1839 results about "Optical flow" patented technology

The invention discloses an industrial surface defect detection method based on multi-scale feature fusion, and the method comprises the steps: collecting the multi-source data of a detected surface in real time through a multi-modal sensor array, and forming a structured data set through time-space synchronization and denoising; constructing an adaptive geometric correction model to realize spatial transformation and scale normalization of multi-scale features, and cooperatively realizing cross-modal alignment and preliminary fusion through texture and physical attribute branches of a double-flow decoding network; dynamically reweighting the fusion features based on a defect physical model, strengthening physical mechanism defect characterization and suppressing interference; combining optical flow compensation and three-dimensional convolution to extract spatio-temporal evolution characteristics, and forming dynamic defect characterization; and finally outputting defect type and severity evaluation through the classification model in combination with the process parameter library. Therefore, the adaptability of the method to a complex industrial environment is enhanced, and the detection stability can be maintained under different materials, illumination conditions and dynamic interference.

The invention provides an intelligent event identification method and system based on a high-speed camera, and the method comprises the steps: setting the collection parameters of the high-speed camera, and triggering the camera to collect a target scene video stream. And hardware acceleration decoding processing is carried out on the collected original video data stream, real-time environment illumination information of the environment illumination sensor is obtained, and dynamic brightness equalization processing is executed. And performing motion adaptive denoising processing on the video sequence. Geometric distortion correction is carried out on the image sequence through camera calibration parameters, sub-pixel-level displacement vectors and dense optical flow field data of a moving object are extracted, and multi-scale morphological features are extracted. And the features are fused to generate motion feature data, the data are processed through a spatio-temporal joint event classification model, an event identification result is output, the result is bound with a high-precision timestamp, and event identification information is output to an industrial control system display device in real time. According to the invention, the accuracy and real-time performance of event identification can be improved.

The invention relates to the technical field of video behavior recognition, and discloses a behavior recognition and early warning system for a real-time video stream. The system comprises a spatio-temporal feature modeling module, a behavior fragment extraction module, an anomaly propagation modeling module, a risk area positioning module and an early warning strategy generation module. The spatial-temporal feature modeling module builds a dynamic model based on historical data, captures a skeleton key point three-dimensional coordinate sequence, a motion optical flow vector field and a micro-expression intensity spectrum, and outputs a theoretical behavior mode vector; the behavior fragment extraction module generates a multi-modal difference feature tensor through cross-modal difference analysis; the exception propagation modeling module generates an exception propagation path risk probability distribution cloud picture in combination with spatial constraint and trajectory information; the risk area positioning module identifies a high-risk area and marks a boundary; and the early warning strategy generation module dynamically configures monitoring parameters, starts high-frame-rate micro-expression capture for a high-risk area, and performs a track disturbance test on an adjacent area.

The invention discloses a dynamic scene three-dimensional reconstruction method and device based on hydrogen energy unmanned aerial vehicle survey, and the method comprises the steps: obtaining dense time sequence multi-view image data of a target region through a hydrogen energy unmanned aerial vehicle platform, and carrying out the preprocessing of radiation correction and geometric correction; carrying out optical flow analysis and deformation rate clustering on the preprocessed image, identifying a pseudo-static anchor point and constructing a dynamic reference field; introducing a dynamic reference field as a soft constraint in a binding adjustment process, and optimizing a camera pose to generate a three-dimensional point cloud with consistent time and space; and finally, mapping the point cloud to a space-time voxel grid, constructing a surface evolution model by using a graph neural network or an anisotropic diffusion algorithm, and calculating a surface deformation vector to realize continuous and high-precision three-dimensional reconstruction of the disaster scene surface deformation process.

