Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

510 results about "Optical flow estimation" patented technology

Optical flow estimation is used in computer vision to characterize and quantify the motion of objects in a video stream, often for motion-based object detection and tracking systems. Moving object detection in a series of frames using optical flow.

Real-time video quality optimization and enhancement method based on deep learning

The invention discloses a real-time video quality optimization and enhancement method based on deep learning. The method comprises the following steps: S1, collecting a video stream and extracting continuous frames; s2, extracting motion area features by using an optical flow estimation algorithm, and generating a multi-modal feature matrix; s3, carrying out normalization processing; s4, outputting a de-noising optimization frame by using an adaptive multi-dimensional residual network and a frequency domain analysis technology; s5, generating a detail enhancement frame by using a progressive generative adversarial network; s6, constructing an inter-frame relation graph through locality sensitive hashing, correcting the frame by using a double-flow time sensing network, optimizing the frame sequence based on a dynamic time warping method, and outputting the corrected frame sequence; s7, inputting the corrected frame sequence into a dynamic feedback optimization module to generate an optimized frame sequence; and S8, recombining the optimized frame sequence into a continuous video, and transmitting the continuous video to a target platform. According to the method, the video definition and the time consistency are comprehensively optimized through methods of multi-modal feature fusion, dynamic optimization, progressive network generation and the like.
Owner:XIAOYUAN PERCEPTION (HULUDAO) TECH CO LTD

Pixel calibration method and system of high-precision liquid crystal display screen

The invention relates to the field of display screen pixel calibration, in particular to a pixel calibration method and system of a high-precision liquid crystal display screen. The method comprises the following steps: acquiring a real-time playing animation image of a high-precision liquid crystal display screen based on an internal sensor of the display screen; carrying out image scene distortion feature mining on the real-time playing animation image so as to obtain a comprehensive scene distortion feature; performing frame-by-frame pixel optical tracking on the real-time playing animation image, and performing frame-by-frame rolling offset vector calculation so as to construct a pixel point time sequence offset trajectory diagram; carrying out regional dynamic optical flow estimation on the pixel point time sequence offset trajectory diagram, carrying out dynamic trajectory distortion modeling based on comprehensive scene distortion characteristics, and constructing a pixel point offset trajectory distortion model; and carrying out dynamic color change perception on the pixel point offset track distortion model so as to generate a self-adaptive pixel point track offset compensation value. According to the invention, efficient and accurate pixel calibration is realized, and the dynamic visual effect is improved.
Owner:SHENZHEN E B CO LTD

Unmanned aerial vehicle visual navigation method and device based on deep learning

The invention relates to an unmanned aerial vehicle visual navigation method and device based on deep learning, and the method comprises the steps: obtaining a visual image collected by an unmanned aerial vehicle visual system, carrying out the feature extraction of the visual image, and obtaining image feature representation; performing type analysis on the image feature representation to obtain scene data, depth information and continuous image frames; performing scene identification on the scene data to obtain an identification result of the obstacle and the passable area; performing optical flow estimation on the continuous image frames and the depth information through a preset optical flow algorithm to obtain a pose estimation result; obtaining a task demand of the unmanned aerial vehicle, and obtaining a navigation control strategy with environmental adaptability; and optimizing the self-adaptive mixed learning model according to the feedback information in combination with a preset attention mechanism and a reward shaping condition to obtain an optimized self-adaptive mixed learning model. The adaptive capacity of the unmanned aerial vehicle in a complex and dynamic environment can be improved.
Owner:SHENZHEN TIANYING BROTHERS UAV INNOVATION CO LTD

Water area surface flow velocity area monitoring method based on intelligent visual analysis

The invention discloses a water area surface flow velocity area monitoring method based on intelligent visual analysis, and relates to the technical field of intelligent visual analysis. According to the specific implementation scheme, continuous image collection is conducted on a target water area, dynamic images flowing on the surface of the water area are obtained, and image preprocessing is conducted on video frames of the dynamic images; directly comparing global feature similarities through feature extraction, feature matching and optical flow optimization by using an optical flow estimation algorithm of a convolutional neural network, and outputting optical flow field data of the water area surface flow velocity; after the optical flow field data are obtained, pixel displacement information of optical flow estimation is converted into a flow velocity field on an actual physical unit, and meanwhile regional distribution of the flow velocity on the surface of the water body is analyzed. According to the invention, the optical flow estimation algorithm of the convolutional neural network is utilized to directly compare global feature similarities and output water area surface flow velocity data.
Owner:ZHEJIANG INST OF HYDRAULICS & ESTUARY +1

