122 results about "Visual Disparity" patented technology

The present invention relates to the technical field of construction waste treatment. Provided is an on-site intelligent sorting method for construction waste. The method comprises: S10, identifying waste components, and quantifying the proportion of inert material in construction waste; S20, by means of a computer vision method, acquiring visual difference features between the inert material and non-inert material; S30, performing mechanical screening, wherein the construction waste is screened by means of a mechanical screening module; S40, on the basis of precise sorting by a robot, performing detection on waste on a conveyor belt by means of waste detection driven by machine vision, then performing waste positioning, and, according to the results of waste detection and positioning, performing accurate sorting by using multiple robotic arms. The advantages of the present invention comprises: the described method is suitable for compact construction site scenes, the required space for installation and deployment is small, and an intelligent solution is provided for construction waste classification at compact sites.

The invention discloses a vehicle-mounted HUD optical performance comprehensive detection method, and aims to solve the problems that a traditional detection method depends on manual operation and is low in detection efficiency and large in error. Project loading and test starting, picture height position calibration, multi-parameter test, brightness and chromaticity test, ghosting test, static distortion test and binocular parallax test items are automatically implemented through detection equipment, and accurate control (such as application of camera pixel-millimeter ratio) of advanced image recognition algorithm and equipment in the test process is carried out. The vehicle machine controls the step number of the curved mirror motor, and the industrial personal computer controls the motion module, so that high-precision measurement of optical parameters is realized, and the test efficiency and the test accuracy are improved.

The invention discloses a position monitoring method and system based on different-source image registration and binocular positioning, and relates to the field of position monitoring. The method comprises the following steps: performing target detection and instance segmentation on image data of a dangerous area acquired by left and right binocular cameras to construct a mask image set; matching and processing the mask image of the target to obtain a target matching and correction image; introducing angle fusion score screening to obtain an optimal feature point, carrying out image registration on the optimal feature point according to the bit difference degree, and carrying out fusion display; calculating an optimal binocular parallax to obtain a target three-dimensional coordinate, and generating a point cloud; and carrying out background integration on the personnel target point cloud image according to the obtained crane space position to form a complete real-time personnel monitoring point cloud image. Through a binocular vision technology combining infrared and visible light cameras, a YOLOv8 algorithm and three-dimensional point cloud modeling, real-time monitoring of a hoisting operation dangerous area is realized, and operation safety and monitoring efficiency are remarkably improved.

The invention discloses a robust two-dimensional code steganography method based on an attention flow model, and particularly relates to the technical field of image super-resolution. According to the method, a carrier image and a two-dimensional code image are used as input, and a steganographic image which is very small in visual difference with the carrier image is obtained. The hidden two-dimensional code can be obtained by decoding the steganographic image, and the recovered two-dimensional code image can be identified and original information can be restored. According to the method, steganography and decoding processes are simultaneously realized through a neural network based on an attention flow model. According to the method, the steganography can be allowed to bear image interference such as noise, image quality compression, printing and photographing on the premise of ensuring that the recovered two-dimensional code can be identified. The steganography model based on the attention mechanism is realized, and explicit visual loss caused by steganography can be effectively reduced. The method can be applied to actual application scenes such as copyright protection and encryption communication, and has relatively high calculation efficiency and anti-interference performance.

The present invention relates to a vehicle control method, a binocular stereoscopic vision-based road unevenness feature detection method, system and device, and a computer readable storage medium. The binocular stereoscopic vision-based road unevenness feature detection method comprises the steps: S1, road surface unevenness feature detection; S2, generating a binocular disparity point cloud; S3, feature region point cloud projection; and S4, region feature calculation: calculating unevenness information of a corresponding region point cloud. The vehicle control method comprises the steps: T1, performing ego-vehicle trajectory prediction on the basis of the motion state of the vehicle; T2, on the basis of the predicted ego-vehicle trajectory, calculating a degree of correlation to a corresponding region point cloud; and T3, sending to an ADAS controller the concavity and convexity and height position of the corresponding region point cloud and the acquired degree of correlation as summarized information of each road unevenness feature. The present invention can effectively identify road unevenness information, reduce calculation resource consumption, and thus improve the comfort of intelligent driving.

