2401 results about "Feature matching" patented technology

The invention relates to an underwater robot navigation positioning method and system. The method comprises the following steps: S1, acquiring angular velocity and acceleration signals through an inertial measurement unit; s2, resolving a three-dimensional velocity observation value according to the beam radial velocity vector signal in combination with the angular velocity signal, and extracting environment feature point cloud data according to the acoustic image signal; s3, multi-source data time synchronization is carried out, and a fusion input signal with time-space alignment is generated; s4, constructing an adaptive factor graph optimization model, and dynamically adjusting an inertial navigation solution node based on a real-time weight coefficient; inputting the environment feature point cloud data into a closed-loop detection module to generate a loopback factor node, and adaptively correcting the weight of the node according to the feature matching degree; and S5, solving the adaptive factor graph optimization model through a nonlinear optimization algorithm. According to the underwater robot navigation positioning method and system, the problem that the fusion positioning precision of a multi-source heterogeneous sensor is insufficient in an underwater GPS-free environment can be solved.

The invention discloses an industrial image anomaly detection method based on deep learning, and particularly relates to the technical field of industrial visual detection. The problems of high false alarm rate, fuzzy fine defect positioning, insufficient real-time response capability, difficulty in model increment updating and the like caused by data distribution drift in an industrial scene are solved. According to the method, robust features are extracted through a multi-scale feature fusion auto-encoder, and a dynamic memory bank is constructed to update a normal sample prototype online; a dual-path detection mechanism is adopted to cooperate with a pixel-level reconstruction error and attention weighted feature matching deviation; efficient edge reasoning is realized in combination with block parallel processing and model compiling optimization; and designing an elastic incremental learning framework to prevent disastrous forgetting. And finally, false alarms caused by environmental changes are reduced, accurate positioning of pixel-level defects is realized, millisecond-level detection requirements of high-resolution images are met, safe and efficient model online evolution is supported, and adaptability and reliability of an industrial quality inspection system are comprehensively improved.

The invention provides a dam leakage intelligent identification method based on multi-modal fusion and knowledge enhancement, and the method comprises the steps: collecting real-time data of a multi-source sensor disposed at a key part of a dam in a preset monitoring time period, and generating seepage characteristic data; identifying a seepage form entity based on the seepage characteristic data and extracting an instantaneous characteristic entity, and associating the entity into a structured knowledge unit according to a space-time proximity principle; knowledge units are classified according to spatial positions and influence ranges, association rules of the knowledge units are complemented, and knowledge graph construction is achieved; and then, a map inference engine is triggered in a real-time feature matching mode, and graded early warning is implemented. According to the method, physical enhanced seepage characteristics are constructed, seepage forms, dynamic characteristics and inducements are deeply associated by utilizing a knowledge graph technology, accurate diagnosis and reasoning from data abnormity to seepage types, causes and risk levels are realized, and finally, the seepage characteristics are analyzed and analyzed through a dynamic conflict resolution and self-evolution mechanism. And a reliable dam leakage intelligent identification and decision-making system is formed.

The invention discloses a construction site three-dimensional scene reconstruction method based on an unmanned aerial vehicle image and a monitoring video. The method comprises the following steps: acquiring a construction site scene multi-view image; a sparse three-dimensional point cloud and a camera pose are generated through a feature matching and motion recovery structure algorithm, and dense reconstruction is carried out to obtain a global three-dimensional point cloud; aligning the global three-dimensional point cloud with a world coordinate system by using geographic position information; estimating the position of a shooting camera in the three-dimensional point cloud, sampling a candidate view angle and rendering a virtual RGB image; based on two-dimensional feature matching of the shot image and the virtual RGB image, internal parameters and external parameters of the shooting camera are iteratively solved through triangulation and a pose optimization algorithm; monocular depth estimation is carried out on the shot image, and the shot image is converted to a measurement scale through static region depth alignment; and projecting the depth of the shot image to the three-dimensional point cloud, updating the dynamic object in real time, and fusing the dynamic object into a complete three-dimensional scene model. The method has the advantage that the real-time three-dimensional reconstruction of the dynamic scene of the construction site is realized.

