motion trajectory when part of the limb is occluded during the tracking of the three-dimensional skeletal motion model in step S4; Reflection suppression unit: A solution combining polarizing filters and software is used to reduce the impact of reflections on detection.

[0042] Specifically, in different test sites and scenarios, it can be quickly deployed and automatically adjust the detection distance and angle to adapt to different test needs; when encountering reflection interference, the reflection suppression unit can effectively reduce the impact of reflection on the detection results and improve the accuracy and reliability of detection.

[0043] The anti-occlusion compensation algorithm works together with the dynamic occlusion processing engine and the multi-target decoupling mechanism. During long-term gait tracking, it can accurately track the target and provide continuous and reliable gait data even in the event of brief occlusion or the presence of multiple people at the same time.

[0044] The anti-occlusion compensation algorithm is specifically as follows: Assume the detection set of the tth frame is , the tracker set is , where each tracker Include: State Vector in, is the target center coordinate; is the aspect ratio; is the height; The rate of change of the corresponding parameter; Appearance feature vector ; Covariance matrix Describe state uncertainty; Input: Target ID k , current frame tracking list Output: Target position ( ) The output target does not exist in the tracking list When the occlusion processing principle is triggered: N consecutive frames are not matched: In case of short-term loss, that is, when N≤3, Kalman filter is used to predict the trajectory: Among them, F is the state transfer matrix; B is the control input matrix; is the state vector of target k at time t (including the center coordinates , aspect ratio γ, height h and its rate of change); is the control vector; In case of long-term loss, that is, when N>3, the system prompts the tester to take his place.

[0045] In a specific embodiment, the embedded vision module integrates a retractable multi-spectral camera array, which is a wide-angle camera group with adjustable angles. The embedded vision module adopts a mode that combines a visible light camera and an infrared ToF depth sensor, and automatically switches according to ambient lighting conditions.

[0046] Specifically, the retractable multispectral camera array adopts a foldable structure design, which forms an adjustable field of view of 60°-120° when unfolded, and the volume is less than or equal to 220mm×200mm×100mm when folded. This design makes it easy to carry and store. Whether it is for large-scale screening in remote areas or for transfer between different medical institutions, it can be easily carried, greatly improving the flexibility of use.

[0047] The purpose of illumination adaptation is achieved by integrating the visible light camera and the infrared ToF depth sensor, and an illumination invariant feature extraction network (LIF-Net) is designed. The illumination-shadow decoupling representation is constructed through a generative adversarial network, and a detection accuracy of 92.4% is maintained in strong backlighting scenes. In actual use, light conditions are often complex and changeable. For example, strong direct sunlight or shadows may be encountered during outdoor screening. The present invention can automatically adapt to these illumination changes to ensure the accuracy of the detection results. For example, in outdoor screening in the early morning or evening, even if the light is weak and there is backlighting, human posture and gait characteristics can still be accurately detected.

[0048] In a specific embodiment, the data processing module is equipped with an Nvidia Jetson Nano computing module, adopts an NPU+GPU dual-core heterogeneous architecture, and the visual processing core and the motion analysis core work in parallel.

[0049] Specifically, the Nvidia Jetson Nano computing module of the data processing module can be powered by AC power or lithium battery. It adopts a portable architecture of embedded edge computing and adaptive reasoning. Through the NPU+GPU dual-core heterogeneous architecture, the NPU specializes in fixed-point acceleration of lightweight posture detection networks, and the GPU is responsible for the timing convolution operation of gait analysis. Compared with the traditional pure CPU solution, it achieves an 11.6-fold improvement in energy efficiency. For example, with the same power supply, it can work continuously for a longer time, which is especially important for large-scale screening scenarios. There is no need for frequent charging, which improves work efficiency. When processing high-definition video streams, it can quickly complete data processing and analysis, and give accurate detection results in a timely manner to meet the needs of real-time analysis and improve work efficiency and user experience.

[0050] In addition, the real-time processing speed is ensured to be no less than 30fps. In the gait analysis process, real-time performance is very important. For example, in clinical diagnosis, doctors need to obtain the patient's gait data in a timely manner for diagnosis. The high-speed real-time processing capability of the present invention can meet this demand, quickly provide accurate gait analysis results, and provide timely basis for the doctor's diagnosis.

