653 results about "Pedestrian detection" patented technology

An intelligent traffic management device for optimizing traffic flow at one or more intersections using reinforcement learning, comprising: a central control unit housed in a weatherproof enclosure and mounted on a structural support near an intersection; a sensor interface operatively connected to a variety of multimodal sensors, including at least radar-based vehicle detectors, inductive loop sensors embedded in the road surface, infrared pedestrian detection detectors, and high-resolution optical imaging modules; a powerful embedded computing unit consisting of a multi-core processor and a GPU configured for on-device inference; a reinforcement learning engine embedded in the computing unit, comprising a deep reinforcement learning model trained to map environmental states defined by traffic-related sensor inputs to optimized action policies for traffic light control; a signal actuation module electrically connected to traffic signal controllers, with action policies outputting signal phase durations and transitions in real time; a communications module supporting wireless connectivity and configured for device-to-device communication and cloud synchronization; a policy synchronization module configured to perform federated learning-based updates of model parameters by exchanging gradient weights or distilled traffic state vectors with neighboring intelligent traffic management devices deployed in a traffic network; where the reinforcement learning engine continuously observes traffic state vectors consisting of vehicle counts, average speeds, queue lengths, and pedestrian activity, and dynamically updates the policy to maximize cumulative traffic throughput and minimize average delay.

The invention discloses an SCCA-YOLO-based unmanned aerial vehicle tiny target detection method, which mainly carries out innovative design around neck feature processing and backbone network optimization, improves vehicle and pedestrian detection in a complex road environment under an unmanned aerial vehicle view angle through a multi-module cooperation mechanism, designs a parallel heterogeneous convolution MCAD module, and improves the detection accuracy of a small target on the premise of ensuring the real-time performance. Local details and global semantic comprehension are considered; the method comprises the following steps: designing a space and channel attention module SCCA introducing a PSAS intelligent dimension adaptation mechanism, and combining a bottleneck structure BottleNeck of a YOLOv11 backbone network C3k2 module with the SCCA space and channel attention module to form an SCCA-BottleNeck; the MSFI and SCC modules are introduced into the NECK part, the modeling capacity of the model for scale change and hierarchy association is remarkably enhanced on the premise of keeping reasonable calculation overhead, and the method is particularly suitable for the traffic road environment of fine multi-scale processing.

The invention provides a three-dimensional space track identification method based on multi-view three-dimensional reconstruction, which comprises the following steps of: shooting the same scene from different angles by using a plurality of cameras, and determining a picture intersection part of the plurality of cameras as a research scene; frame extraction and pedestrian detection are carried out on the video of each camera, pedestrians and position information of the pedestrians in each frame of video are identified, a unified identity number is distributed to the same pedestrian, registration is carried out on video frame images of different cameras, the pixel position of each pedestrian in each camera is obtained, and a multi-view-angle triangulation method is adopted, and internal and external parameters of the cameras are combined, so that the pedestrian positioning accuracy is improved. Solving a three-dimensional point coordinate of each pedestrian in a camera coordinate system; the three-dimensional point coordinates are converted into coordinates in a world coordinate system, and world coordinate system coordinates of pedestrian point locations of all frames and all numbers are obtained; and according to the time information, connecting the pedestrian point locations of each frame and each number to form a track, and completing reconstruction of the pedestrian three-dimensional space track in the world coordinate system. According to the invention, manpower and calculation cost can be reduced.

The invention provides a low-visibility environment pedestrian detection method based on an improved YOLOv8n model. A double-branch fusion attention network is adopted in a backbone network of an original YOLOv8n model, and a CBFuse module and a CBLinear module are introduced for feature fusion between different branches; a feature aggregation and calibration pyramid network is introduced, multi-scale feature fusion is carried out through an up-sampling module, a down-sampling module and a feature aggregation and calibration module, and the feature aggregation and calibration module carries out feature calibration and enhancement through a local attention mechanism, a global attention mechanism and a pixel attention mechanism; an adaptive task alignment detection head is introduced to execute a dynamic convolution mechanism, a task decomposition mechanism and a dynamic feature alignment mechanism; an improved YOLOv8n model is formed based on the improvement and serves as a foggy day pedestrian detection network model; according to the method, the detection accuracy and stability of the network in processing shielded and background complex images can be enhanced, and the boundary and detail features of a fuzzy target can be extracted more accurately in low-visibility environments such as foggy days and the like.

