89 results about "Global matching" patented technology

The invention discloses a crop disease multi-modal diagnosis and classification method and system, and relates to the technical field of data processing, and the method comprises the steps: collecting disease multi-modal data, and carrying out the preprocessing; constructing a disease multi-modal diagnosis model, respectively inputting images and text sequences in the multi-modal data into a visual feature extraction subnet and a text feature coding subnet of the disease multi-modal diagnosis model, and extracting global visual features, sequence state features and global text features; calculating a global matching score based on the global visual features and the global text features, executing fine-grained local interaction on the global visual features and the sequence state features, introducing a category channel attention mechanism to correct the features obtained by interaction, and weighting to generate multi-modal fusion features; and constructing a loss function based on the global visual features, the global text features and the multi-modal fusion features, training a disease multi-modal diagnosis model, inputting to-be-classified data into the disease multi-modal diagnosis model, and outputting a classification result.

The invention discloses a fuzzy video real-time jitter removing method and system, and the method comprises the steps: distributing feature points through multi-scale FAST detection, lightweight MLP detection and dynamic weight, combining a MobileNet-FPN network and the lightweight MLP dynamic weight to extract the robust features of the feature points, modeling the global matching relation of the feature points of two adjacent frames through Transform, and carrying out the real-time jitter removing of a fuzzy video. And a Bayesian adaptive RANSAC algorithm is adopted to realize high-efficiency mismatching pair elimination, and finally an affine transformation matrix is solved and reverse mapping is performed to compensate jitter. According to the method, while the real-time performance of the mobile terminal is ensured, the image stabilization precision in a violent shaking scene is remarkably improved.

The invention discloses a real-time multi-target tracking method based on occlusion information. The real-time multi-target tracking method specifically comprises the following steps: step 1, initializing a tracker; step 2, obtaining a current frame target and appearance characteristics of the current frame target, and sending the obtained target and corresponding characteristics into a tracker; 3, constructing an incidence matrix, and carrying out two-stage global matching to obtain a matching result M; step 4, correcting the influenced target based on the division of the track category in the step 1 and the division of the target category in the step 3; then the track information is updated; 5, increasing the shielding duration of the unmatched tracks, deleting the tracks with overlong shielding duration, converting the types of the tracks, and initializing the unmatched targets; and step 6, after track category conversion is completed, outputting a current frame tracking result, and returning to the step 2 for cyclic tracking until tracking is finished. According to the method, the tracking effect on the low-confidence target in the low-camera-angle scene is effectively improved, and the accuracy of the multi-target tracking task is improved.

The invention discloses a method for realizing intelligent sag measurement of a power transmission line by using a binocular depth camera, which comprises the following steps of: firstly, fixing the binocular camera on a rotary holder at the central position of two towers to complete camera calibration and epipolar correction; then, controlling the holder to rotate according to a fixed stepping angle, collecting a binocular image sequence covering the whole section of lead, and preprocessing the binocular image sequence; performing feature matching and image splicing by using an SIFT algorithm based on the left eye image sequence to generate a panorama and establish a panorama-local mapping relationship; thirdly, detecting an insulator and a spacer target in the panorama based on a Mask-RCNN model, accurately positioning key point coordinates of the insulator and the spacer target, and mapping the key point coordinates to an original local image; in the corresponding left and right local images, a semi-global matching (SGM) algorithm is adopted to calculate parallax and generate depth information, and then three-dimensional coordinates of a target point are obtained through conversion; and finally, performing catenary fitting according to the ordered three-dimensional point set, introducing a temperature and windage yaw dynamic correction model, and accurately calculating a sag value. According to the invention, non-contact, automatic and high-precision sag measurement is realized, the method is suitable for routing inspection of complex terrains and large-span power transmission lines, and the operation safety and efficiency are remarkably improved. The invention also provides a system, equipment and a medium for realizing the method.