The invention relates to the technical field of building structure health monitoring, in particular to a building defect detection method based on infrared thermal imaging and visible light bimodal fusion and a matched intelligent imaging device. According to the method, infrared thermal imaging and visible light bimodal image fusion are combined, and an improved YOLOv8m-seg model is combined, so that accurate detection of the defects of the outer wall of the building is realized. Firstly, a bimodal data set containing multi-material temperature difference data is constructed, ORB feature matching is combined with a feature alignment module (FAM) to achieve accurate image alignment, the defect detection robustness is improved through an improved bimodal feature fusion network, and finally automatic recognition and quantitative analysis of cracks, fractures and other defects are achieved. The problems that single-mode detection is interfered by dirt and is poor in multi-material adaptability are solved, the detection accuracy rate reaches 96% or above, the recall rate exceeds 93%, the single image detection time is shorter than or equal to 0.3 s, and the method is suitable for efficient detection of various building outer wall defects.

The invention relates to the technical field of power system data processing and network security, in particular to a system log data anomaly detection and management system and method. The system comprises an atlas establishment module, an anomaly identification module and a feedback adjustment module. According to the method, the global knowledge graph is constructed through the graph establishment module, the deviation degree is calculated in combination with historical baselines, direct association anomalies are judged, the potential influence degree between nodes is calculated based on a graph neural network propagation mechanism through the anomaly recognition module, and non-direct association anomalies are recognized through feature vector cosine similarity. A multi-dimensional feature matching rule base is combined to determine an anomaly type and execute response measures, a feedback adjustment module collects execution data through buried points, quantifies and evaluates effectiveness, optimizes a scheme through feature backtracking and root cause positioning and relies on digital twinborn simulation and gray scale landing to realize scheme iteration, and a feedback adjustment module performs feedback adjustment. The accuracy of anomaly detection and the dynamic adaptation capability of response measures are improved, and the method is suitable for log management and risk prevention and control of a complex system.

The invention relates to the technical field of security and protection management, in particular to a campus security and protection management system based on deep learning, which improves the accuracy and robustness of identity recognition by acquiring access control card numbers, face images or fingerprint features and generating standardized identity authentication data. And on the basis of a comparison result of the identity authentication data and the campus database, a behavior chain initialization identifier is generated, and accurate identity binding of the school entering personnel is realized. Furthermore, by collecting multi-camera image stream data, pedestrian re-identification and similarity calculation are executed by using a deep feature matching network, and a cross-camera continuous trajectory data set is generated. And matching the behavior track data set with the conventional path template to generate a behavior offset feature vector. And carrying out joint modeling on the behavior offset characteristics and the identity information through a graph neural network model containing an attention mechanism, and outputting a behavior purpose label and a risk grade score. And a graded security response instruction is generated based on the risk score, so that the missing report rate and the false report rate are effectively reduced.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a segmentation and matching method, device, equipment and medium for an image background region. Multi-scale features are obtained through cavity convolution branch, fusion features are generated through weighted fusion, the fusion features are input into a decoder network to obtain a background segmentation mask, a background area image is obtained by combining the preprocessed image, and a visual converter model is input to extract background feature vectors; and performing similarity matching with a target feature vector in a preset feature database to retrieve a target image. According to the method, the segmentation accuracy and robustness are improved through combination of multi-scale feature fusion and the visual converter, meanwhile, the retrieval discrimination and reliability are enhanced through feature matching, the problems that an existing method is insufficient in segmentation precision and limited in retrieval capacity are solved, and precise segmentation and efficient retrieval of the background in a complex scene are achieved.

The invention relates to an underwater topographic measurement method based on laser radar and visual fusion, which comprises the following steps: synchronously acquiring underwater point cloud, images and physical environment sensing data, and endowing a unified space-time label to realize the space-time consistency of multi-source data; according to the method, the data quality of different modes is improved by means of preprocessing, denoising, scale normalization, feature enhancement and the like, an environment interference weight matrix is constructed in combination with an environment sensing model, feature extraction and matching algorithm parameters are adaptively adjusted according to different environment states, and multi-scale feature description, spatial consistency and physical constraint criteria are established, so that the multi-modal data quality is improved. According to the scheme, high-reliability feature matching between the point cloud and the image is achieved, finally, through environment-driven iterative optimization and fusion, the robustness and precision of space registration are improved, high-precision multi-modal data automatic registration can be stably achieved in the underwater dynamic environment, adaptability is high, and environment perception and space measurement quality is effectively improved.

