800 results about "View camera" patented technology

The invention provides a rehabilitation training action evaluation method and device based on multi-view vision. According to the method, a multi-view camera is adopted to synchronously collect a rehabilitation training image sequence, two-dimensional coordinates of key points of a human body are extracted by improving an HRNet deep learning model, three-dimensional reconstruction is performed in combination with a Gaussian process, motion feature data are extracted, and rehabilitation training quality is evaluated. Accurate motion capture without wearing mark points by the patient is realized, the training constraint feeling of the patient is effectively reduced, the rehabilitation evaluation accuracy is improved, and a personalized rehabilitation scheme can be generated.

The invention discloses a mechanical arm positioning and grabbing method based on machine vision, and relates to the technical field of machine vision and mechanical arm control, the method comprises the following steps: synchronously acquiring RGB-D images of a target scene through a multi-view camera array, and generating three-dimensional point cloud data through data fusion; an improved LSD algorithm and a PnP algorithm are adopted to calculate the initial pose of the target object, illumination distortion is eliminated in combination with the generative adversarial network, and three-dimensional coordinates are output; a mechanical arm motion error transfer model is constructed based on Monte Carlo simulation, and a candidate grabbing scheme set is generated through reinforcement learning; and an optimal grabbing scheme is screened through a preset priority evaluation rule, and a mechanical arm joint movement track and a control instruction set are generated. Through multi-modal data fusion and a nonlinear optimization algorithm, the technical problems of large target positioning deviation and sensitive illumination interference in a complex environment are solved, and the grabbing precision and robustness of the mechanical arm are improved.

The invention relates to the technical field of image processing, and discloses an industrial part alignment method and system based on visual analysis and a storage medium. The method comprises the steps that a three-view camera collects an industrial part image, and preprocessing is carried out through gradient magnitude local contrast enhancement to obtain an enhanced image; performing hierarchical feature extraction to identify edge contours and key control points to form a multi-dimensional feature set; and establishing a dynamic reference coordinate system based on the feature set to obtain a part space attitude matrix. And the attitude deviation is compensated through Z-axis offset and rotation coupling error analysis. Posture adjustment is decomposed into a plurality of sub-stages, an alignment track is optimized by adopting a variable speed planning strategy, and accurate alignment of the parts is achieved. The problems that multi-view visual information fusion is insufficient, a special recognition algorithm for geometrical characteristics of the industrial parts is lacked, and Z-axis offset and rotation coupling error compensation is inaccurate in the posture adjustment process are solved, and the precision and stability of alignment of the industrial parts are improved.

The invention relates to the technical field of automatic workpiece grabbing and visual servo control, and discloses a workpiece grabbing method and system based on visual feedback, and the method comprises the steps: obtaining a real-time image through a front-view camera, a side-view camera and a top-view camera, and extracting surface features through a feature fusion network; inputting the features into a pose estimation model based on a particle filtering framework, and iteratively updating the pose in combination with a multi-dimensional observation likelihood function to generate prediction parameters; constructing a multi-target path planning model based on the parameters, and optimizing the path by adopting a dynamic planning algorithm with the shortest path and the minimum joint movement as targets; a hierarchical control model is established, a strategy layer performs global planning, an adjustment layer corrects a local path, and an execution layer realizes trajectory tracking through visual servo control and outputs a control instruction to complete grabbing. Through multi-view perception, robust pose estimation, global optimization path planning and hierarchical control, the precision, efficiency and stability of workpiece grabbing in a complex environment are improved.

The invention relates to the technical field of tunnel engineering construction, and discloses an intelligent material transportation and safety monitoring system and method for shield construction, and the system comprises a visual perception unit, a sensor network module, an AI analysis center module, a safety decision module and a human-computer interaction interface. According to the invention, data acquisition is carried out through the visual perception unit and the sensor network module, multi-target detection operation is carried out on image frames through the AI analysis center module after target identification and track prediction, target types, space coordinates, contour boundaries and confidence coefficients are identified and extracted, and safety judgment and early warning output are carried out. According to the invention, by integrating the multi-view camera equipment and the UWB, GNSS and other sensors and adopting a deep learning target detection algorithm, high-precision identification and continuous tracking can be carried out on construction site personnel, equipment, segments and other key objects, and accurate input is provided for subsequent risk analysis.