The invention discloses a panoramic image real-time splicing algorithm and system based on multi-sensor fusion, and particularly relates to the technical field of panoramic image real-time splicing, and the algorithm comprises the following steps: constructing a structured fusion sequence based on multi-source images, postures and position information, optimizing a matching effect through high-density feature extraction and repeated texture recognition, and obtaining a multi-source image fusion sequence; a dynamic foreground and a static background are distinguished by using sparse optical flow so as to improve the visual angle estimation precision, pose fusion optimization is realized in combination with a multi-mode residual error, and the continuity and stability of a spliced image are improved through edge smoothing, brightness tuning and color correction; according to the method, the structured fusion sequence is constructed through multi-source data alignment, so that the data synchronization and splicing stability is improved; identifying repeated regions based on texture direction features, and optimizing feature matching accuracy; and through edge smoothing, brightness harmonizing and color consistency processing, the visual coherence and output quality of the panoramic image are enhanced.

The invention belongs to the technical field of image recognition, and provides a target tracking method and system based on AI vision, and the method comprises the following steps: collecting original video frames; environment adaptive image enhancement; performing multi-target detection and multi-modal feature extraction; estimating local optical flow motion; performing multi-target trajectory association; carrying out shielding processing and re-identification; outputting a track and analyzing a result; according to the method, a physical-deep learning cascade defogging model is set, light / dense fog processing paths are dynamically switched through a dark channel mean value, atmospheric scattering physical prior and U-Net residual error correction are fused, an environment self-adaptive sensing architecture is provided, the failure bottleneck of a traditional single model under sudden change fog concentration is broken through, and the real-time performance of the system is improved. According to the method, an apparent-motion-geometry ternary coupling trajectory cognition system is constructed, a dynamic cost matrix and a feature cache pool are designed, the ID switching problem caused by similar target aggregation and long-time shielding is solved, and the accuracy of target tracking in the shielding environment is improved.

The invention relates to a hydraulic engineering concrete crack intelligent identification and quantitative analysis method and system based on machine vision. The method comprises the following steps: firstly, acquiring an original image sequence of the surface of a hydraulic engineering concrete structure, classifying according to illumination intensity, shooting angle and shooting distance, extracting crack edge features through a convolutional neural network, and fusing to obtain a crack feature set; correcting illumination through adaptive histogram equalization, correcting angles and distances through geometric transformation, and combining edge detection and scale invariant feature transformation to obtain standardized geometric parameters including crack length, maximum width and the like; if the parameter exceeds the engineering safety standard threshold value, tracking a crack track through an optical flow method to calculate increment, and inputting a neural network to output a damage trend; and finally, generating a three-color risk distribution diagram by using a finite element based on the trend, extracting high-risk data to calculate a real-time evaluation value, and dynamically adjusting the monitoring frequency to generate an optimization strategy. By adopting the method, the reliability and economy of engineering safety monitoring can be remarkably improved.

The invention discloses a flow field measurement method based on an event camera, and the method comprises the steps: generating a PIV data set, each time sequence sample sequence comprising a plurality of frames of continuous particle images, a corresponding velocity vector field, and particle event data at all moments; establishing a flow field data acquisition device based on an event camera and a high-speed camera, acquiring real event data and real image data which are synchronous in time so as to adjust parameters of an event simulator, and verifying and updating particle event data in the PIV data set according to the adjusted event simulator so as to obtain a flow field data acquisition result; obtaining the updated PIV data set as a training data set; building an event camera optical flow method model, and training by adopting the training data set; and on the basis of the trained event camera optical flow method model, event sequences in two adjacent time periods are used as inputs to calculate a velocity vector field corresponding to a middle moment. According to the invention, the flow field velocity field at the required moment can be obtained based on the event data within a period of time.

The invention belongs to the technical field of deep learning, and particularly discloses an ultra-precision full-field displacement measurement method and system based on a convolutional variational auto-encoder. Comprising the following steps: acquiring a video when a to-be-detected structure is subjected to vibration deformation, and selecting a picture of a deformation position to construct a data set; training a deep learning model of the convolutional variational auto-encoder based on the data set; reconstructing the gray value of the original image by using the trained deep learning model to obtain a gray value containing infinitesimal displacement information; and carrying out displacement calculation on the reconstructed image by utilizing an optical flow method, and realizing ultra-precision displacement calculation on the to-be-measured structure according to gray value conversion. According to the method, the problem that the infinitesimal displacement smaller than the sensitivity limit is difficult to measure is solved, the problem that the to-be-measured structure is blocked and cannot be measured is solved by utilizing the characteristics of the generative deep learning model, and the basic data precision of displacement measurement is remarkably improved.