The invention relates to the field of intelligent analysis, and provides a reclamation area land subsidence high-precision survey monitoring method, which comprises the following steps: carrying out ROI generation and visual multi-scale feature extraction on a first reclamation area image and a second reclamation area image by using an image recognition and analysis algorithm based on machine vision; local neighborhood perception enhancement is carried out on the extracted first reclamation area ROI visual feature description feature and the extracted second reclamation area ROI visual feature description feature; and intelligently obtaining a settlement monitoring result of the settlement height based on visual difference feature representation between the enhanced first enhanced reclamation area ROI visual feature description feature and the enhanced second enhanced reclamation area ROI visual feature description feature. Therefore, the accuracy of reclamation area land subsidence height calculation can be effectively improved.

A method for calibrating a binocular camera calibration parameter, an apparatus, a computer device, and a medium. The method comprises: acquiring a binocular disparity map and / or a binocular depth map; performing epipolar alignment detection on the binocular disparity map and / or the binocular depth map to obtain an epipolar alignment error; and on the basis of the epipolar alignment error and a first preset threshold, determining a target calibration parameter to be calibrated of a binocular camera. In the solution, in the process of calibrating the binocular camera calibration parameter, the epipolar alignment error is obtained by performing epipolar alignment detection on the binocular disparity map and / or the binocular depth map, and the target calibration parameter of the binocular camera is determined on the basis of the epipolar alignment error, thereby not only simplifying the calculation of the epipolar alignment error but also improving the precision of the epipolar alignment error, thus enhancing the accuracy of calibration of the calibration parameter.

The invention discloses an anti-jitter data acquisition and obstacle recognition method for a rail transit vehicle, and relates to the technical field of rail transit vehicle data acquisition and processing, continuous four frames of original images are acquired through a binocular camera by adopting synchronous and staggered shooting, and global motion estimation is performed in combination with acquired sensor data; local pixel level alignment is realized by using a preset image layer and pixel grid division, a stable image is generated through weighted fusion, local features of the image are optimized based on a multi-head attention mechanism, the stable image is mapped to a high-dimensional vector space by using a depth encoder, motion correction information is fused, and finally, the motion correction information is obtained. A deep reconstruction network is combined with binocular parallax to generate a three-dimensional point cloud, three-dimensional coordinate changes are monitored in real time, obstacle recognition and early warning are achieved, high-quality images can be obtained in the violent vibration environment of a vehicle, the data acquisition precision and the real-time performance and accuracy of obstacle detection are improved, and the operation safety of rail traffic is effectively guaranteed.

The invention discloses an integrated three-dimensional space modeling method based on Gaussian splashing and a three-dimensional point cloud. The method comprises the following steps: step 1, converting a scene multi-view image and depth data into the three-dimensional point cloud; 2, constructing a point sequence input set; step 3, inputting the point sequence input set into a PointMamba model; 4, performing Gaussian parameter initialization, performing scale expansion on a local sparse region, and performing direction constraint on a global key region; 5, obtaining a prediction depth map through a binocular parallax matching algorithm, calculating a rendering depth map of the initial Gaussian point set, and adjusting the optimization intensity; and step 6, executing an adaptive encryption operation, and outputting a three-dimensional space model. According to the method, high-precision three-dimensional reconstruction of a complex scene is realized, and the method is suitable for scenes needing high-density point cloud modeling and semantic understanding, such as building scanning, industrial detection and virtual reality.

The embodiment of the invention provides an audio and video alignment method, an audio and video understanding method, electronic equipment, a storage medium and a computer program product. The alignment method comprises the following steps: performing feature extraction and coding processing on a target audio to obtain a first audio feature sequence, and performing block feature extraction and coding processing on a target video to obtain a first video feature sequence; performing visual dynamic enhancement coding processing on the first video feature sequence based on the visual difference of the cross-frame image blocks to obtain a second video feature sequence; performing time sequence information injection on the second video feature sequence and the first audio feature sequence to obtain a third video feature sequence and a second audio feature sequence; and performing cross-modal alignment fusion processing on the third video feature sequence and the second audio feature sequence to obtain an aligned video feature sequence and an aligned audio feature sequence. According to the method, the visual dynamic change corresponding to the audio event can be accurately captured, and the alignment accuracy of the audio and the video is improved.