The invention relates to the technical field of unmanned aerial vehicle autonomous control, and discloses an unmanned aerial vehicle obstacle avoidance control method and system based on computer vision, and the method comprises the steps: collecting the multi-view image data of a flight environment in real time through a multi-view camera, and carrying out the preprocessing; using an improved YOLOv7 network to identify obstacles in the preprocessed image, and extracting position, size and motion information of the obstacles; generating a three-dimensional environment map and a plurality of candidate obstacle avoidance paths in combination with the flight parameters of the unmanned aerial vehicle and the extracted obstacle information; an optimal path is screened based on a dynamic safety evaluation model, and the attitude and power output of the unmanned aerial vehicle are adjusted in real time to complete obstacle avoidance; an obstacle avoidance effect is verified by using an optical flow method and depth information, and path planning is dynamically corrected. According to the method, the dynamic safety evaluation model is introduced, multi-dimensional factors are comprehensively considered, the safety of each path is dynamically determined, and it is ensured that the flight path of the unmanned aerial vehicle can be timely and accurately modified and optimized in a dynamic complex environment.

The invention discloses a public transport passenger flow monitoring method and system based on human body detection, and the method comprises the steps: synchronously collecting skeleton key points, heat distribution and contour features of passengers through a vehicle-mounted multi-view camera and an infrared sensor, and generating a passenger space-time feature matrix; outputting a passenger movement track set based on the passenger space-time characteristic matrix; generating a dynamic congestion degree index according to the staying duration and the spatial distribution density of the passengers in the passenger movement track set; calculating an abnormal behavior probability based on the dynamic congestion degree index, and outputting an abnormal event early warning signal; and fusing the dynamic congestion degree index, the abnormal event early warning signal and the real-time passenger flow data, and generating a bus passenger flow monitoring result through space-time correlation analysis. According to the embodiment of the invention, high-precision, low-delay and intelligent passenger flow state monitoring and abnormity early warning can be realized.

The invention discloses a three-dimensional attitude high-precision acquisition and reconstruction system for exercise training, which relates to the technical field of three-dimensional attitude acquisition and reconstruction and comprises a camera calibration module, an image acquisition module, a key point extraction module, a three-dimensional reconstruction module, an attitude optimization module, a data fusion module and a feedback generation module. The camera calibration module is used for performing internal and external parameter calibration on a multi-view camera assembly by adopting a self-adaptive joint calibration method to obtain a projection matrix parameter and a transformation matrix of each camera; the image acquisition module is used for synchronously acquiring multi-view video images of the athlete in the training process based on the calibration parameters, and performing timestamp alignment processing to obtain an original image sequence; and the key point extraction module is used for detecting and identifying a human body image by adopting a deep learning model, extracting two-dimensional coordinates of key human body joint points of each frame from an original image sequence, and obtaining a two-dimensional key point set under each view angle.

The invention discloses a target detection method and device based on an aerial view, equipment, a medium and a product. The method comprises the following steps: extracting multi-scale features for an input image of a multi-view-angle surround-view camera; converting the point cloud data of the laser radar into a sparse voxel structure and generating BEV features for voxel features; fusing the multi-scale features and the BEV features to obtain fused BEV features; road topology and semantic information are extracted according to the fused BEV features, and a map is generated; and determining a three-dimensional bounding box and a motion state of the traffic participant according to the fused BEV features and a prediction result of the position of the traffic participant in the map. According to the technical scheme, multi-scale geometric features, BEV features and semantic information are fused, time sequence features of dynamic target detection and static map segmentation are synergetic, the reliability of target detection based on aerial view is improved, and the method is suitable for multi-task BEV perception of three-dimensional object detection, high-precision map segmentation and motion prediction.

The invention discloses a calibration method, system and device for a vehicle around-view camera and a computer medium, and relates to the technical field of image processing, and the method comprises the steps: collecting a calibration plate image obtained after a calibration plate is shot by the around-view camera on a vehicle; projecting the calibration plate image to a world coordinate system to obtain a distorted image; selecting an initial angular point in the distorted image according to the calibration plate; projecting the initial angular point to a fisheye image coordinate system of a look-around camera to obtain a target angular point; according to the target angular point, generating an initial external parameter of the look-around camera; in the calibration plate image, extracting overlapped corner point parameters in the overlapped shooting area; and based on the initial external parameter, generating a target external parameter which enables the error between the overlapping angular point parameters to be minimum, and taking the target external parameter as the external parameter of the surround-view camera. According to the method, the extraction precision and robustness of the angular points are improved, the continuity and smoothness of the images shot by the surround view camera are improved, splicing gaps and dislocation phenomena are reduced, and the calibration result of the vehicle surround view camera is more accurate.