The invention provides a guide registration method, system and device for RGB and infrared image fusion and a storage medium, and belongs to the technical field of image enhancement based on computer vision. Firstly, input of a visible light image and an infrared image is obtained, main target objects in the images are recognized and detected, and a preliminary target detection frame is generated; then, taking the target detection frame as spatial prior information, and generating an RGB image segmentation result and an infrared image segmentation result; performing feature matching on two segmented image results through a newly-designed cross-modal feature matching engine strategy, firstly extracting coarse-grained and fine-grained features through two parallel encoders, then obtaining a homography matrix through a global matcher, distortion refining and matching sampling, and finally obtaining a cross-modal feature matching algorithm; and then homography transformation is carried out on the original infrared image to obtain a final registration image. The method is superior to an existing method in the aspects of registration accuracy and stability, and a robust solution is provided for registration of infrared and visible light images.

The invention relates to the technical field of geophysical exploration, and discloses a three-dimensional fine electromagnetic detection method for ore control fracture of a deep gold ore. The method comprises the following steps: arranging a measuring point array to emit a coding artificial electromagnetic pulse signal, and synchronously receiving a plurality of induced magnetic field responses to form an original data volume; estimating a noise baseline based on statistical distribution and adaptively calibrating data; constructing a spatial correlation network by using the time sequence correlation of adjacent measuring points, and identifying a high-connectivity cluster as a suspected fracture region; extracting a regional time sequence to perform multi-level clustering, and screening a typical fracture response mode; based on the mode set global matching enhancement response, generating an enhancement data volume; multi-scale three-dimensional tensor decomposition is adopted to extract a tensor kernel component, and an electrical structure is reconstructed according to the spatial compactness and energy attenuation characteristics of the tensor kernel component; and finally, iteratively fusing with a geological constraint model to output a three-dimensional ore control fracture fine detection result. According to the method, intelligent identification and high-precision imaging of the deep fracture are realized.

Examples relate to a concept for an entry-exit matching system, and in particular to an evaluation device, a method and a computer program for person re-identification for entry-exit matching in a transportation system. The evaluation device comprises processing circuitry configured to obtain a plurality of re-identification codes. Each re-identification code represents a person being recorded by at least one camera when entering or exiting at least a section of the transportation system. The processing circuitry is configured to match the plurality of re-identification codes using a global matching scheme to obtain a plurality of matched pairs of re-identification codes, such that each matched pair of re-identification codes comprises a re-identification code of a person entering and a re-identification code of a person exiting. The global matching scheme is based on reducing an overall distance between the re-identification codes of the matched pairs of re-identification codes over the plurality of matched pairs of re-identification codes. The processing circuitry is configured to determine points of entry and exit for the plurality of matched pairs of re-identification codes.

The invention relates to the technical field of three-dimensional modeling, in particular to an augmented reality-oriented three-dimensional scene reconstruction method and system, and is used for solving the technical problem that an iterative nearest point algorithm cannot meet high real-time performance and high-precision reconstruction requirements required by augmented reality at the same time. The method comprises the following steps: acquiring a pose transformation relationship between multiple frames of point cloud data and adjacent frames of point cloud data; extracting a plurality of feature points in each frame of point cloud data, and determining a feature descriptor of each feature point; according to the feature descriptors of the feature points, calculating a matching weight between feature point pairs in two adjacent frames of point cloud data, and calculating a local matching error based on the matching weight and a pose transformation relationship; performing global matching optimization based on the local matching error of the plurality of feature point pairs and the distribution density of each feature point in the respective point cloud frame, and determining an optimal matching point pair set which minimizes the global matching error; and according to the optimal matching point pair set, fusing the multi-frame point cloud data, and reconstructing a three-dimensional scene model.

The invention discloses a future computing-oriented super-node cluster liquid cooling efficient computing platform and a resource management method thereof. A CPU, a GPU and a reserved photon / quantum accelerator slot in a super node are virtualized into a computing resource pool through a unified heterogeneous resource abstraction layer, and a CXL large-capacity memory and an NVMe-oF storage are virtualized into a cross-node memory resource pool and a storage resource pool respectively; the physical state of the super node cluster, the temperature-flow distribution of the liquid cooling heat dissipation system and the operation parameters of the heat recovery system are mapped in real time in the digital twin system; the intelligent scheduler takes task completion time, cluster total power consumption and waste heat recovery efficiency as a joint optimization target, and decomposes the task based on a virtual model; and in the task execution process, the energy efficiency cooperative controller adjusts the operation frequency of the allocated resources and the rotating speed of the liquid cooling pump in real time according to the node temperature change predicted by the digital twin model, so that the task performance, the energy consumption and the heat dissipation capability are globally matched.