The invention discloses an intelligent control and detection system for precision coating uniformity, and relates to the technical field of non-contact thickness measurement, the system comprises a spectrum confocal chromatography detection module, a non-contact multi-wavelength full-breadth detection module, an optical flow field dynamic measurement module and the like, a data processing unit is combined with a model to generate an evaluation model, and the evaluation model is used for evaluating the coating uniformity. The system has the advantages that multi-layer coating structure data are obtained in a full-breadth mode through a linear array sensor of the spectrum confocal chromatography detection module, a slurry full-breadth flow velocity vector field is analyzed in combination with the optical flow field dynamic measurement module, and the flow velocity measurement accuracy is improved. And the data processing unit fuses the multi-modal data to generate an evaluation model, and the regulation and control strategy generation module outputs an instruction containing edge air pressure regulation, so that accurate control over coating uniformity is achieved, damage to a base material is avoided, material waste and manual debugging time consumption are reduced, and the production efficiency and the product yield are remarkably improved.

The invention discloses a video monitoring abnormal behavior real-time detection method based on a graph neural network, and the method comprises the following steps: collecting a video frame sequence, extracting a detection frame, a key point and an optical flow feature, generating a node feature matrix, and constructing a dynamic graph structure; establishing a dynamic graph neural network model based on EvolveGCN, and updating a convolution weight by using a gating circulation unit; calculating event intensity and change rate according to the motion abrupt change signal, generating a time delay parameter and adjusting a weight modeling step length; performing low-rank decomposition and spectral radius projection on the convolution weight matrix, and adjusting a spectral constraint threshold according to an abnormal score; inputting a weight matrix to generate graph branch and hypergraph branch embedded representation; exchanging topology correction information based on a mutual generation mechanism and updating model parameters; and inputting the dynamic graph structure and the node feature matrix in real-time reasoning, calculating an abnormal score and outputting a detection result. According to the invention, adaptive evolution and high-precision anomaly detection of dynamic graph modeling are realized.

The invention discloses an AI-based child story video generation method and system, and relates to the technical field of artificial intelligence and multimedia crossing, and the method comprises the steps: generating a script from an original text input by a user through constructing an AI model fusing an emotion modeling capability; constructing an image generation combination model, defining a joint loss function, calculating an edge intensity graph of the contour image by using a Sobel edge detection algorithm, calculating an optical flow field of frame change by using a block matching algorithm, and performing color image dynamic frame alignment; a fine tuning WaveNet model is used to generate audio; through constructing an image generation combination model, combining a StyleGAN3-T model and an LDM model, defining a joint loss function, and using a Sobel edge detection algorithm and a block matching algorithm to calculate an edge intensity graph and an optical flow field, dynamic frame alignment of a color image is realized, and inter-frame continuity of a generated video is improved.

The invention provides a bridge structure damage detection method based on image processing and CNN-LSTM, relates to the field of graphic image processing, and solves the problems that bridge vibration monitoring in the prior art is time-consuming, labor-consuming, high in cost and limited in precision, and adopts the technical scheme that the method comprises the steps of obtaining a recorded vibration video of a to-be-detected bridge structure; extracting the vibration video frame by frame to obtain bridge image data; detecting angular points by using a Harris algorithm, screening image data, and calculating vertical displacement of each feature point one by one; using a Lucas-Kanade optical flow algorithm to calculate the motion vectors of the feature angular points of the adjacent frame images; calculating the actual vibration displacement of the bridge; and carrying out standardization processing on the actual vibration displacement to obtain a two-dimensional matrix, inputting the two-dimensional matrix into the trained CNN-LSTM model, and outputting a final identification result of each type of damage. According to the scheme of the invention, high-precision bridge vibration displacement can be calculated, and efficient, accurate and high-precision bridge damage detection can be realized through the CNN-LSTM damage identification model.