The invention relates to the technical field of artificial intelligence computer vision, in particular to an event camera pedestrian detection method based on a space-time state space model, and the method comprises the steps: collecting a pedestrian detection data set based on an event camera, obtaining original event data, carrying out the preprocessing, determining an event tensor, and obtaining an event frame sequence; modeling is carried out through combination of a state space and an event tensor, an event-driven recursive space-time state space module is defined as a core unit, and an isomorphic deep neural network architecture is constructed; training the isomorphic deep neural network architecture by adopting the training set, and verifying through the verification set; inputting the test set into the verified isomorphic deep neural network architecture for detection, and generating a pedestrian detection result; the collaborative optimization of sparse adaptation-dynamic capture-noise suppression is realized in a unified framework, the essential characteristics of the event camera triggered based on brightness change are theoretically fit, and higher robustness and generalization ability are shown in an actual complex scene.

The invention provides a subway pedestrian anomaly detection method and system based on an improved yov8 network and a clip model, and relates to the technical field of subway pedestrian detection, and the method comprises the steps: obtaining a video frame in a subway scene, and carrying out the preprocessing of the video frame; inputting the preprocessed frame data into an improved yolov8 neural network model to obtain an abnormal behavior target detection frame, and performing target candidate tracking on the target detection frame by using a target tracking algorithm to obtain a candidate image of a target area of a specific behavior; the method comprises the following steps: inputting a candidate image containing a target area into a clip model, inputting a set detection text into the clip model, mapping the detection text and the candidate image of the target area, performing text-image similarity matching, and optimizing a similarity matching threshold by adopting a Q-Learning reinforcement learning immune algorithm to obtain a similarity matching result; and the abnormal behavior detection accuracy is improved.

The invention relates to a multi-modal pedestrian command gesture recognition method fused with a large model, and belongs to the field of automatic driving. The method comprises the following steps: collecting a pedestrian data set, and carrying out data set division; extracting human body key points from the data set by adopting a pre-trained pedestrian detection model; processing the extracted human body key point information through a target tracking network to obtain dynamic key point track information; establishing a multi-modal action recognition model for recognizing gestures, wherein the multi-modal action recognition model at least comprises a skeleton encoder and a text encoder; and the multi-modal gesture recognition model is trained and optimized through multi-part comparison learning loss, and a recognition result is obtained. The trained model is installed on an automatic driving automobile, pedestrian gestures are distinguished, and the intention of pedestrians is accurately judged. According to the method, a multi-modal framework is adopted, the recognition precision is high, and the recognition speed is high.

A low-light environment multispectral pedestrian detection method based on a cross-modal attention fusion network comprises the following steps: constructing a pedestrian detection network comprising a double-flow feature extraction backbone network (CSPDarknet53), a multi-model aggregation Transformer network (MFT), a double-model feature aggregation network (DMFF) and a detection head at an offline stage, training by adopting a multispectral data set, and then, carrying out multi-spectral detection on the pedestrian detection network; and performing real-time image processing through the trained pedestrian detection network in the online stage. According to the method, better pixel-level attention can be generated for small objects, and feature representation under different scales is enhanced.

The invention belongs to the technical field of image pedestrian detection, and particularly relates to a dense pedestrian detection method based on an improved YOLOv5s lightweight model. Comprising the following steps: acquiring a pedestrian image, and inputting the pedestrian image into an improved YOLOv5 model to obtain an initial dense pedestrian detection result; performing structured pruning on the improved YOLOv5 model according to the initial dense pedestrian detection result to obtain an intermediate improved YOLOv5 model; calculating the total loss of the model according to the initial dense pedestrian detection result, and adjusting the parameters of the intermediate improved YOLOv5 model according to the total loss of the model to obtain a trained dense pedestrian detection model; and screening the detection results of the trained dense pedestrian detection model by using a Soft-NMS algorithm to obtain a final dense pedestrian detection result. The pedestrian recognition accuracy can be improved, the problem of shielding between pedestrians can be effectively relieved, and the method can be operated on equipment with limited resources and has a good effect.