The invention provides a robot repositioning method in a dynamic environment based on laser visual complementation. The robot repositioning method comprises two stages of offline mapping and online repositioning. In the off-line stage, two-dimensional and three-dimensional elimination of a dynamic target is realized through a lightweight detection network and geometric projection, and the purity of a prior map is improved; visual and laser radar static features are respectively extracted, a complementary double descriptor database is constructed, and laser radar descriptors fuse geometry and reflection intensity information to enhance discrimination. In the online stage, a coarse-to-fine strategy is adopted, rapid and robust global matching is achieved by combining GPS coarse positioning and radius search-based database retrieval, and scene recognition and accurate pose recovery are completed by using vision and radar dual channels. According to the method, a high-purity priori library is constructed through dynamic target collaborative elimination and multi-modal feature fusion, and autonomous high-precision global repositioning without manual initial pose input is realized in combination with GPS coarse positioning and a self-adaptive channel switching mechanism.

The application discloses a kind of crop disease multi-modal diagnosis and classification method and system, it is related to data processing technical field, the method of the present application includes collecting disease multi-modal data and pre-processing;Disease multi-modal diagnosis model is constructed, the image and text sequence in multi-modal data are respectively input into the visual feature extraction subnet and text feature coding subnet of disease multi-modal diagnosis model, extract global visual feature, sequence state feature and global text feature;Based on global visual feature and global text feature, calculate global matching score, perform fine-grained local interaction on global visual feature and sequence state feature, and introduce class channel attention mechanism to correct the features obtained by interaction, and generate multi-modal fusion features by weighting;Based on global visual feature, global text feature and multi-modal fusion feature, construct loss function and train disease multi-modal diagnosis model, input the data to be classified into disease multi-modal diagnosis model and output classification results.

This invention discloses a long text matching method combining noise filtering and a divide-and-conquer strategy. The method includes: constructing a long text matching model, which comprises a keyword extraction layer, an association extraction layer, and a filtering layer. The keyword extraction layer extracts keywords from the text; the filtering layer filters noise from the text based on sentence similarity to obtain a denoised text sequence; and the association extraction layer further removes keywords from the denoised text sequence to obtain the remaining associated text. The long text matching model is trained with the optimization objective of minimizing a set overall loss function, which reflects the global matching distribution and combines the keyword and association matching distributions. For the target text, real-time text matching is performed using the trained long text matching model. This invention improves the generalization ability and accuracy of text matching.

This invention discloses a video tag dynamic overlay anti-shake method and system based on AR, comprising: acquiring real-time video stream and device pose parameters at corresponding timestamps; constructing a dynamic perspective projection model based on the device pose parameters and calculating the initial pixel coordinates of the target AR tag in the current video frame; planning a local feature search window based on the initial pixel coordinates; calculating the average pixel displacement vector of image feature points in the local feature search window of the current and adjacent historical video frames; performing reverse displacement compensation on the average pixel displacement vector to obtain the target rendering coordinates, and rendering the target AR tag to the current video frame based on the target rendering coordinates. Compared with the prior art, this invention can overcome the shortcomings of large drift errors caused by simply relying on mechanical pose, high computational power consumption caused by global matching, and high-frequency jitter of tags caused by slight device vibrations, thereby improving tag mapping accuracy, reducing system computational power consumption, and improving the visual stability of video overlay.

This invention proposes a method and system for detecting missing weld points on vehicle bodies based on 3D vision and global matching, belonging to the field of image recognition technology. The method includes: determining the transformation relationship between the camera coordinate system and the vehicle body coordinate system through calibration; at each observation position, a 3D camera acquires an image I containing a frame of 2D texture and the corresponding 3D data; inputting the acquired image I into a pre-trained deep learning object detection model, outputting the bounding box information (u, v, w, h) for each weld point; for each detected weld point, calculating the set S of the weld point's 3D coordinates in the vehicle body coordinate system. det For the theoretical solder joint library S cad Each theoretical solder joint P in cad,i In set S det The invention employs a "detect first, match later" strategy, which does not rely on the precise projection of the theoretical position, thus reducing the requirements for the positioning accuracy of the production line tooling fixtures and conveying system.