The invention discloses an image processing method and device and a storage medium, and belongs to the technical field of shooting. The method is applied to the electronic equipment comprising a plurality of cameras, the plurality of cameras comprise a reference camera, and the method comprises the following steps: under the condition that a first camera is called for shooting, determining a first white point of a current frame shot by the first camera and a first environment color temperature of a shooting environment corresponding to the current frame; according to an environment color temperature difference between the first environment color temperature and a second environment color temperature of a shooting environment corresponding to a memory frame of a reference camera, carrying out fusion processing on white point information of the first white point and white point information of a second white point of the memory frame to obtain white point information of a third white point; and performing white balance correction on the current frame according to the white point information of the third white point. Therefore, the color difference of the images shot by other cameras and the reference camera in the same scene and the visual difference caused by the color difference can be reduced, and the color consistency of multi-camera shooting in the same scene is improved.

The embodiment of the invention provides a three-dimensional image generation method and device, a storage medium and a program product. In the embodiment of the invention, based on binocular parallax, a first monocular view with a cavity area and a second monocular view without a cavity area corresponding to a two-dimensional image are generated; according to the method, the first monocular view is taken as a global constraint, the hole area in the first monocular view is subjected to block repair, image details can be accurately restored, the image quality is remarkably improved, important image details are kept, the second monocular view without the hole area is further taken as the global constraint, and the third monocular view obtained after hole area repair is subjected to global repair, so that the image quality is improved. And the generated content is ensured to be controllable during repairing, the consistency of stereoscopic vision is maintained, and the repairing definition is higher.

An external scene image captured by an external scene imaging electronic camera attached to a head mounted display (HMD) is projected and displayed onto an image display screen arranged in front of the eyes of the user as a virtual image with a suitable viewing distance corresponding to the visual acuity of the user. At this time, for each object image presented in the virtual image of the external scene image, the virtual image is processed and formatted to add a predetermined degree of binocular disparity and image blur to the virtual image projected and displayed on the right and the left image display screen on the basis of a predetermined converted distance calculated from the real distance of each object. Thus, the user is given a sense of a realistic perspective for the virtual image of the external scene, free of the discomfort or unease.

The invention provides a clustering cluster coloring method based on a space transcriptome, electronic equipment and a storage medium. The method comprises the following steps: constructing a clustering label confusion matrix according to a plurality of clustering labels of a plurality of clustering clusters in spatial transcriptome data, and constructing a color visual difference matrix according to a plurality of preset colors; performing order-preserving mapping on a first loop corresponding to the clustering label confusion matrix and a second loop corresponding to the color visual difference matrix to obtain a plurality of initial mapping relationships; aligning the clustering label confusion matrix and the color vision difference matrix according to each initial mapping relation, and calculating an error of the corresponding initial mapping relation according to the clustering label confusion matrix and the color vision difference matrix after each alignment; and coloring the plurality of clusters according to a target mapping relation determined from the plurality of initial mapping relations according to the plurality of calculated errors. By using the method, the distinction degree between the clustering clusters can be improved, so that the user can better distinguish the clustering clusters with relatively high similarity degree.

The invention discloses a binocular disparity map obtaining method, device and system for a small target, and is used for improving the disparity optimization effect of the small target, and the method comprises the steps: carrying out the hierarchical feature extraction of a left view and a right view, obtaining a feature map, compressing the feature map to 32 channels through the convolution operation integrated with the structure information, and obtaining a binocular disparity map; therefore, an initial splicing body is constructed; obtaining attention weights of the stereo images corresponding to the left view and the right view, screening the initial splicing bodies by using the attention weights, and constructing a cost body according to a screening result and initial parallax loss; fusing the convolutional context information with the preliminarily aggregated intermediate features to perform cost aggregation on the cost body to obtain an aggregation result; and adopting a self-adaptive multi-modal cross entropy loss function to supervise an aggregation result, and performing multi-modal output on the supervised aggregation result through a multi-modal parallax estimator to obtain a binocular parallax graph of the left view and the right view.