The invention discloses a Voxel RCNN Complex HD-based road target detection model and detection method, and proposes an improved three-dimensional feature extraction network and a two-dimensional feature extraction network for the problem that the Voxel R-CNN algorithm is insufficient in point cloud feature extraction. In order to solve the problem of low pedestrian detection precision, a mixed detection head with an anchor frame and a mixed detection head without an anchor frame are provided, and the detection precision of a large target and a small target is improved by using the mixed detection head based on an anchor and a mixed detection head without an anchor. The voxel candidate box self-attention pool module is provided for solving the problem that the difference between the detection precision of buses and trucks and the detection precision of trolleys in vehicle categories is large, local and global features of an object are better obtained, and therefore the size, the position and the course angle of a large target can be more accurately refined. And finally, the problem of insufficient detection accuracy of pedestrians, buses and trucks in a complex traffic scene is solved.

This application provides a pedestrian detection method, a method for training a pedestrian detection model, an electronic device, and a computer-readable storage medium. The pedestrian detection method includes: acquiring an image to be recognized; inputting the image into a multi-task recognition network to acquire a predicted pedestrian location and a predicted pedestrian attribute in parallel; and correlating the predicted pedestrian location and the predicted pedestrian attribute to output a detection result. The pedestrian detection method utilizes the multi-task recognition network to acquire the predicted pedestrian location and the predicted pedestrian attribute in parallel, and the detection result containing the predicted pedestrian location and the predicted pedestrian attribute is acquired only by inputting the image to be recognized once, thereby improving detection efficiency, quickly obtaining the detection result and saving device resources.

The invention relates to a dense pedestrian detection method for a traffic scene, and belongs to the technical field of machine vision, and the method comprises the following steps: S1, collecting pedestrian images of the traffic scene, and constructing a training and testing data set; s2, constructing a pedestrian detection network, fusing high and low frequency attention and a bidirectional feature fusion module, and introducing a target frame matching strategy; s3, preprocessing the image, and inputting the preprocessed image into a detection network training model; and S4, deploying the trained model to a traffic monitoring system to realize pedestrian detection. The method improves the detection precision and the calculation efficiency, still has the precise detection capability in a complex background and a dense shielding environment, and can be applied to an intelligent traffic monitoring and automatic driving system.

The invention is suitable for the technical field of pedestrian detection, and particularly relates to a pedestrian detection method and system based on computer vision, and the method comprises the steps: constructing an intersection basic model; carrying out image acquisition through a binocular camera, carrying out distance measurement and calculation, determining the position of each object in a picture, and generating an intersection standard model; defining a pedestrian detection area, identifying pedestrians in the pedestrian detection area through a binocular camera, marking each pedestrian, and calculating a motion prediction track of each pedestrian; and identifying each vehicle, calculating a motion prediction track of the vehicle, carrying out sight shielding checking and track checking, and sending out warning information based on a checking result. According to the invention, the binocular camera is used for determining the driving tracks of pedestrians and vehicles, and when the sight is blocked, the vehicle is warned through the warning information, so that traffic accidents caused by the sight blocking are avoided, and the traffic safety is improved.

The invention belongs to the field of machine learning and target detection, and discloses an infrared and visible light fusion pedestrian detection method based on weight autonomous optimization. According to the method, feature extraction is carried out on infrared and visible light images through a convolutional neural network; and through a learnable proportionality coefficient, the extracted features are superposed back to the original image according to respective proportions. In the feature fusion stage, the fusion proportion of the infrared and visible light modes is dynamically adjusted through a learnable fusion weight coefficient. In the training stage, end-to-end optimization is carried out by using a large-scale annotation data set, so that the superposition proportion and the fusion weight alpha of each mode can be adaptively adjusted to adapt to different illumination conditions and scene changes, and the generalization ability of the model is remarkably improved. In a robot vision system for night pedestrian detection, an infrared and visible light modal fusion method based on machine learning weight optimization is adopted, and the accuracy and robustness of pedestrian detection are effectively improved.

The invention discloses a multistage voxel adaptive laser radar pedestrian tracking method, which comprises the following steps: S1, acquiring laser radar point cloud data, and adding ground filtering and elevation filtering; s2, performing hierarchical voxel grid processing on the basis of the point cloud data after ground filtering and elevation filtering, inputting the point cloud data after hierarchical voxel grid processing into a DV-Det model to detect a point cloud pedestrian target of a current frame, and adding a Soft-NMS for post-processing optimization; s3, designing an unscented Kalman filter based on a pedestrian kinematics equation, predicting the motion state of a pedestrian target, and adding a joint probability data interconnection algorithm and an adaptive life cycle management strategy; and S4, the mass center of the pedestrian target is calculated and detected, the relative position and the movement speed of the pedestrian target are solved, and a display panel of pedestrian state information is added to a visual interface. In conclusion, the defects in the prior art are overcome, high-precision and low-delay pedestrian detection and tracking can be achieved in multiple indoor and outdoor scenes, and the method has high social use value.