The application relates to a multi-sensor-based repositioning method, device, equipment and storage medium. The method comprises the following steps: acquiring environment images collected by respective sensors; performing global matching on the respective environment images and images in a prior environment image library to obtain respective robot poses before updating corresponding to the respective sensors; performing local matching on the respective environment images and respective surrounding environment images corresponding to the respective robot poses before updating in the prior environment image library to obtain score values of respective robot poses after updating; and determining a repositioning result of a current robot pose according to the score values of the respective robot poses after updating. By performing global matching and local matching on the environment images collected by different types of sensors and the images in the prior environment image library, the repositioning result of the current robot pose can be ensured to have accuracy and reliability.

Establishing an AI empowered global loan matching of borrowers and lenders, by creating a loanchain of “atomic loans”. Large long duration loans are constructed from a succession of small, short duration loans, thereby mitigating lender's risk, and pulling into the loan dynamics hundreds of billions of dollars that currently earn no interest to their owners.

The invention provides a semi-global matching binocular depth estimation method based on polarization information guidance, and the method comprises the steps: obtaining a focal plane polarization optical image of a target under a binocular visual angle, calculating the polarization information of the focal plane polarization optical image, and obtaining the polarization degree information and the polarization angle information; constructing a polarization matching cost function by adopting a window matching method based on the polarization angle information; the method comprises the following steps: constructing a gray scale matching cost function by adopting an SAD-Census hybrid calculation method based on a focal plane polarization optical image; taking the polarization degree information as a fusion weight, and carrying out weighted fusion processing on the polarization matching cost function and the gray matching cost function to obtain a fusion cost function; performing semi-global matching SGM based on polarization clue guidance by adopting a fusion cost function to obtain final parallax information of the target; and performing three-dimensional reconstruction processing on the target through the final parallax information of the target to obtain target point cloud data. On the basis, the matching precision and the robustness are remarkably improved.

This invention proposes a hinged vehicle trajectory planning method based on multi-camera surround view information. It estimates the relative pose of the cameras based on the surround view images, combines the independent semantic cognition of each camera to obtain a bird's-eye view semantic cognition map, and establishes a time-invariant global matching relationship with the semantic map. Based on the matching features, it completes high-precision estimation of the vehicle pose. By improving the accuracy of vehicle pose estimation and the long-term robustness of the matching features, it enhances environmental perception and localization accuracy, providing high-precision data to be fused for subsequent trajectory planning. This invention designs a vehicle trajectory planning method based on the bird's-eye view semantic cognition map and vehicle pose estimation. It fuses the constructed traffic strategy set with quasi-static representation and vehicle pose to complete trajectory planning, improving the real-time performance and completeness of trajectory planning. Tracking is performed based on the predicted trajectory, and the traffic strategy set is updated based on the tracking accuracy, improving the feasibility of trajectory planning.

The application discloses a kind of multilingual contract intelligent comparison method, system, equipment and storage medium, and its technical scheme points are in that first language version contract and second language version contract are preprocessed to obtain first text content and second text content;First text content and second text content are corrected to obtain first corrected text and second corrected text;All clauses in first corrected text and second corrected text are traversed, the overall semantic similarity and multilevel semantic similarity between the clauses are calculated, and the global matching degree between them is calculated;According to overall semantic similarity, multilevel semantic similarity and global matching degree, the similarity score between the clauses is calculated, and whether the clause is a problem clause is determined according to the similarity score;Identify the problem category of problem clause, and generate corresponding correction suggestion according to the problem category.The application realizes automatic comparison of multilingual contract, and ensures the consistency and accuracy of multilingual contract.