The invention relates to the technical field of unmanned aerial vehicle positioning, in particular to an unmanned aerial vehicle positioning method and system combining environment characteristics. According to the technical scheme, the method comprises the steps that multi-modal data of the environment where the unmanned aerial vehicle is located are collected through a multi-source heterogeneous sensor, and the multi-modal data comprise GNSS signal data, visual image data, laser radar point cloud data, inertia measurement data and electromagnetic interference monitoring data; and carrying out cooperative processing on the multi-modal data by utilizing the fusion deep learning model. A comprehensive basis is provided for subsequent processing through multi-source data collection, data quality and feature matching reliability are improved through fusion processing, timely and accurate positioning is guaranteed through real-time calculation, safe and efficient flight is achieved through a decision-making model based on accurate positioning, and the flight speed is high. The method not only solves the traditional technical problems of signal shielding, interference, dynamic interferent influence and contradiction between real-time performance and precision in a complex environment, but also shows excellent positioning stability and adaptability in various complex scenes.

The invention belongs to the technical field of computer vision and images, and discloses an AI vision-based fabric defect detection method, which specifically comprises the following steps: S1, adopting an industrial-grade linear array camera and a synchronous light source array; s2, carrying out noise filtering on the collected original image; s3, inputting the enhanced image into an improved ResNet multi-scale convolutional neural network; s4, embedding a residual attention mechanism into the feature map; s5, performing dynamic feature matching on the defect enhancement feature map and the standard sample library image; s6, inputting the suspected flaw region obtained by preliminary screening into a self-supervised anomaly detection model; s7, combining an abnormal detection result with a historical batch detection error; and S8, carrying out multi-class classification on the detected flaws based on a dynamic threshold value. According to the invention, through combined application of the improved ResNet multi-scale feature extraction network and the residual attention mechanism, the complex texture, edge structure and small flaw features of the fabric can be deeply extracted.

The invention provides an underwater target identification method and system based on multi-source sensor data fusion. The method comprises the following steps: firstly, synchronously acquiring an original sound wave reflection signal and original optical image data of a target underwater area, then carrying out acoustic compensation processing on the original sound wave reflection signal to generate a target sound wave reflection signal, and meanwhile, carrying out optical compensation processing on the original optical image data to generate target optical image data; performing dynamic weighted fusion on the reliability measurement of the target sound wave reflection signal and the reliability measurement of the target optical image data through an adaptive fusion module to generate an enhanced multi-modal data set; and finally identifying the specific category of the underwater target through a multi-modal feature matching and decision-making mechanism. According to the technical scheme provided by the invention, the limitation of a single sensing mode is overcome, the quality of collected information is improved, the direct confirmation efficiency of common target recognition is also improved, and high accuracy and data reliability of target category recognition in a complex scene are ensured.

The invention relates to a three-dimensional point cloud registration method and system based on a two-dimensional visual large model. A source point cloud and a target point cloud are decoupled into two-dimensional projection representation; constructing a structure consistency restoration domain, restoring geometric structure fracture and semantic deficiency in the projection image, and generating a dense and continuous restoration image; inputting the repaired image into a pre-trained visual geometry large model, carrying out cross-modal feature matching and pose resolving, and synchronously outputting a pixel-level matching confidence map; and inversely mapping a two-dimensional pose calculation result to a three-dimensional space to complete coarse registration, constructing a high-credibility anchor point set in the three-dimensional space by using a confidence map, and guiding a point cloud fine registration algorithm to converge to global optimum. According to the method, the registration large model for natural image training can be seamlessly migrated to the point cloud data, and retraining is not needed; in a weak texture and partially overlapped point cloud scene, a robust rough registration initial value can still be provided; the convergence speed and the anti-noise performance of fine registration are remarkably improved, and adaptive improvement from coarse to fine is achieved.