The invention belongs to the field of computer vision, and particularly relates to a method, a device and a system for monitoring suction-scrabbling falling of a cleaning robot, and the method comprises the following steps: 1) a rear-view camera arranged on the cleaning robot collects suction-scrabbling images, and carries out data labeling; 2) building a deep learning labeling and training environment in a server or a workstation, selecting a YOLOv8 target detection network model, sending labeled suction and scrabbling image data into the model for training, and performing format conversion and quantization on the model after the training is completed; 3) inputting an image acquired in real time into the trained target detection model, and judging whether the suction rake falls off or not; (4) if the suction scrabbling device falls off, the upper computer sends falling abnormal information to a robot controller of the cleaning robot, and the robot controller controls a hub motor to brake emergently; and meanwhile, the upper computer transmits the abnormal information of the suction-scrabbling falling and the position coordinate information of the robot in the global map to the operation and maintenance personnel through the cloud platform and then transmits the abnormal result and the position information of the suction-scrabbling falling to the operation and maintenance personnel.

The invention provides a camera three-dimensional target detection method and system based on multi-modal distillation, and relates to the technical field of target detection, and the method comprises the steps: determining a trained multi-modal teacher model employing a point cloud and a multi-view camera image as the input, performing cross-modal comparison distillation on the constructed student model taking the multi-view camera image as the input by using the point cloud features in the teacher model, so that the student model has the space geometry reasoning ability to construct the false point cloud features, and performing multi-modal adaptive smooth distillation to obtain the multi-view camera image. And aligning student model features obtained based on heterogeneous fusion of the false point cloud features and the image features and teacher model features obtained based on channel fusion of the point cloud features and the image features, when the regression output of the teacher model is superior to the regression output of the student model, selecting to distill the regression frame knowledge into the student model, and through the above training process, obtaining the teacher model. The structure consistency of the student model and the teacher model can be ensured, and the three-dimensional target detection accuracy of the student model is improved.

The invention provides a traffic track deformation detection method and system based on multi-modal three-dimensional point cloud fusion, and relates to the technical field of data processing, and the method comprises the steps: carrying out the track data collection through a multi-view camera and a laser radar which are integrated on a track detection vehicle; configuring the dynamic credibility of the time sequence multi-modal data set, and performing time sequence data three-dimensional point cloud fusion on the time sequence multi-modal data set; establishing a driving data set; and performing target attention detection on the three-dimensional point cloud fusion result and the driving data set by using a multi-modal three-dimensional target detection network, and outputting a three-dimensional bounding box and classification confidence of the track deformation region according to a target attention detection result. The technical problem that the accuracy of track deformation detection is low due to the fact that the precision of multi-source data fusion is insufficient is solved, the precision of data fusion is improved through multi-modal data fusion, the fused data is detected through the multi-modal three-dimensional target detection network, and the timeliness and accuracy of track detection are improved.

The invention provides a scene semantic occupancy prediction method based on probabilistic three-dimensional Gaussian, and the method comprises the steps: processing a multi-view camera image through employing a two-dimensional backbone network, generating multi-view and multi-scale image features, predicting the three-dimensional occupancy distribution aligned with pixels through the image features, and initializing the position attribute of the three-dimensional Gaussian according to the distribution; the method comprises the following steps: taking three-dimensional gauss as point cloud data, generating sparse voxel data through voxelization, and processing the sparse voxel data by using three-dimensional sparse convolution to complete feature interaction between the three-dimensional gauss; by using a cross attention mechanism, updating three-dimensional Gaussian features by image features; performing layer-by-layer iterative optimization on each attribute in the three-dimensional Gaussian features by using a Gaussian attribute fine tuning model; and aggregating geometric attributes and semantic attributes of the three-dimensional Gaussian by using a probability Gaussian superposition method, and generating a three-dimensional semantic occupation prediction result of the scene. According to the invention, the problem of efficient adaptive three-dimensional semantic occupancy prediction of an automatic driving scene can be solved.