The present application relates to a kind of power transmission engineering smoke hidden danger identification method, device and storage medium.In the present application, the output feature of the motion recognition of the motion recognition network of the DBG video action recognition network is cascaded with the output optical flow feature of the global matching optical flow network of GMFlow after operation, and then input into the first Transform for deep feature fusion;In the first Transform, the feature map after target feature extraction is converted into input-output sequence, and then the multiple self-attention layers are optimized to calculate the multiple attention outputs linearly connected to the desired dimension;Obtain the hidden danger data containing smoke hidden danger in power transmission engineering, train the recognition network architecture by hidden danger data to obtain parameters, and finally obtain the recognition model for power transmission engineering smoke hidden danger.The present application detects smoke by combining spatial features and time sequence features, greatly reduces the frequency of smoke false alarm and improves the accuracy of prediction.

The invention discloses a task self-adaption-based multi-modal fusion garment matching recommendation method and system, and the method comprises the steps: S1, splicing the image features, original text features and fashion perception text features generated by a multi-modal large-language model of each single item in a set of garment matching, and carrying out the splicing of the image features, original text features and fashion perception text features; a fine-grained multi-modal feature vector is formed; s2, combining the multi-modal feature vectors of all single items in clothing matching with a learnable specific task token to form an input sequence, and encoding the input sequence through a Transform encoder to capture a context dependency relationship among the single items to generate an output sequence containing the hidden state of each single item; s3, introducing a learnable global query vector, and actively selecting and integrating significant information from the hidden state sequences of all single items through a cross attention mechanism to generate a global matching representation; and S4, inputting the global matching representation into the prediction model, and outputting a result of the clothing matching task.

The invention discloses a gold ore particle size distribution three-dimensional reconstruction method and device based on a GPU and a medium, and relates to the technical field of three-dimensional image processing, and the method comprises the steps: collecting a gold ore material pile multi-view image and a camera attitude, completing the image standardization and calibration alignment processing on the GPU, calculating the view quality weight, and obtaining a synchronization frame group, a pose matrix and a quality weight table; performing candidate depth mutual projection on the synchronous frame group in parallel according to the pose matrix, converging similarity according to a quality weight table, generating a matching cost body, generating a dense depth map and a depth confidence map by the matching cost body through semi-global matching, performing back projection on the dense depth map to obtain a three-dimensional sampling point, and obtaining a three-dimensional sampling point; and parameterizing the three-dimensional sampling points into Gaussian primitives and forming a three-dimensional model state. According to the method, the dense depth and the depth confidence coefficient are output by fusing the multi-view mutual projection similarity and combining semi-global matching, so that the mismatching is inhibited under the conditions of shielding and weak textures, and the depth stability and reliability description are improved.

The application provides a sea surface wave field reconstruction method and device based on binocular stereo vision, comprising: collecting sea surface stereo images of an observation area based on a binocular image acquisition system at a preset frame rate; constructing an initial three-dimensional wave field by combining the sea surface stereo images with a semi-global matching algorithm; filling small-size holes in the initial three-dimensional wave field by combining a morphological closing operation to obtain a preliminarily filled three-dimensional wave field; and reconstructing large-size holes in the preliminarily filled three-dimensional wave field by combining a physical model of variational data assimilation to obtain a complete sea surface wave field. In a four-dimensional variational data assimilation framework, incomplete binocular vision observation data and a wave physical model are fused to solve the problem of large-scale data holes that cannot be handled by traditional optical methods, so that a complete three-dimensional wave field that is continuous in time and space and physically consistent is reconstructed.

The invention discloses a partition power grid scene generation method fusing multi-type resource output characteristics, and belongs to the technical field of power system optimization. Comprising the following steps: dividing a target power grid into a plurality of regions, constructing a wind power output probability model and a photovoltaic output probability model in each region, and further constructing a multi-type resource joint probability distribution model of each region; according to the multi-type resource joint probability distribution model of each region, generating a preliminary output scene of each region; performing scene reduction on the initial scene set of each region to generate a typical output scene of each region; according to the historical net load covariance matrix of each region, constructing a global output scene model with the target of minimizing the global matching cost between the typical output scenes of each region; and solving the global output scene model, and generating a global output scene with space-time correlation characteristics. According to the method, the problem that multi-type resource space-time correlation characteristics are difficult to accurately describe is solved.