The invention relates to the field of image processing, and discloses an object monitoring method and device based on multi-source data and a storage medium, and the method comprises the steps: synchronously collecting multi-channel video streams, environment parameters and equipment position information, and carrying out the time alignment and data association processing, and forming associated data; performing feature matching on the multiple paths of video streams, fusing position information and environment parameters, and establishing a mapping relation between video feature points and a unified space coordinate system; splicing the multiple paths of video streams in real time according to the mapping relation to generate a panoramic video stream; performing dynamic scene analysis based on the panoramic video stream and the environmental parameters, and identifying a target type and a state to obtain an analysis result; and generating an equipment regulation and control strategy based on the analysis result, and generating and issuing a regulation and control instruction for adjusting the working parameters of the multi-view image acquisition device based on the equipment regulation and control strategy. According to the invention, the splicing precision, the real-time performance and the target identification accuracy of panoramic monitoring can be improved, and the dynamic adaptive regulation and control of the equipment can be realized.

The invention belongs to the technical field of geometric pretreatment in computer aided engineering (CAE), and particularly relates to a dirty geometry restoration method for a complex three-dimensional geometric model, which comprises a dirty geometry detection and restoration module based on heuristic rules and geometric topology analysis. By means of a multi-model collaborative alignment and bonding mechanism, high-precision assembly between parts is achieved through geometric feature matching and adjacent domain self-adaptive adsorption; acquiring material attributes provided by the simulation platform, and performing accurate cutting and boundary reconstruction on an intersection domain based on an intersection domain intelligent segmentation algorithm of the material attributes to ensure correct mapping of boundary conditions of a physical field; a geometric Boolean processing engine iterative learning mechanism of a general merging algorithm is integrated, and a high-quality model for simulating a grid is generated through multi-round iterative optimization. According to the method, double challenges of internal dirty geometry of a single model and derivative dirty geometry of intersection / adjacent areas among multiple bodies are solved, and key physical attributes and topological continuity of electromagnetic signal links are ensured and are completely reserved during repair.

The invention relates to the technical field of unmanned aerial vehicle navigation, and discloses an unmanned aerial vehicle navigation method and system based on computer vision, and the unmanned aerial vehicle navigation method based on computer vision comprises the following steps: collecting a current visual field image of an airborne camera of an unmanned aerial vehicle, and carrying out adaptive image enhancement; performing scene semantic understanding; semantic perception feature extraction is carried out; feature matching and outer point elimination are carried out; floor identification is carried out, and multi-sensor fusion positioning is carried out; plane segmentation, structural constraint extraction and map normalization are carried out; performing visual navigation evaluation, judging a navigation mode according to an evaluation result, and generating an exploration control instruction quantity based on the navigation mode; generating a cross-floor path sequence, optimizing a track in real time, and performing control fusion in combination with a navigation mode identifier and an exploration control vector; according to the method, the navigation problem of the unmanned aerial vehicle in complex scenes such as smoke interference, multi-story buildings and illumination dramatic change in a GPS denial environment is solved, and high-precision autonomous navigation is realized.

The invention discloses a PDF (Portable Document Format) drawing recognition and information structured extraction method. The method comprises the following steps: generating a high-resolution bitmap through image preprocessing; positioning and classifying a text region, a table region and a symbol region in the drawing based on a target detection model of transfer learning; hough transform is combined with SIFT feature matching to identify engineering symbols, and sub-pixel positioning is realized through an RANSAC algorithm; after the oblique text is corrected through affine transformation, the content is extracted through OCR; reconstructing a table structure based on OPTICS clustering and projection analysis; constructing an RDF knowledge graph according to a coordinate association rule; and using U-Net difference to detect and position an omission area and complementing the omission area. According to the method, deep learning and image processing technologies are fused, the problems of low rotating text recognition rate, table structure loss and semantic association deficiency in a traditional method are solved, through lightweight model compression and TensorRT acceleration, the analysis accuracy is remarkably superior to that of the traditional method, and the method can be widely applied to the fields of constructional engineering, petrochemical engineering and the like and has wide application prospects. And the drawing information processing efficiency and the data integrity are improved.