The invention discloses an infrared thermal imaging gas leakage image identification and positioning method based on deep learning. The method comprises the following steps: S1, capturing thermal signal characteristics of gas leakage through an infrared thermal imaging module; s2, performing bilateral filtering and edge enhancement processing on the infrared thermal imaging image through a preprocessing module; s3, a deep learning detection module is improved through a YOLOv8-SAM2 model; and S4, the optical flow tracking and positioning module calculates a continuous frame optical flow field based on a Lucas-Kanade algorithm, reversely deduces the coordinates of a leakage source, and realizes three-dimensional space positioning in combination with GPS / IMU (Global Positioning System / Inertial Measurement Unit) data. The infrared thermal imaging gas leakage image recognition and positioning method based on deep learning solves the problems that in infrared thermal imaging gas leakage detection, tiny leakage recognition under a low-contrast image is difficult, the false alarm rate under complex background interference is high, and the real-time positioning precision is insufficient.

The invention discloses a space-time speckle projection three-dimensional imaging method based on multi-frame optical flow alignment. Firstly, a projector based on DLP is used for projecting a space-time speckle pattern to a measured scene, and a binocular camera synchronously collects a three-dimensional space-time speckle image. The calibration parameters of the binocular camera are used to carry out stereo correction on an acquired original speckle image, and a parallax image is generated frame by frame in combination with a coarse-to-fine single-frame speckle matching strategy. And estimating a two-dimensional inter-frame displacement field between continuous disparity maps by using an optical flow method by taking an intermediate frame disparity map as a reference, compensating motion artifacts in a space-time speckle image, and ensuring strict space-time registration of a dynamic target. And based on the speckle image after motion correction, a speckle matching strategy is expanded to a time-space domain, and high-precision multi-frame three-dimensional measurement of a complex dynamic scene is realized. The method is suitable for performing rapid and high-precision three-dimensional modeling on a moving target in an unstructured environment, and can perform accurate three-dimensional measurement on a high-speed dynamic target undergoing any translation or rotation motion.

The invention provides a multi-mode intelligent control method and device for a robot body and electronic equipment. The multi-mode intelligent control method comprises the following steps: acquiring multi-view images and task texts of cameras at multiple parts of the robot; generating two-dimensional track supervision information and key point supervision information based on the two, and converting the two-dimensional track supervision information and the key point supervision information into a visual supervision graph; key point features are generated through the supervision graph, and track features are generated in combination with the multi-view image; extracting a depth image, optical flow information, a matched segmentation mask, an execution mechanism attitude and a motion frequency, and generating corresponding features; inputting each feature into a multi-modal fusion reasoning model, generating a relative action prediction feature and converting the relative action prediction feature into an action control instruction; and controlling an execution mechanism to complete the task. According to the method, track supervision, key point supervision and multi-modal prior are introduced under the vision-language condition, and perception integrity, robustness and execution precision are remarkably improved.

The invention discloses an intelligent medical image diagnosis system and method based on hierarchical cross-modal conversion and dynamic feature tracking. The system adopts three-step cross-modal conversion: a first-layer small model for converting user questions to realize medical ontology matching; the second-layer multi-modal model extracts image features, and outputs text states such as JSON data with focus coordinates, density and other features; and the third-layer large model fuses the medical history and the image features to generate diagnosis suggestions, and credibility verification is carried out. A dynamic focus tracking engine is introduced, a focus evolution rule of multiple scanning is analyzed through a convolutional network, and an optical flow field is adopted to compensate artifacts. The system also integrates a multi-expert voting mechanism to simulate a clinical consultation process, and outputs consensus diagnosis and objection viewpoints. A hierarchical routing algorithm is designed for emergency treatment scenes, so that the recognition response time of emergencies such as pneumothorax is shortened. Further, the system automatically generates a full chain of evidence report that conforms to medical regulations, including a model version, a guide reference, and a data hash value.