The invention belongs to the technical field of underwater target space positioning, and discloses an underwater benthos rapid positioning method and system based on binocular vision, and the system comprises an underwater environment data binocular camera collection device which carries out the image enhancement processing of collected image data; inputting the enhanced image into a lightweight Slim-RT-DETR target detection network, and carrying out the detection and recognition of a fishing object; cutting target areas of left and right views of the binocular camera based on a target detection and recognition result, and calculating a parallax value by adopting an anti-noise optimization method of random sampling and neighborhood interpolation; and calculating three-dimensional space coordinates of the fishing object according to the binocular parallax and the re-projection matrix, and positioning the underwater benthos. According to the invention, a rapid image enhancement algorithm and a target detection model suitable for underwater fishing are designed, a normal form method suitable for underwater biological positioning is provided, and high-precision and high-real-time underwater fishing object positioning can be realized.

The invention provides a brain surgery image analysis method based on a computer vision technology, and relates to the technical field of computer vision, and the method comprises the steps: collecting a three-dimensional binocular image in a brain surgery; determining visual difference between a left eye and a right eye in the binocular camera, generating a depth map space of a three-dimensional binocular image, and further extracting a visual missing area in the brain surgery; determining an obstacle shielding domain of an obstacle in the binocular camera according to the depth map space, and performing light stripe tracking through the obstacle shielding domain and a relative position between a left eye and a right eye in the binocular camera to obtain light stripe missing information in the brain surgery; and determining a reconstruction missing threshold value of the binocular camera according to the light bar missing information and the visual missing area, performing fusion vacancy filling on the three-dimensional binocular image based on the reconstruction missing threshold value to obtain a three-dimensional fusion image, and taking the three-dimensional fusion image as an analysis image of the brain surgery. And the image integrity of the brain surgery is improved.

The invention belongs to the field of computer graphics, and discloses a self-adaptive LOD subdivision method and system oriented to virtual reality and based on a perceptual model. The method comprises the following steps: firstly, researching factors influencing visual perception, establishing a perception model BD-castleCSF fused with stereoscopic vision by combining binocular parallax, and dynamically dividing a rendering region; then, on the basis of a discrete LOD initial order processing grid model, introducing a mosaic technology to execute grid subdivision, calculating a downsampling factor according to a perception model, dynamically adjusting the subdivision degree, and proposing a perception adaptive subdivision LOD algorithm; experimental results show that compared with a traditional static rendering method, the LOD switching frequency of the method is reduced by 67%, the effective subdivision triggering rate is improved by 19.9%, the redundant triangular surface compression rate is improved by 11.9%, and the frame time standard deviation is reduced. Therefore, the method can dynamically and smoothly adjust the model details under different watching conditions, guarantees the consistency of visual effects, and remarkably improves the rendering efficiency. According to the method, an efficient and adaptive rendering solution is provided for the field of virtual reality.

Embodiments of the present application relate to a method and system for three-dimensional modeling of a train based on a binocular disparity prediction model, the method comprising: setting installation, acquisition and splicing rules of double parallel linear array cameras; setting a binocular disparity prediction model; acquiring first data set based on the installation, acquisition and splicing rules; training the binocular disparity prediction model based on the first data set; installing the double parallel linear array cameras after the training; when a train passes through the two installed cameras on the current train track, acquiring and splicing images to obtain images I1 and I2, inputting the images I1 and I2 into the binocular disparity prediction model for prediction to obtain a disparity map D 1‑2 , and based on I1, I2 and D 1‑2 , the present application can improve prediction accuracy in high-speed scenes and complex lighting environments, effectively overcome the limitations of a single perspective, and improve the integrity of three-dimensional reconstruction of edge and occluded areas.