The invention relates to the technical field of artificial intelligence, and discloses a traditional Chinese medicine diabetes dry eye treatment difference evaluation system and method based on artificial intelligence, and the system comprises a four-diagnosis integrated module, a syndrome modeling module, an intelligent decision module, a curative effect feedback module, a knowledge base management module and a self-adaptive learning module. Multi-mode traditional Chinese medicine four-diagnosis data of tongue condition, pulse condition and eye diagnosis and modern physiological parameters of metabolic indexes are fused, a deep learning method is adopted for standardization processing, the problem that traditional Chinese medicine syndrome differentiation depends on subjective experience is solved, traditional Chinese medicine syndrome feature extraction of diabetes dry eye has objectivity and quantifiability, and the traditional Chinese medicine syndrome feature extraction efficiency is improved. The comprehensiveness and the accuracy of the diagnosis basis are improved; and the curative effect feedback module compares a prediction result with revival curative effect data in real time, and the knowledge base management module is linked to carry out case feature matching and strategy optimization, so that continuous optimization and long-term reliability of the treatment decision model are ensured.

The invention relates to a metal surface defect identification method and device based on artificial intelligence, equipment and a medium. The identification method comprises the following steps: synchronously acquiring an electromagnetic impedance signal and an optical image of a metal surface based on an eddy current sensor and an industrial camera; generating a spatially positioned interference area mask by quantifying cross-physics field interference intensity of the electromagnetic gradient and the optical edge feature; performing skin effect compensation on an electromagnetic signal by using the mask, and simultaneously performing shadow suppression on an optical image to realize physical field decoupling; a double-branch neural network is called to fuse the decoupled electromagnetic impedance features and optical texture features, and cross-modal associated joint feature expression is established; and analyzing the defect probability heat map based on the fused features, and outputting defect types and coordinates in combination with geometric feature matching. According to the method, the problem of defect feature mixing caused by mutual interference of electromagnetic-optical signals is solved, and the recognition precision and the positioning reliability of the micro defects are remarkably improved.

The invention discloses a multi-source field-level blood relationship tracking method and system. The method comprises the following steps: extracting features from a multi-source heterogeneous system, matching templates, triggering a corresponding acquisition strategy, and outputting an original blood relationship log; reading an original blood relationship log to generate an abstract syntax tree, extracting a source / target field set to output a field-level mapping relation, further writing the field-level mapping relation into a graph database to form a blood relationship edge, writing metadata into a relational database, establishing a two-level index, and outputting a blood relationship graph capable of being quickly positioned; and taking the blood relationship map as input, returning a target path with the maximum sum of confidence coefficients by adopting a weighted shortest path algorithm, outputting a link-level traceability result, and displaying the link-level traceability result. According to the method, complete tracking of the field-level blood relationship is realized, the query response time is shortened to a millisecond level, rapid access to multiple types of data sources is supported, and the problems of insufficient blood relationship analysis precision, low query efficiency and weak multi-source adaptability in the prior art are solved.

The invention discloses a robot arm control method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a pre-training dynamic model and a real visual depth map of a real robot arm visual angle, and the pre-training dynamic model is used for completing a specified task; determining a joint control value according to the real vision depth map and a pre-training kinetic model; hybrid action control is carried out based on the joint control value, and remote target navigation is carried out on the response action of the real robot arm through a visual navigation model; and the controlled simulation target image and the actual image are obtained, feature matching and closed-loop estimation are carried out based on the simulation target image and the actual image, and pose error compensation is carried out on the action of the real robot arm. The motion is observed and deduced through a real visual depth map, then real and simulated mixed motion control is carried out to reduce a visual and dynamic gap, and finally pose error compensation is carried out. And the pose error of the arm is reduced, and a start pose guarantee is provided for downstream control.