The invention relates to the technical field of face verification, and discloses a face identity verification data processing method based on dynamic feature extraction, which comprises the following steps: acquiring a continuous face video frame sequence and calculating a full-pixel instantaneous velocity vector to generate an original dense optical flow field, selecting rigid region anchor points to calculate a rigid affine transformation matrix and construct a theoretical rigid motion field, performing differential stripping on the theoretical rigid motion field from the original dense optical flow field, and extracting a non-rigid micro-motion residual field; mapping the non-rigid micro-motion residual field to a facial muscle topological grid to generate a time sequence feature tensor, and calculating a geodesic line distance between a covariance matrix of the time sequence feature tensor and a reference dynamic feature in a Riemannian manifold space; when the geodesic distance is smaller than a threshold value, verification is passed, through a rigid-non-rigid orthogonal decomposition mechanism, the special viscoelastic micro-motion and cooperation law of biological soft tissue is captured by utilizing a residual field, and the high-simulation mask is effectively defended.

The invention belongs to the technical field of computer vision and deep learning, and relates to a cultured fish intelligent feeding system based on multi-feature fusion and a control method thereof, and the system comprises an image acquisition module, a space-motion feature extraction module, a motion track feature extraction module, a feeding state recognition module, a feeding control module and a feedback adjustment module. Extracting a depth optical flow image reflecting fish school feeding state characteristics through a fish school real-time video stream; classifying the fish school feeding state image samples to form a space-motion optical flow feature map data set; meanwhile, fish swimming trails are extracted, and a swimming trail feature map data set is formed; and training is carried out to obtain an optimal model weight, real-time identification is realized, an identification result is transmitted to the feeding control module, the feeding state of a fish school after feeding is completed is evaluated, the feeding amount is adjusted, or a feeding decision is optimized. According to the invention, real-time, accurate and efficient identification and decision control of the feeding state of the fish school can be realized, and intelligent feeding is realized on a low-cost edge end computing platform.

The invention provides an airborne image target feature enhancement and three-dimensional reconstruction joint optimization method and system, and relates to the technical field of image processing, and the method comprises the steps: collecting an image sequence through a binocular camera, carrying out the epipolar correction and alignment, calculating an optical flow field to obtain space-time alignment feature points, generating a disparity map based on the matching cost, and converting the disparity map into a scene point cloud, performing graph structure segmentation to obtain a target point cloud, and finally extracting boundary points to generate a triangular mesh and mapping a texture image to reconstruct a three-dimensional model. According to the invention, effective enhancement of image target features is realized, and the target identification accuracy and the three-dimensional reconstruction precision are improved.

The invention provides a micro-expression recognition method and device based on a multi-scale optical flow guiding attention mechanism, and the method comprises the following steps: constructing a pre-trained micro-expression recognition model which comprises a preprocessing module, a dynamic motion branch and a space-time appearance branch which are arranged in parallel, a cross-modal fusion module, and a classification head; and obtaining a to-be-recognized micro-expression video, and inputting the to-be-recognized micro-expression video into the micro-expression recognition model to obtain an emotion category According to the scheme, the attention sensitivity of the model to micro-motion of key areas such as orbiculus oculi muscle and zygomatic lesser muscle is remarkably improved under the guidance of the optical flow dynamic information, so that the accuracy of emotion category prediction is improved.

The invention discloses a satellite video multi-target tracking method based on an optical flow and a state space model. The satellite video multi-target tracking method comprises a network model training part and a video multi-target tracking part, the network model training part comprises the steps of preprocessing a training data set, constructing and training a target detection network fused with optical flow feature enhancement, and constructing and training a multi-target sequence association network based on a state space model; the video multi-target tracking part comprises the steps of inputting an unstable image satellite video stream, detecting the position of an interested target in each frame by using a target detection network, carrying out inter-frame target association by using a multi-target sequence association network, and generating a continuous multi-target tracking trajectory. Through multi-scale optical flow enhancement, residual mask fusion and autoregression prediction, unification of high precision, real-time performance and track continuity is realized, and the method is suitable for complex and dynamic satellite video scenes.