[0051] In a specific embodiment, the data processing module adopts a dynamic model clipping strategy for automatically switching between full network and clipped network modes according to scene complexity; The interactive module uses a touch screen for interface display.

[0052] Specifically, dynamic model cropping can automatically switch the network depth (full network / cropped network) based on the complexity of the scene, reducing the computing load by 38% while ensuring that AP is greater than or equal to 85%. In different scenarios, it can intelligently adjust the allocation of its own computing resources to avoid unnecessary computing waste. For example, in a simple gait analysis scenario, it can quickly switch to the cropped network mode to speed up the processing speed, while ensuring sufficient computing accuracy in complex scenarios.

[0053] In a specific embodiment, in step S3: The timing constraint loss function is: Among them, J is the number of key points, T is the length of the time window; is: the coordinates of the jth key point in the tth frame.

[0054] In a specific embodiment, in step S4: The hierarchical association metric function is: Among them, S IoU is the intersection-union similarity; is the motion similarity; is the appearance similarity, α, β, γ are weight coefficients; Motion similarity Smotion introduces an improved Social-LSTM interaction model.

[0055] Specifically, the integrated geometry ( ), motion (improved Social-LSTM) and appearance (128-dimensional feature vector) similarity ( ), improve the robustness of multi-target tracking and solve the ID switching problem in dense crowds.

[0056] In a specific embodiment, in step S5: The Graph-TCN hybrid network satisfies: Among them, A is the adjacency matrix of the skeleton connection graph; is the feature matrix of the lth layer; is the weight matrix of the graph convolution layer; It is a temporal convolutional network; is the activation function.

[0057] In a specific embodiment, the dynamic occlusion processing engine includes a mask predictor based on spatiotemporal attention. Through the mask predictor, a motion probability heat map is constructed using historical trajectories. When occlusion occurs, the LSTM-based trajectory prediction module maintains continuous tracking of less than or equal to 15 frames, and the position prediction error is less than or equal to 7.2 pixels.

[0058] Specifically, in actual gait analysis scenarios, the test subject may be obstructed by surrounding objects or people. The dynamic occlusion processing engine of the present invention can effectively solve this problem. For example, when conducting gait screening in crowded places, when the test subject is briefly obstructed by other people, his or her movement trajectory can still be accurately tracked to ensure the continuity and accuracy of the data.

[0059] The portable posture detection and gait analysis method in the embodiment of the present application is described above. The portable posture detection and gait analysis system in the embodiment of the present application is described below. Figure 2 In the embodiment of the present application, one embodiment of the portable posture detection and gait analysis system includes: A hardware module, used to build a hardware system, wherein the hardware system includes an embedded vision module, a data processing module and an interaction module, and is used to collect a human motion video stream through the embedded vision module; The dynamic foreground extraction module is used to extract the dynamic foreground from the collected video stream using the background difference method and the adaptive illumination compensation algorithm, and output an illumination compensated image; A skeleton model building module is used to add a timing constraint loss based on the YoLoV8 model, locate the key points of the human body, and build a three-dimensional skeleton motion model by using the data processing module according to the output illumination compensation image; Tracking module, which uses the dynamic occlusion processing engine and multi-target decoupling mechanism to track the constructed three-dimensional skeletal motion model based on the hierarchical correlation metric function, obtains posture data, uses the Graph-TCN hybrid network to analyze the tracked posture data, obtains the displacement of key points between consecutive frames, and calculates gait data; The feedback module is used to display the posture assessment score and correction suggestions in real time through the interactive module according to the acquired posture data and gait data, and generate an analysis report including a gait parameter trend graph and a risk assessment matrix.

[0060] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A portable posture detection and gait analysis method, characterized in that: The method comprises: Step S1, building a hardware system, wherein the hardware system includes an embedded vision module, a data processing module and an interaction module, and collecting a human motion video stream through the embedded vision module; Step S2, extracting dynamic foreground from the collected video stream using background difference method and adaptive illumination compensation algorithm, and outputting illumination compensation image; Step S3, according to the output illumination compensation image, using the data processing module, adding the timing constraint loss on the basis of the YoLoV8 model, locating the key points of the human body, and constructing a three-dimensional skeletal motion model; Step S4, using the dynamic occlusion processing engine and the multi-target decoupling mechanism, based on the hierarchical association metric function, the constructed three-dimensional skeletal motion model is tracked to obtain posture data, and the tracked posture data is analyzed using the Graph-TCN hybrid network to obtain the displacement of key points between consecutive frames and calculate the gait data; Step S5: Based on the acquired posture data and gait data, the posture assessment score and correction suggestions are displayed in real time through the interactive module, and an analysis report including a gait parameter trend graph and a risk assessment matrix is ​​generated.