The application discloses a binocular disparity map acquisition method, device and system for small targets, which is used for improving disparity optimization effect of small targets. The method comprises the following steps: performing hierarchical feature extraction on left and right views to obtain a feature map, compressing the feature map to 32 channels through a convolution operation with structure information, and constructing an initial splicing body; obtaining attention weights of corresponding stereo images of the left and right views, screening the initial splicing body by using the attention weights, constructing a cost volume according to a screening result and an initial disparity loss; fusing convolution context information and intermediate features after preliminary aggregation to aggregate the cost volume, and obtaining an aggregation result; supervising the aggregation result by using an adaptive multi-modal cross-entropy loss function, and performing multi-modal output on the supervised aggregation result by using a multi-modal disparity estimator, so as to obtain binocular disparity maps of the left and right views.

The invention belongs to the technical field of grain quality detection, and particularly discloses a grain quality detection device which comprises a detection vehicle, an oblique insertion flow guide sampling barrel, an alternate lifting rolling bearing type dyeing mechanism, a quality highlighting device and a paving observation device. According to the difference between surface structures and internal pore structures of wizened grains and full grains, the difference can cause different adsorption capacities of the wizened grains and the full grains when the wizened grains and the full grains are in contact with dyes, and the difference can be presented in a visual color difference form by dyeing the grains, so that the quality of the grains can be conveniently distinguished; the method for distinguishing the grain quality based on the visual difference after dyeing has the advantage of being high in intuition, and the grain quality can be rapidly judged under the condition that complex instrument analysis is not needed.

The application discloses a feature extraction method and system based on difficult sample mining and multi-granularity division, which is used for a cross-view geographical image retrieval task. The method first preprocesses cross-view street view images and satellite images, and uses a generative model to generate cross-view images, reducing the visual difference between different view images. Then a two-stage difficult sample mining model is constructed, including a sampling strategy based on geographical location and visual similarity, mining difficult negative samples in different ranges, and enhancing the inter-class discrimination ability. Then a multi-granularity feature division module is introduced, the image features are extracted through a ResNet50 backbone network, and the features are divided and fused according to different granularities to obtain rich and robust view-invariant feature representation. Finally, the satellite image to be retrieved is input into the trained feature extraction model, the features are extracted, and similarity matching is performed with the street view image library to obtain the cross-view retrieval result.

The invention relates to the technical field of robot sensors, in particular to a visual tactile sensor based on color block mark array optimization and a three-dimensional reconstruction method, and the method comprises the steps: enabling four colors with remarkable visual difference to correspond to two patterns with different sizes to form eight digital identifiers, a binocular vision camera is used for collecting a color block array on the surface of an elastomer, on the basis of completing three-dimensional calibration and image preprocessing, the color block characteristics of mark points and neighborhood distribution of the mark points are used as constraints, displacement distance screening, line positioning and inter-frame movement continuity are combined, rapid matching and dynamic tracking of the mark points are achieved, and the accuracy and the accuracy of three-dimensional calibration are improved. According to the method, the spiral search traversal frequency is remarkably reduced, the system processing time is shortened to about 270 ms from about 320 ms through array structure design, matching strategy optimization and sensor structure miniaturization cooperation, high-precision reconstruction is guaranteed, meanwhile, the real-time performance and robustness are improved, and the method is suitable for complex operation scenes such as industrial robot precision assembly and flexible grabbing.

The present invention relates to the field of autonomous driving technology, and discloses a multi-sensor fusion odometer generation method and system based on facet fitting, the method comprising: obtaining laser radar sensor data, visual sensor data and IMU sensor data; pre-integrating the IMU data to obtain the relative transformation relationship within the posture update cycle; performing coordinate transformation on the laser radar sensor data and the visual sensor data to obtain the laser point cloud disparity map and the visual disparity map of adjacent frames, and eliminating dynamic obstacles; extracting facets from the laser point cloud data and extracting key points from the visual image data, and constructing the constraint relationship between frames; according to the relative transformation relationship within the posture update cycle, the facet information and the constraint relationship between frames are jointly optimized to obtain the posture output information; performing smoothing based on the RTS smoother to obtain a stable posture result. The present invention improves the efficiency and accuracy of the odometer by eliminating dynamic obstacles and facet fitting.