The invention discloses a pose estimation method and device based on point pair feature matching, a medium and a product. The method comprises the following steps: performing coarse registration on a fusion scene point cloud and each template point cloud, and calculating point pair features; according to the corresponding hash key values, retrieving from each hash table to establish registration point pairs; calculating a translation vector and a rotation quaternion matched with each registration point pair according to the reference point coordinate system and the template coordinate system, and performing clustering processing on each registration point pair to obtain each initial corresponding set; screening out a target pose candidate transformation matrix and a matched target template point cloud from the pose candidate transformation matrixes matched with the initial corresponding sets respectively; a target optimization function between the fusion scene point cloud and the target template point cloud is constructed, iterative optimization is performed on parameters in the target pose candidate transformation matrix, and the target pose of the fusion scene point cloud is obtained at the end of iteration, so that the precision, real-time performance and reliability of six-dimensional pose estimation are improved.

The invention discloses a rapid exchange chip resetting method and system, and belongs to the technical field of chips. The method comprises the steps of abnormal trigger type identification, reset granularity dynamic determination, operation state freezing, hierarchical reset execution, reset validity verification and redundant reset system reconstruction, rapid abnormal positioning is achieved through hardware monitoring and feature matching, a dynamic reset strategy generation mechanism is combined, the reset granularity is accurately controlled according to the abnormal severity degree, and the system reliability is improved. Excessive reset or insufficient reset is avoided, the system resource utilization rate and the fault processing efficiency are improved, a state freezing technology is operated to maintain the state of a key register, progressive pulse injection and priority control of hierarchical reset execution are matched, it is ensured that a key module is preferentially recovered, the energy consumption is reduced while the reset effect is ensured, and the system performance is improved. Reset effectiveness multi-dimensional verification is combined with redundancy reset and a system reconstruction mechanism, a standby repair scheme is dynamically triggered for different fault types, and the reliability, fault-tolerant capability and maintainability of the system are improved.

The invention discloses a volume cloud rendering method and system based on three-dimensional Gaussian splash, and the method comprises the steps: carrying out the feature matching and structure reconstruction of a volume cloud image through an SfM algorithm, obtaining a sparse point cloud in a scene, and representing the sparse point cloud as an anisotropic Gaussian ellipsoid; decomposing the illumination transmission process of the volume cloud into two parts of forward single scattering and internal multiple scattering based on a radiation transmission equation to obtain an illumination modeling formula embedded volume cloud rendering process; determining the contribution of each three-dimensional Gaussian ellipsoid to a rendering result according to the opacity index of the three-dimensional Gaussian ellipsoid, and dynamically cutting the low-contribution three-dimensional Gaussian ellipsoid by adopting a delay deletion strategy to reduce redundancy; a comprehensive loss function is constructed, so that the three-dimensional Gaussian model is focused on the volume cloud region and the structure detail reduction capability is enhanced; and outputting the optimized volume cloud rendering result and the three-dimensional Gaussian model. According to the method, the volume cloud rendering efficiency and quality are effectively improved on the premise of ensuring real-time rendering.

The invention relates to the technical field of landslide geological disaster hidden danger point identification, in particular to a landslide hidden danger point identification method based on an air-space remote sensing fusion neural network, which comprises the following steps: acquiring satellite SAR data, a digital elevation model, a vector boundary map and a precision orbit ephemeris of a research area; carrying out interference processing on the InSAR data, and carrying out deformation rate inversion, terrain residual error correction and atmospheric delay phase modeling and correction; preprocessing an original high-resolution remote sensing image, interpreting a high-resolution image, and outputting spatial distribution of suspected landslide hidden danger points in a research area; planning an aerial survey route of the unmanned aerial vehicle, and performing distortion correction, feature matching, dense point cloud generation and orthoimage generation processing; performing multi-dimensional feature analysis, and performing comprehensive interpretation in combination with an expert knowledge base; according to the method, the key effect of the multi-source remote sensing fusion technology in landslide hidden danger monitoring is displayed from data acquisition to hidden danger recognition.