2. The portable posture detection and gait analysis method according to claim 1, characterized in that: The hardware system is also configured with an environment adaptation module, and the environment adaptation module includes: Multi-scale feature fusion network: used for adaptive detection distance; Anti-occlusion compensation algorithm: used to complete the data by predicting the motion trajectory when part of the limb is occluded during the tracking of the three-dimensional skeletal motion model in step S4; Reflection suppression unit: A solution combining polarizing filters and software is used to reduce the impact of reflections on detection.

3. The portable posture detection and gait analysis method according to claim 1, characterized in that: The embedded vision module integrates a retractable multi-spectral camera array, which is a wide-angle camera group with adjustable angles. The embedded vision module adopts a mode that combines a visible light camera and an infrared ToF depth sensor, and automatically switches according to ambient lighting conditions.

4. The portable posture detection and gait analysis method according to claim 1, characterized in that: The data processing module is equipped with an Nvidia Jetson Nano computing module, which adopts an NPU+GPU dual-core heterogeneous architecture, and the visual processing core and the motion analysis core work in parallel.

5. The portable posture detection and gait analysis method according to claim 1, characterized in that: The data processing module adopts a dynamic model clipping strategy to automatically switch between full network and clipped network modes according to scene complexity; The interactive module uses a touch screen for interface display.

6. The portable posture detection and gait analysis method according to claim 1, characterized in that: In step S3: The timing constraint loss function is: Among them, J is the number of key points, T is the length of the time window; is: the coordinates of the jth key point in the tth frame.

7. The portable posture detection and gait analysis method according to claim 1, characterized in that: In step S4: The hierarchical association metric function is: Among them, S IoU is the intersection-union similarity; is the motion similarity; is the appearance similarity, α, β, γ are weight coefficients; Motion similarity Smotion introduces an improved Social-LSTM interaction model.

8. The portable posture detection and gait analysis method according to claim 1, characterized in that: In step S5: The Graph-TCN hybrid network satisfies: Among them, A is the adjacency matrix of the skeleton connection graph; is the feature matrix of the lth layer; is the feature matrix of the l+1th layer; is the weight matrix of the graph convolution layer; It is a temporal convolutional network; is the activation function.

9. The portable posture detection and gait analysis method according to claim 1, characterized in that: The dynamic occlusion processing engine includes a mask predictor based on spatiotemporal attention. Through the mask predictor, a motion probability heat map is constructed using historical trajectories. When occlusion occurs, the LSTM-based trajectory prediction module maintains continuous tracking of less than or equal to 15 frames, and the position prediction error is less than or equal to 7.2 pixels.

10. A portable posture detection and gait analysis system, used to implement the portable posture detection and gait analysis method according to any one of claims 1 to 9, characterized in that: Includes the following modules: A hardware module is used to build a hardware system, wherein the hardware system includes an embedded vision module, a data processing module and an interaction module, and collects a human motion video stream through the embedded vision module; The dynamic foreground extraction module is used to extract the dynamic foreground from the collected video stream using the background difference method and the adaptive illumination compensation algorithm, and output an illumination compensated image; A skeleton model building module is used to add a timing constraint loss based on the YoLoV8 model, locate the key points of the human body, and build a three-dimensional skeleton motion model by using the data processing module according to the output illumination compensation image; Tracking module, which uses the dynamic occlusion processing engine and multi-target decoupling mechanism to track the constructed three-dimensional skeletal motion model based on the hierarchical correlation metric function, obtains posture data, uses the Graph-TCN hybrid network to analyze the tracked posture data, obtains the displacement of key points between consecutive frames, and calculates gait data; The feedback module is used to display the posture assessment score and correction suggestions in real time through the interactive module according to the acquired posture data and gait data, and generate an analysis report including a gait parameter trend graph and a risk assessment matrix.

Images