The invention relates to a tunnel three-dimensional holographic splicing method and device for panoramic array camera networking, and the method comprises the steps: enabling a reference transmission camera array and a three-dimensional laser scanner on an inspection vehicle to move to different inspection positions along with the inspection vehicle for adjustment, achieving the transmission of peripheral control information at two ends of a tunnel into a measurement region, and constructing a dynamic control field; the limitation on measurement conditions is reduced; high-precision positioning and attitude determination are carried out based on fixed connection constraints of a look-around camera array and a three-dimensional laser scanner and a constructed dynamic control field, so that a measurement platform is unified to a global coordinate system, and the inherent defect of large accumulative error of a traditional three-dimensional modeling method is effectively avoided; and then the high-resolution look-around image is mapped to the three-dimensional point cloud data under the global coordinate system, so that high-resolution and high-precision three-dimensional holographic splicing of the tunnel ring surface under the global coordinate system is realized, global and local high-resolution and high-precision are achieved, and the acquisition precision of the tunnel three-dimensional hologram is greatly improved.

The invention relates to the technical field of sports artificial intelligence and data management, in particular to a physical exercise AI standing long jump evaluation data management system which comprises a dynamic environment calibration module, a multi-mode identity recognition module, a three-dimensional posture analysis module and the like. The dynamic environment calibration module uses a multispectral sensor array and a deep learning algorithm to establish a dynamic coordinate system without fixing a marker; the multi-mode identity recognition module fuses gait and face features to realize non-contact identity authentication; the three-dimensional attitude analysis module performs high-precision modeling and analysis on the long jump action through a multi-view camera and an advanced algorithm; the intelligent violation determination engine combines rules and an AI model, automatically identifies violation behaviors and can dynamically adjust determination criteria. The method gets rid of the limitation of a traditional evaluation mode, realizes high-precision and intelligent evaluation, effectively solves the problems of poor environmental adaptability, inaccurate identity authentication, unguaranteed data security and the like, and is scientific and reliable in evaluation result and safe and efficient in data management.

Disclosed herein is a point of view camera system. The point of view camera system includes a camera mount configured to attach to a headwear, the camera mount including a base configured to secure the camera mount to the headwear, a first camera including a first image sensor and a first camera lens, a second camera including a second image sensor and a second camera lens, and a camera housing configured to attach to the camera mount. The camera housing includes a first opening configured to receive and secure the first camera and a second opening configured to receive and secure the second camera.

The invention provides an intelligent heavy truck end-to-end driving method based on focus attention and probabilistic game, and belongs to the technical field of intelligent driving. The method comprises the following steps: firstly, acquiring multi-source data such as a laser radar, a look-around camera, an IMU (Inertial Measurement Unit) and a load signal, and generating an anti-jitter space-time BEV feature through cross-dimensional position coding based on motion compensation, near-field non-uniform sampling, focus attention and time sequence fusion; then, vectorization decoding is carried out on the features to obtain obstacle vehicle movement and map element vector information. And finally, on the basis of the expert track prior space, probability game interaction is carried out through multi-round iterative prediction and planning, a self-vehicle track conforming to heavy truck variable load dynamics constraints is generated, and the self-vehicle track is output after safety verification. According to the method, the problems of heavy truck high-position sensor vibration distortion, hinge structure blind area and trajectory planning under the large-inertia variable-load working condition are effectively solved, and the driving safety and robustness are remarkably improved.

A vehicular driver monitoring system includes a vehicular interior rearview mirror assembly having a mirror head that accommodates a mirror reflective element. A video display is disposed behind the mirror reflective element and operable to display video images captured by a rearward viewing camera of the vehicle. A driver monitoring camera and a near infrared light emitter are accommodated by and move in tandem with the mirror head. The near infrared light emitter is accommodated within the mirror head so that, with the mirror head adjusted relative to the mounting base to set the rearward view of the driver of the vehicle, a beam of near infrared light emitted by the near infrared light emitter is directed toward a driver's region of the vehicle. The driver monitoring camera is disposed adjacent to the video display screen so as to not view through the video display screen.

The invention belongs to the technical field of laser radar-camera panoramic segmentation, and particularly relates to a multi-mode panoramic segmentation method for multi-view space-time alignment and implicit feature interaction, and the method is executed by a multi-mode panoramic segmentation network, and comprises the steps: S1, obtaining laser radar point cloud data and multi-view camera image data in the same scene; s2, performing double-branch feature coding on the laser radar point cloud data; performing multi-scale image feature extraction on the camera image data; s3, generating false point cloud features with geometric perception capability; s4, generating semantic pixel features; s5, performing implicit fusion on the pseudo point cloud features generated in the S3 and the semantic pixel features generated in the S4 to obtain cross-modal fusion features; and S6, based on the cross-modal fusion features obtained in the S5, generating a unified panoramic segmentation result containing semantic tags and instance IDs. The method can effectively improve the robustness and precision of multi-mode panoramic segmentation in a complex urban environment.