This application belongs to the field of virtual art restoration technology, specifically providing a deep learning-based virtual art restoration system. The system primarily analyzes historical images and environmental data of the artifact and restoration materials to train an aging prediction model and simulate long-term appearance changes. By quantitatively comparing the differences and stability of their aging trajectories, it calculates the long-term compatibility score for each restoration material and automatically selects the optimal material to generate the final virtual restoration image. This application effectively solves the problem in existing technologies where it is difficult to predict significant visual differences that may appear between restoration materials and the artifact itself after long-term natural aging, ultimately leading to insufficient durability of the restoration results. It achieves scientific prediction and optimized selection of the long-term visual compatibility of restoration schemes, significantly improving the reliability and stability of restoration results and reducing the risk of restoration failure due to material aging incompatibility.

This application relates to a method for identifying wildfire hazards based on a spatial-temporal correlation operator using visual language priors. The aim is to address the problems of high false alarm rates and difficulty in early identification of concealed fires in vision-based power transmission line wildfire monitoring methods under complex backgrounds. The method constructs a multimodal fusion tensor for the current frame based on visible light and infrared images of the target area. It then uses a visual language prior module to extract features from the multimodal fusion tensor and meteorological data to obtain semantic feature vectors and semantic credibility. Finally, it uses a spatial-temporal correlation module to obtain a spatial-temporal evolution feature vector based on the multimodal fusion tensor, historical time-series cache queue, binocular disparity map, and the semantic credibility. Finally, it uses a spatial-temporal correlation operator to fuse the semantic feature vector, the semantic credibility, and the spatial-temporal evolution feature vector to obtain the probability of wildfire hazard risk.

The embodiment of the invention provides a task execution method and device, electronic equipment and a storage medium, and relates to the technical field of robotics.The method comprises the steps that a view pair collected through a binocular camera is obtained, and a first monocular geometric feature of a left view of the view pair and a second monocular geometric feature of a right view of the view pair are extracted; determining similarity characterization values of the first monocular geometric feature and the second monocular geometric feature under the plurality of different parallax characterization values, and obtaining binocular parallax features including the plurality of different parallax characterization values and the similarity characterization values; taking at least one view in the view pair as a target image, and extracting visual semantic features from the target image; performing feature fusion based on the binocular parallax features and the visual semantic features to obtain fused features; and controlling the robot to execute the task for the task object based on the fusion feature and the task description instruction. According to the scheme provided by the embodiment of the invention, the task execution accuracy can be improved.

The invention belongs to the technical field of energy intelligence, and provides a regional integrated energy system multi-level agent construction method, which comprises the following steps: carrying out space-time alignment processing on real-time operation data to obtain a synchronous data stream; respectively mapping parameters in the synchronous data stream into specific visual attribute primitives to obtain a multi-level state semantic image; performing visual semantic segmentation on the multi-level state semantic image to obtain visual semantic units, and constructing a spatial correlation map between the visual semantic units; performing visual difference comparison on the spatial correlation map and a historical same-period spatial correlation map to obtain an abnormal visual semantic unit; performing multi-frame tracking verification on the abnormal visual semantic unit, and integrating an abnormal unit identifier and an abnormal type into an abnormal event report; and carrying out hierarchical decision making on the abnormal event report and the spatial correlation graph to obtain a collaborative regulation and control instruction. According to the invention, the efficiency of cooperative management of the regional integrated energy system can be improved.

The invention provides an intelligent nuclear power embedded part detection and acceptance method based on a binocular camera, belongs to the technical field of detection and acceptance, is an intelligent detection algorithm based on binocular vision and a deformable attention mechanism, and aims to break through the technical bottleneck of three-dimensional positioning and multi-scale feature fusion of embedded parts in a complex scene. A three-dimensional pyramid network with reserved features is designed, multi-scale features are fused in a layered mode, binocular geometric consistency is kept, and the problem of information loss in cross-resolution feature fusion is effectively solved; parallax perception position coding is innovatively introduced, binocular parallax information and two-dimensional position coding are deeply fused, and the three-dimensional space perception capability is enhanced; a non-parametric anchor-based target query mechanism is provided, query embedding covered by dense space is generated by multiplexing low-resolution three-dimensional features, the model convergence efficiency and the detection precision are improved, the detection cost is reduced, the detection efficiency is improved, and the detection safety is guaranteed.