The invention discloses a mutual cooperative door lock complementary acquisition method and system, and the method comprises the steps: extracting the structural feature data of a target person according to an event that a self door lock recognizes a non-white list person, generating an assistance request containing a target ID and the feature data, and transmitting the assistance request to an adjacent door lock; according to the assistance request received by the adjacent door lock, target feature matching is carried out, and after matching succeeds, a target video stream is collected and selectively coded; according to the time points when the target appears and disappears, generating an association starting pointer and an association ending pointer, and synchronously storing the pointers between the door locks; and analyzing the association pointer according to the playback request, and automatically starting stream playing of the association video streams of the plurality of door locks to realize multi-view synchronous display. By utilizing the embodiment of the invention, continuous automatic tracking and multi-view synchronous playback of cross-equipment target activities can be realized through active cooperation and data association between door locks, and the continuity and efficiency of security monitoring are improved.

The invention relates to a six-eye camera panoramic video real-time splicing method and system and computer equipment, and the method comprises the steps: synchronously carrying out the image collection through a six-eye camera array, and adding a timestamp to each video frame image; performing real-time feature extraction on the video frame image, and establishing a feature matching relationship in a view field overlapping region of adjacent cameras; based on the feature matching relationship, mapping each video frame image to a unified splicing coordinate system through projection transformation; performing splicing processing on the video frame images after projection transformation through multi-band fusion, and eliminating splicing traces at the boundary of the field of view; and reconstructing the panoramic frame images obtained after splicing processing according to a time sequence, and outputting a continuous panoramic video stream so as to realize real-time and seamless splicing and correction of six paths of high-definition video streams and finally output a global panoramic video stream with no visual fracture and consistent time and space.

The invention provides a multi-step automatic testing method based on machine vision, and the method comprises the steps: capturing an original image sequence of a test scene through a camera, extracting the contour features of a test object in an image through an edge detection algorithm, and obtaining a preliminary positioning coordinate; if the dynamic position change trend exceeds a preset threshold value, adjusting an image enhancement parameter to suppress background noise, and obtaining an enhanced target image; feature matching is carried out through the enhanced target image, a robust identifier such as a texture mode is extracted, and an accurate three-dimensional position coordinate is obtained; according to the accurate three-dimensional position coordinates, calculating an execution deviation value of the current step, and judging whether the deviation value is within an allowable range or not; if the deviation value is within the allowable range, a control instruction sequence is generated and transmitted to the mechanical arm, and a step execution confirmation signal is obtained; comparing a confirmation signal with a next image sequence through the steps, updating positioning model parameters, and determining a continuous adjustment scheme of the whole test process.

The invention relates to the technical field of computer vision, in particular to a method for generating a blind person navigation obstacle avoidance map. The method comprises the following steps: driving a blind guiding robot to a preset inspection point, and collecting a surrounding environment image in real time; generating a three-dimensional point cloud according to the environment image, and constructing an environment map; extracting feature points based on the surrounding environment image, performing feature matching, and outputting a feature matching result; evaluating an inter-frame motion state by using a feature matching result; determining pose features of the blind guiding robot according to the inter-frame motion state; semantic segmentation is carried out by using the pose features, and an obstacle area is determined; acquiring an obstacle image of the obstacle area, and fusing the obstacle image with the surrounding environment image to generate an obstacle map; and constructing a dynamic occupancy grid based on the obstacle map. According to the invention, real-time updating and intelligent obstacle avoidance functions of the blind navigation map are realized based on the computer vision technology, and the navigation safety and the path planning accuracy are improved.

The invention provides a universal visual perception method for an open world based on language guidance, and belongs to the crossing field of computer vision and natural language processing, and the method comprises the steps: generating an initial multi-modal fusion representation, and obtaining the initial multi-modal fusion representation through the collection of a video frame sequence and a language instruction through processing and fusion; then determining a target candidate region, and carrying out matching, screening and optimization based on semantic keywords and visual region features; then generating a target identifier, and allocating a unique identifier to the high-confidence region; a continuous tracking trajectory sequence is formed, and a bounding box is updated and the trajectory is smoothed in combination with an algorithm; when the target disappears, the state vector of the target is temporarily stored, and the tracking identifier is recovered when a similar region appears; optimizing the tracking sequence, and adjusting a bounding box to generate an optimized sequence; and finally, outputting target motion trail, position and state information. Through multi-modal fusion, an optimization algorithm and a recovery mechanism, the open world target identification and tracking effect is effectively improved, and the practical value is high.