The invention provides a multi-view camera image and laser radar fused road perception method and system. The method comprises the steps of obtaining depth information features of a camera aerial view and depth information features of a laser radar aerial view based on a vehicle-mounted camera multi-view image and laser radar point cloud data; obtaining camera aerial view features with depth distribution based on the depth information features of the camera aerial view and the depth information features of the laser radar aerial view; performing feature alignment on the camera aerial view features with depth distribution and the camera aerial view features without depth distribution to obtain camera aerial view image features with depth information representation; and obtaining a prediction result based on the camera aerial view image features containing the depth information representation and the depth information features of the laser radar aerial view. According to the invention, the road condition of the current scene is inferred and predicted in real time through the image of the vehicle-mounted camera during vehicle driving, and the current driving road condition is sensed in real time under the unstructured road condition with limited visual field and severe environment.

The invention relates to the technical field of garbage classification detection, and discloses a garbage classification supervision system based on multi-sensor fusion, which comprises a multi-view camera, an ultrasonic sensor, an edge calculation layer and an execution layer, the edge calculation layer comprises a data acquisition module, a human body feature detection module, a garbage classification detection module and a garbage overflow detection module; the garbage classification detection module performs garbage classification detection and identification on video image data in target data based on an improved visual Transform algorithm and a front-back time sequence comparison algorithm, so that model updating is automatically started under low-confidence alert, disastrous forgetting is effectively prevented, and meanwhile, the real-time performance and high precision of the system are kept.

The invention relates to the technical field of digital image processing and computer vision, and discloses a remote multi-view video stitching and monitoring method and system based on digital twinning, and the method comprises the steps: constructing a digital twinning model containing geometric, material and semantic information, and calibrating and initially registering a multi-view camera; based on the model and camera parameters, collecting a preprocessed video stream, and refining the camera pose in combination with the model; predicting expected visual content by using the model and the refined pose, and performing non-rigid alignment on the preprocessed video frame; based on the aligned video frames, a model semantic optimization splicing suture line is utilized to generate a reconstructed video, and information loss is repaired in combination with a model context; and finally, performing integrated monitoring interaction on the repaired reconstructed video and the digital twin model, comparing and detecting abnormality, and updating the model by using the reconstructed video. According to the invention, the problems of traditional remote monitoring in the aspects of scene comprehensive perception, intelligent anomaly detection and synchronism of environment digital representation and physical reality are solved.

The invention discloses a tobacco logistics carbon emission real-time monitoring method and system based on AI visual identification. According to the method, vehicle operation videos and equipment working state images in a logistics park are collected in real time through a multi-view camera, sensor data are synchronously obtained, and multi-source data fusion is achieved through a time alignment and normalization method. A space-time fusion network model is constructed, the idle speed state of a fuel vehicle is detected by using improved YOLOv7, equipment energy consumption time sequence characteristics are analyzed in combination with Transform, and a space correlation model between equipment is established through a graph convolutional network. And inputting the extracted features and power data into a TCN-LSTM-Attention model subjected to Bayesian optimization, calculating real-time carbon emission, and dynamically adjusting model parameters based on a result. And finally, the edge-cloud collaboration platform generates hierarchical alarms and feeds back regulation and control instructions to form a closed-loop control loop. According to the invention, accurate monitoring and intelligent optimization of carbon emission in the whole process of tobacco logistics are realized, and an innovative solution is provided for green logistics.

This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, an image processing method includes receiving image frames; determining an ordered set of neural rays based on the image frames; determining a graph network that represents each neural ray of the ordered set of neural rays as a sequence of points; and determining a feature set based on the graph network. Each neural ray of the ordered set of neural rays represents three-dimensional positions of pixels of an image frame. Each point on the graph network is associated with a node of a plurality of nodes of the graph network. The feature set includes features of each of the image frames. Other aspects and features are also claimed and described.