The invention relates to a micro-expression recognition method based on double-flow feature fusion, and belongs to the field of computer vision. The method comprises the steps of obtaining N frames of images of a micro-expression video from a start frame to a vertex frame, and calculating an optical flow field between adjacent frames by adopting an optical flow algorithm so as to effectively extract optical flow features of micro-expressions; the method comprises the following steps: acquiring N frames of images of a micro-expression video from a start frame to a vertex frame, converting the N frames of RGB face images into a CIE Lab color space, calculating a pixel difference between two frames of converted Lab images, and extracting pixel stream features of micro-expressions; and inputting the optical flow features and the pixel flow features into a constructed double-flow three-dimensional convolutional network for feature extraction and fusion, and classifying micro expressions. According to the method, the dynamic and subtle changes of the micro-expression are effectively captured by combining the optical flow and the pixel difference characteristics. By integrating spatial and temporal information, richer feature representations are provided. The improved attention mechanism further focuses on fine facial changes, and the accuracy of micro-expression classification is improved.

The invention relates to the field of sealing control, in particular to a multifunctional sealing control method based on visual identification and a sealing machine. The method comprises the following steps: collecting a multispectral visual image of a material to be sealed, performing material depth visual identification and intelligent sealing parameter matching one by one, and generating personalized sealing process parameters; performing dynamic optical flow tracking according to the multispectral visual image, and calculating an accurate position coordinate and a time point when the material arrives at the position of the sealing machine; intelligent sealing action planning is carried out according to the precise position coordinates and the time point, and an intelligent sealing planning instruction is generated; carrying out conveyor belt rhythm analysis based on the multispectral visual image, and carrying out conveyor belt synchronous adjustment based on the intelligent sealing planning instruction to generate a synchronous adjustment signal; and synchronous transmission and sealing driving are carried out based on the personalized sealing process parameters and the synchronous adjusting signals. Sealing process parameters are adjusted in real time, and the overall production rhythm and efficiency of the sealing machine are improved.

The invention relates to the technical field of data processing, in particular to a method for driving emotion interaction of an intelligent device based on multi-modal understanding, and aims to eliminate illumination and noise interference and output a standardized face video stream, an effective voice segment and a touch thermodynamic diagram through an environment adaptive acquisition module. The feature extraction module extracts facial action optical flow features, voice Mel-frequency cepstral coefficient vectors and tactile pressure gradient parameters. The cross-modal correlation model adopts a tensor decomposition algorithm to calculate a space-time correlation matrix of visual and voice features, and the tactile feature weight is dynamically adjusted in combination with environmental parameters. According to the response strategy, an intervention scheme is retrieved based on a graph database, emotion confirmation statements, guide statements and behavior suggestions are fused to generate multi-mode response, and PID adjustment of the temperature control device and tactile pulse output of the vibration device are synchronously driven. And the feedback evaluation module verifies the emotion recognition consistency through a Pearson's correlation coefficient, triggers conflict sample separation storage and model increment training, and realizes closed-loop optimization.

The invention provides a robot vision object semantic understanding and posture generation method based on a large model, and belongs to the technical field of image processing. Comprising the following steps: S1, inputting an image and a 3D model; s2, object detection; s3, multi-modal feature alignment is carried out; s4, diffusion model sampling; s5, performing geometric screening; s6, carrying out NeRF (New Random Field) morphological modeling; s7, optimizing the optical flow; s8, joint loss calculation; s9, confidence coefficient analysis; and S10, outputting the attitude junction. According to the invention, through an innovative single-view rendering-optical flow optimization closed loop strategy, the calculation overhead is significantly reduced and the estimation precision is improved. According to the method, the algorithm performance in a complex scene is remarkably improved through multi-scale feature fusion and a confidence decomposition strategy.