The invention discloses a construction method and device for a mobile robot map and a storage medium, and belongs to the technical field of positioning and mapping. The construction method comprises the following steps: acquiring a current measurement point cloud and a current prediction pose of the mobile robot at a current moment; performing normal distribution transformation matching on the current measurement point cloud and a point cloud corresponding to the current prediction pose on a pre-constructed global voxel map to obtain a point cloud global matching residual error; performing iterative nearest point matching on the current measurement point cloud and a point cloud corresponding to a current prediction pose on a pre-constructed local dense map to obtain a current observation pose and a point cloud local matching residual error; determining a current actual pose according to the current observation pose, the current prediction pose and the point cloud local matching residual error, and obtaining a current actual point cloud matched with the current actual pose; and constructing a mobile robot map according to the current actual pose and the current actual point cloud. The method is used for improving the construction precision of the mobile robot map.

The application provides a silk screen defect detection method and device, electronic equipment and storage medium, and belongs to the technical field of intelligent manufacturing. The method comprises the following steps: performing global matching on a to-be-detected image of a to-be-detected product by using a global template; determining an initial matching position of a local template in the to-be-detected image based on the global matching result and a relative position relationship, determining a local search region according to the initial matching position, and performing accurate matching in the local search region to obtain a to-be-detected region image accurately aligned with the local template; and comparing the to-be-detected region image with the local template to generate a silk screen defect detection result. The application firstly performs global matching by using a global template, and then performs accurate alignment of each local template in a local region of the to-be-detected image based on the global matching result and the relative position relationship of the local template relative to the global template, thereby reducing false positives caused by inaccurate alignment and improving the efficiency and accuracy of silk screen defect detection.

The invention discloses a high-precision 3D imaging plug-in system for mobile phone vertical screen close-range live broadcast, and belongs to the technical field of 3D imaging and live broadcast equipment. The system realizes high-precision real-time modeling of which the depth error is less than or equal to 0.03 mm within the distance of 0.2 m-0. 5m by arranging a double 5 million pixel main shooting module with the baseline distance of 10 + / -0.5 mm and combining a special depth processing chip and an improved semi-global matching algorithm. The system optimizes a field angle and double-channel annular light supplement for vertical screen live broadcast, synchronously transmits a depth map and a double-channel 4K video through a USB-C3.2 Gen2 interface, supports 30fps non-delay live broadcast application, and effectively solves the problems of insufficient precision, poor real-time performance and close-range adaptability existing in an existing scheme.

The invention discloses a canal channel construction earthwork stone intelligent scheduling transportation method and system, and particularly relates to the technical field of channel construction, and the system comprises a resource pool construction module, a transportation equipment bidding generation module, a transportation task intelligent matching module, and a transportation task execution and optimization module. According to the method, the transport capacity resource pool and the task order pool based on the block chain are constructed, the equipment intelligent agent generates differentiated quotation based on a built-in cost model, the predefined algorithm is executed by running at the edge computing node, the equipment is subjected to order global matching, then the optimal transport equipment is matched, and in the task process of the transport equipment, the task efficiency of the transport equipment is improved. Based on releasing and sensing virtual pheromones to the virtual pheromone map where the intelligent agent is located, self-organized path optimization and dynamic updating of the pheromone map are carried out, resources can flow to reasonable and efficient task points, the scheduling efficiency is improved, and the method is suitable for linear engineering scenes such as canal channel construction which is large in range, large in environment variable number and poor in network condition.

The application relates to the technical field of games, in particular to a game player matching method and device, electronic equipment and a storage medium. The application inputs game data of a plurality of to-be-matched players into a trained game battle matching model, and matches the plurality of to-be-matched players according to a global matching rationality condition, so that a target player team matching result of a plurality of matches that satisfy global maximum profit maximization as a whole can be determined. In this way, the application can not only match a plurality of matches at one time, but also ensure the global optimality of the matching result, so that the purpose of improving the global matching accuracy and the game balance is achieved.