A three-dimensional scene local editing method based on text control comprises the steps that a three-dimensional Gaussian semantic field is constructed based on text query, and accurate three-dimensional object masks are directly generated by embedding semantic features into anisotropic Gaussian primitives and combining multi-view semantic supervision and cosine similarity calculation of a CLIP model; screening an effective view angle by taking a target object as a center, determining an effective view angle range through azimuth clustering analysis and kernel density estimation, and generating a continuous dense surround-view camera track; an image grid technology is adopted to organize and edit visual angles, a submerged space alignment module GLAM fusing global-local attention is utilized to synchronously process multiple frames of images, style benchmarks are unified and geometric consistency is enhanced through a cross-visual-angle attention mechanism, a multi-visual-angle consistent editing result is generated, and only Gaussian parameters corresponding to a target object are finely adjusted, so that the target object can be edited more accurately. And the background area is kept unchanged. According to the method, the boundary definition of local editing is remarkably improved, and efficient and accurate three-dimensional content modification of a multi-target complex scene is achieved.

The invention provides a lane lighting method based on vehicle visual perception, a storage medium and a system. The method comprises the following steps: analyzing a road image collected by a vehicle front-view camera; when the lane type in front of the vehicle is identified as a curve, determining the position of a center line of a curve entrance; an initial illumination angle is calculated according to the road curvature and the current illumination angle of the headlamp, and the transverse offset of the vehicle in the lane is calculated according to the position of the center line and the real-time position of the vehicle; and calculating an angle adjustment coefficient of the headlamp according to the transverse offset and the vehicle speed, adjusting the initial illumination angle according to the angle adjustment coefficient to obtain a target illumination angle, and controlling the headlamp to illuminate according to the target illumination angle. According to the method, the illumination angle of the headlamp in the curve scene is accurately adjusted, so that a driver can clearly see the curve boundary at night, the driver is assisted in judging the distance between the vehicle and the curve boundary, and the driving safety is improved.

The application relates to the technical field of blind area monitoring, and relates to a low-speed blind area monitoring method and system based on multi-view camera shooting, which comprises the following steps: registering multiple cameras in a vehicle to obtain a target vehicle and a vehicle coordinate system; confirming multiple early warning coordinates based on the vehicle coordinate system, a vehicle bird's eye view and the vehicle; confirming a candidate window based on the vehicle bird's eye view and the early warning coordinates; performing target detection on the candidate window by using a pre-constructed target detection model to obtain a detection result; if the detection result is a first result, taking a pre-constructed safety instruction as a target instruction; otherwise, confirming relative positions and relative speeds based on target bounding boxes in a second result and multiple radars in the target vehicle; calculating an expected collision time according to the relative positions and the relative speeds; confirming the target instruction based on the expected collision time; and summarizing the target instruction to obtain multiple target instructions, thereby completing low-speed blind area monitoring. The application can improve the precision of low-speed blind area monitoring.

The invention discloses an automatic labeling method and system for small target detection data, a storage medium and electronic equipment, and the method comprises the steps: carrying out the target detection of a collected narrow-field camera image through a target detection model, obtaining a large target detection bounding box of the narrow-field image, carrying out the image registration of the wide-field camera image, and obtaining a large target detection bounding box of the narrow-field image; the method comprises the following steps: acquiring a homography matrix for converting a narrow-field-of-view image into a wide-field-of-view image, a registered narrow-field-of-view camera image and a wide-field-of-view small target bounding box before adjustment, and adjusting the position of the wide-field-of-view small target bounding box to obtain an accurately labeled small target bounding box. And training the target detection model by using the accurately labeled small target bounding box to obtain a trained small target detection model. According to the method, the labeling precision of the small target detection data is improved, and labeling missing is reduced.

The invention relates to the technical field of food safety supervision, in particular to a food processing visual monitoring system and method based on order tracing, and the system comprises an intelligent collection terminal, a space-time coding server, a block chain evidence storage platform, an exception handling module and a user access terminal. The intelligent acquisition terminal comprises a multi-view camera array, a temperature sensor and an edge calculation module; the space-time coding server encrypts and binds order information with a three-dimensional space, and the block chain evidence storage platform stores video slices and associated metadata to generate a time sequence block chain record; the exception handling module automatically triggers order blocking and illegal evidence storage based on AI identification; and the user access terminal checks the video stream through the traceability code to implement dynamic privacy protection. Accurate tracing is realized through space-time encryption binding triggered by an order, edge calculation key frame extraction optimization storage and block chain evidence storage are combined, cross-system cooperative supervision is supported through dynamic privacy protection, and efficient, safe and low-cost food processing monitoring is realized.