The invention relates to the field of image processing, and discloses a video image segmentation method which is used for improving the precision, robustness and real-time performance of video image segmentation in a complex dynamic scene. The video image segmentation method comprises the following steps: generating an entropy generation rate map through weighted combination of light flow divergence and rotation, and quantifying motion irreversibility; a double-virtual-form prime concentration field is constructed, next-frame texture prediction is realized through iterative evolution, and the dynamic background adaptability is enhanced; fusing the projection entropy generation rate graph and the enhanced texture residual graph, dynamically distributing motion and appearance weights, and generating a high-precision boundary response graph; and extracting and persistent filtering are carried out, topological consistency maintenance of segmentation masks is realized, multi-scale collaborative segmentation and dynamic computing resource scheduling are supported, and efficiency and precision are balanced. The segmentation precision of the method is obviously superior to that of a traditional method in complex scenes such as illumination variation and rapid motion, and the method is suitable for the fields with high real-time requirements such as monitoring, medical treatment and automatic driving.

The invention discloses a multi-scale linear array camera splicing method and system based on point cloud. The method comprises the following steps: completing acquisition and preprocessing of point cloud data and image data of a target area; determining an overlapping region range between adjacent images; extracting spatial structure characteristics in the point cloud data, and performing multi-scale hierarchical decomposition on the point cloud through a multi-scale segmentation method; meanwhile, multi-scale image feature extraction is carried out on the images of the linear array camera; solving gradients in X and Y directions by adopting an optical flow method aiming at any pixel in the overlapping region, and calculating a motion vector between the pixels; fusing the optical flow information obtained under each scale, and constructing a globally consistent optical flow vector field; according to the fused optical flow vector, calculating to obtain a geometric transformation matrix of the whole overlapping region; and after image transformation and alignment are completed through the transformation matrix, fusion processing is carried out on overlapped areas. And the unification of the visual effect and the spatial integrity of the spliced image is ensured.

The invention provides an automatic vehicle damage assessment method and system based on video segmentation in vehicle insurance claim settlement. The method comprises the following steps: constructing a chain hash and a digital signature by taking an accident video as input, and detecting secondary compression and frame pulling; a shared trunk and double-branch network is adopted to complete part damage segmentation, and optical flow and re-identification are combined to keep cross-frame consistency and refine a mask; under the calibration of a license plate, a hub and a marked line, a monocular depth and part curvature prior estimation recess depth and normal disturbance are fused; calculating quantitative indexes such as scratch length, scratch width, paint removal area, crack span and the like according to component topology, and performing grade evaluation; the evaluation result is mapped to a part BOM, man-hour and price library, replacement, repair and spraying schemes and cost details are automatically generated, a structured report containing key frame superposition and check codes is output, and video-level stable quantification, evidence traceability and automatic loss assessment are achieved.

The invention discloses a dynamic scene robust vision SLAM (Simultaneous Localization and Mapping) method based on multi-feature collaborative optimization, which comprises the following steps of: acquiring an image sequence, carrying out dynamic target detection and segmentation through an instance segmentation network, generating a segmentation mask containing a dynamic region mark, and identifying and separating a dynamic object and a static background; removing feature points corresponding to the dynamic object based on the segmentation mask to obtain static feature points; carrying out pose estimation based on the static feature points, and for the key frame, carrying out feature matching with the previous key frame by minimizing a re-projection error, and solving to obtain the camera pose of each key frame; for non-key frames, performing camera pose tracking and data association on the previous frame by adopting an optical flow algorithm, and accumulating solving results to obtain pose tracks of all the non-key frames; the key frames and the non-key frames are subjected to differential processing by fusing feature matching and an optical flow algorithm, so that the calculation efficiency is remarkably improved while the positioning precision is ensured, and the real-time performance is improved.