The invention belongs to the field of computer vision, and particularly relates to a YOLOv8-based lightweight dense pedestrian detection method and system, and the method comprises the steps: carrying out the pedestrian detection of a dense pedestrian image shot from a high altitude through employing a YOLOv8-based lightweight target detection model, the lightweight target detection model based on YOLOv8 comprises a lightweight backbone network, a lightweight spatial information sensing module and a lightweight multichannel compression decoupling head. According to the method, the parameter quantity and the calculation quantity of the detection model are reduced, and the detection accuracy rates of the detection model in a Crown human data set and a Widder Person data set are respectively improved by 1.8% and 1.6%.

The invention provides a time-space correlation multi-camera personnel tracking method and system, and the method comprises the steps: obtaining video streams of all cameras in a scene, carrying out the frame-by-frame detection of the video streams through a detection module based on a deep learning model, and obtaining pedestrian detection samples under different cameras at the current moment and corresponding appearance features. Associating the detection sample with a historical tracking trajectory to obtain a trajectory in each single camera; and carrying out inter-camera association on the trajectory in the single camera by combining a pedestrian re-identification ReID technology and homography-based spatial constraint to obtain a complete tracking trajectory of the current frame. According to the method, in the aspect of position representation of the trajectory, 2D Kalman prediction is used in an image plane, meanwhile, the 3D space position of the trajectory is predicted and tracked, and the trajectory position can be accurately drawn and output.

The invention discloses a multi-pedestrian target detection method based on a YOLOCDG network in a complex scene, and aims to solve the problems of small target missing detection, model redundancy and inaccurate positioning in multi-pedestrian detection in a scene with dense people flow and serious shielding. The method comprises the following steps: firstly, based on YOLOv8, deleting a redundant convolution fusion layer of a backbone network, adjusting the size of a detection head, and simplifying a framework to reduce small target feature dilution; secondly, designing a context attention module CoAM and embedding the CoAM into a backbone network, and enhancing feature distinction degree in a shielding scene by capturing cross-target context association of dense pedestrians; thirdly, an improved C2fG module is proposed to replace a neck C2f module, the parameter quantity is reduced, and the detection performance and the edge deployment efficiency in a complex scene are balanced; then, an SPPFDSC multi-scale fusion layer containing depth separable convolution is designed, an original SPPF layer is replaced, and fine-grained feature perception of small-size pedestrians in the distance is enhanced; and finally, optimizing a bounding box loss function by adopting WIOU v3, improving the target positioning precision in the dense people stream, and finally constructing a multi-pedestrian detection model.

The invention belongs to the field of computer vision and artificial intelligence security, and discloses a self-adaptive frequency domain adversarial training method and device for a target detector, the target detector comprises a repair module and a pedestrian detector which are connected in series, and the input of the repair module is connected with the output of a patch detector; the self-adaptive frequency domain adversarial training method comprises the following steps: losses in joint training comprise standard target detection losses, repair consistency losses on a frequency domain based on a frequency domain image corresponding to a training image and a clean image, and repair dependence losses based on a detected average precision mean value; according to the invention, the end-to-end joint training is carried out through the restoration module and the subsequent pedestrian detector, and the optimization target of the restoration module is directly aligned with the improvement of the detection robustness, so that the confrontation disturbance is eliminated as far as possible, and meanwhile, the key semantic information of the detection task is reserved to the maximum extent. The separation of the performance of the repair module and the pedestrian detector is avoided, and the detection robustness is improved.

The invention relates to an elevator group control system scheduling method based on improved YOLOv10, and belongs to the technical field of intelligent elevator control and computer vision crossing. The elevator group control system scheduling method comprises the following steps that S1, pedestrian images of indoor elevator corridor scenes are collected, and a training set and a test set are constructed; s2, the YOLOv10 network is improved; s3, training the improved YOLOv10 network by using the training set to obtain a pedestrian detection model, and testing by using the test set; s4, the trained pedestrian detection model is used for actual pedestrian detection in the elevator floor; and S5, counting the number of pedestrians on each floor according to a detection result, and dynamically adjusting an elevator scheduling strategy according to the distribution of the number of pedestrians on high and low floors. According to the method, the detection capability of the network on the shielded pedestrians is enhanced, the pedestrian detection precision is improved, and the operation efficiency of the elevator and the riding experience of passengers are remarkably improved.

The invention relates to a scenic spot flow prediction method for scenic spot tourist tracks, and belongs to the technical field of flow prediction, and the method comprises the following steps: S1, laying a video image access network in a scenic spot, including a server and cameras installed at key scenic spots, playing points and entrances and exits of the scenic spot in the scenic spot; s2, performing pedestrian detection and pedestrian re-identification retrieval on the video acquired by the video image access network; detecting and marking pedestrian IDs by cameras arranged at entrances and exits of scenic spots, and obtaining video image information of tourists of the pedestrian IDs appearing in the scenic spots through pedestrian re-identification; s3, constructing a scenic spot trajectory time spectrogram, and obtaining a trajectory route statistical graph based on the adjacency relation directed graph; and S4, constructing a scenic spot trajectory flow diagram time sequence and a scenic spot flow prediction model, and performing prediction and early warning on each scenic spot line and scenic spot flow in the scenic spot.

The invention discloses a multi-pedestrian target detection method based on an unmanned aerial vehicle, and the method comprises the steps: (1) collecting pedestrian video data of the unmanned aerial vehicle, carrying out the frame extraction preprocessing, and marking a pedestrian bounding box, a type, and a confidence coefficient; (2) constructing a YOLOv8 optimization network, wherein a neck network of the YOLOv8 optimization network is integrated with a feature enhancement module, a channel reweighting module and a spatial context sensing module; (3) designing a ternary loss function fusing intersection-to-union ratio, center distance and length-width ratio constraints, wherein the ternary loss function comprises position, category and confidence loss; (4) training the network to converge by adopting a gradient descent method; and (5) deploying the model to the unmanned aerial vehicle to realize real-time detection. According to the method, by improving the network structure and the loss function, the pedestrian detection precision in a complex scene is remarkably improved, efficient data support is provided for an intelligent traffic system, and pedestrian safety guarantee and traffic management efficiency are enhanced.

The invention provides a target detection method and system and a storage medium, and relates to the field of object detection, and the method comprises the steps: obtaining image data and laser radar scanning data corresponding to a current scene; calling a first pedestrian detection model based on an image to carry out pedestrian detection on the image data to obtain position information of a pedestrian target; calling a second pedestrian detection model based on point cloud data to carry out pedestrian detection on the laser radar scanning data to obtain pose information of a pedestrian target; and calling an external parameter matrix to match the position information and the pose information, and outputting three-dimensional position information of the pedestrian target in a space coordinate system. According to the invention, the detection and positioning of the pedestrian target can be realized without using a high-cost depth camera and a three-dimensional laser radar, and the detection precision of the pedestrian target is improved through two different modal data.

The invention discloses a long-distance identity recognition method for a large area, which belongs to the technical field of computer vision and comprises the following steps: S1, initializing a system; s2, collecting video data; s3, pedestrian detection and segmentation; s4, performing gait recognition; s5, multi-target cross-camera tracking is carried out; and S6, result output and application service. According to the invention, an effective solution is provided for large-scene video intelligent security and protection in a complex environment of a park, the accuracy and traceability of personnel identity recognition in a high-risk area are ensured, and the safety production level of the park is improved; a long-distance multi-target identity recognition scheme is provided, real-time monitoring and early warning of illegal person invasion in key protection areas are achieved, and reliable safety guarantee is provided for public places.

The invention discloses a pedestrian detection method based on YOLOv7, and relates to the technical field of image recognition, and the method comprises the following steps: constructing a data set D, and dividing the data set D into a training set DLLVIP-train, a test set DLLVIP-test and a verification set DLLVIP-val; preprocessing images in the data set LLVIP by adopting a Mosaic data enhancement technology, and unifying image sizes to obtain a data set LLVIP '; a network model PCAM-YOLOv7 is constructed; all the images in the data set LLVIP'are sequentially input into the network model PCAM-YOLOv7, and prediction information of a bounding box of each image is obtained; using the training set DLLVIP-train to train a network model PCAM-YOLOv7, and using the training set DLLVIP-train to train a network model; according to the method, the PAELAN module fusing the partial convolution and the Shuffle Attention mechanism, the CCBS module fusing the coordinate convolution and the SPPCSPCATT module fusing the Shuffle Attention mechanism are adopted, the shielded pedestrian target can be efficiently and accurately recognized, and the detection accuracy is remarkably improved.

The invention provides a subway platform edge behavior abnormity real-time identification and early warning method based on deep learning, and relates to the technical field of deep learning, which comprises the steps of obtaining real-time video data, performing pedestrian detection and track extraction, calculating behavior characteristic parameters and a dynamic distance threshold value, performing danger grade division on pedestrians, and performing early warning and early warning. According to the method, time sequence feature extraction is carried out on potential dangerous targets, a behavior abnormity scoring mechanism is established, timely early warning of abnormal behaviors is realized, the accuracy and real-time performance of safety monitoring of the subway platform can be effectively improved, and the occurrence rate of safety accidents can be reduced.

The invention relates to the technical field of automatic driving, in particular to an automatic driving system based on pedestrian motivation and a control method, and the system comprises a data acquisition module, a pedestrian detection module, a pedestrian intention reasoning module and a vehicle control module. The data acquisition module is used for acquiring a video sequence and environment information of a traffic intersection when the intelligent driving vehicle drives to the intersection without the signal lamp. The pedestrian detection module detects pedestrians through video processing and a pedestrian recognition strategy and outputs pedestrian inter-frame images. The pedestrian intention reasoning module classifies pedestrian crossing motivations based on the trajectory and attitude information of pedestrians. The vehicle control module dynamically adjusts the vehicle speed according to the pedestrian motivation type and automatically brakes when necessary so as to ensure that pedestrians safely pass through the intersection. According to the system, self-adaptive comity of the intelligent driving vehicle to pedestrians at the intersection without signal lamps is realized, and the traffic safety and the adaptive capacity of intelligent driving are effectively improved.

The invention provides a pedestrian detection method and device, equipment, a storage medium and a product. The method comprises the steps that a preset neural network model used for pedestrian detection and a to-be-detected image are acquired, the preset neural network model comprises a backbone network, a neck network and a head network, and the backbone network comprises variable kernel convolution; inputting the to-be-detected image into the backbone network, and performing feature extraction on the to-be-detected image through the variable kernel convolution and other modules to obtain image feature information; and performing pedestrian detection on the to-be-detected image based on the image feature information through a neck network and a head network in the preset neural network model to obtain a pedestrian detection result.

The invention provides a single-mirror pedestrian height change perception and adaptive state perception Re-ID tracking method and system. The method comprises the following steps: acquiring a video stream and extracting a video frame; pedestrian detection is carried out on each video frame, and corresponding pedestrian features are extracted according to a pedestrian detection result; judging the confidence coefficient of each detection frame, and constructing a track instance when the confidence coefficient of each detection frame is greater than a threshold value; calculating an adaptive state sensing Re-ID cost matrix and a height change weighted intersection-to-parallel ratio cost matrix to obtain a final cost matrix; performing Hungary matching on the cost matrix to search the most matched trajectory instance for each pedestrian detection object; and integrating the track state, the track updating state and the detection frame state of the current time frame, and updating the track attribute. According to the method, hidden constraints of height changes of the detection frame and the tracking frame are considered, weights of the height changes are added on the basis of area constraints, and the problem of identity switching when pedestrians are shielded can be better solved.

The invention discloses a light-weight unmanned forklift AI visual anti-collision method based on a domestic embedded platform, and the method comprises the following steps: S1, carrying out the preprocessing of an RGB image through a light-weight pedestrian detection module, carrying out the automatic pruning and compression of a deep convolutional network based on an image recognition algorithm of a light-weight convolutional neural network, and carrying out the recognition of the deep convolutional network; lightweight pedestrian detection features are extracted; s2, using a lightweight pedestrian distance estimation module to extract lightweight pedestrian distance estimation features by model compression through camera calibration, image correction, stereo matching and distance acquisition; s3, performing feature fusion, performing feature analysis in combination with a dynamic adaptive sparse transformation network, and completing multi-pedestrian detection and pedestrian distance estimation by introducing a sparse feature adaptive reconstruction mechanism; and S4, deployment is carried out on a domestic embedded platform, and software function module cutting is carried out. According to the invention, a lightweight deep learning algorithm and adaptive feature fusion are adopted, and multi-pedestrian anti-collision detection on a domestic embedded platform is realized.