Method and system for predicting river surface flow velocity based on improved optical flow estimation

The invention belongs to the technical field of river surface flow velocity measurement, and discloses a method and system for predicting river surface flow velocity based on improved optical flow estimation. The RAFT optical flow estimation model established by the invention comprises a query frame residual error estimation module and an optical flow residual error estimation module. The model continuously corrects the deviation between a prediction result and a true value by introducing an IRE mechanism so as to improve the estimation accuracy of a query frame residual estimation module and an optical flow residual estimation module, the query frame residual estimation module is used for performing deep optimization on feature processing and correlation calculation, and the optical flow residual estimation module is used for performing optical flow estimation. The method comprises the following steps: generating query frame estimation through a differentiable internal optimization process, and performing feature convolution operation on the query frame estimation and a query frame image so as to explicitly consider similar areas possibly appearing in a scene. An optical flow residual error estimation module is introduced into a CBAM module, the weight of a feature map is adjusted in a self-adaptive mode, complex water surface information is better captured, and the accuracy of optical flow iteration is improved.
Owner:SHANDONG UNIV OF SCI & TECH

Real-time cable force identification method and device for inhaul cable based on deep learning

The invention belongs to the technical field of bridge health monitoring, and aims at solving the problem that a traditional real-time cable force calculation method is low in recognition precision. The invention provides an inhaul cable real-time cable force identification method and device based on deep learning. The method comprises the following steps that vibration image information of a target inhaul cable is acquired; obtaining a target image sequence based on the vibration image information; adopting an optical flow estimation algorithm based on deep learning to obtain vibration displacement of a target inhaul cable in the target image sequence; variational mode decomposition transformation is conducted on the vibration displacement, and the mode component and the real-time frequency of the target inhaul cable are obtained; performing fast Fourier transform on the modal component, and determining the inherent frequency of each order and the corresponding order of the target inhaul cable; and calculating the real-time cable force of the target cable based on the real-time frequency and the order of the inherent frequency corresponding to the real-time frequency. According to the method, the vibration displacement identification precision of the target inhaul cable is improved, and the robustness of real-time cable force identification is improved.
Owner:CHINA RAILWAY 12TH BUREAU GRP CO LTD +3

Liver blood vessel three-dimensional reconstruction system based on image segmentation

The invention relates to the technical field of three-dimensional reconstruction, and provides a hepatic vessel three-dimensional reconstruction system based on image segmentation, which optimizes an encoder and a decoder of a U-Net by using an attention mechanism, a dynamic weighting uncertainty mechanism and an HS-Swish activation function in image segmentation processing. In combination with hierarchical attention enhancement jump connection and multi-scale cavity convolution, the liver image data is precisely processed; in the aspect of three-dimensional reconstruction, a classical Marching Cubes algorithm is improved, interlayer interpolation of an optical flow estimation method is optimized, intersection point calculation precision is improved by adopting a trisection method, and a high-quality three-dimensional reconstruction model is generated; the system effectively solves the problem that a traditional system is insufficient in precision, image segmentation and reconstruction effects are remarkably improved, and reliable support is provided for the field of liver iconography.
Owner:AFFILIATED HOSPITAL OF ZUNYI UNIV

Rail transit video intelligent analysis method, medium and system

The invention provides a rail transit video intelligent analysis method, medium and system, and belongs to the technical field of rail transit, and the method comprises the steps: constructing a self-adaptive resolution image hierarchical structure, and dynamically determining an optimal resolution hierarchy based on a minimum spanning tree algorithm; constructing an abnormal target movement matrix by combining an improved frame difference method with an optical flow estimation technology; applying a Hungary algorithm to realize target tracking; constructing an abnormal target change index to evaluate a behavior abnormal degree; dividing monitoring stages according to the running state of the vehicle to realize scene self-adaption; an orbit scene attention network model is introduced to identify abnormal behaviors; quantifying a risk level through an abnormal behavior risk assessment function; implementing a hierarchical processing strategy to enable a low-resolution hierarchy to be responsible for global rapid screening and a high-resolution hierarchy to be responsible for fine analysis of key areas; the risk trend is estimated in combination with the rail transit abnormal event prediction model, and the technical problems of large calculation amount and low efficiency of high-definition video processing are effectively solved.
Owner:QINGDAO HENGXUN IND & TRADE CO LTD

Efficient optical flow estimation method and device based on Mama

The invention discloses an efficient optical flow estimation method and device based on Mama, and the method comprises the steps: carrying out the normalization and size alignment of two adjacent frames of images, and extracting the dense features of a fixed down-sampling rate through a shared weight convolution encoder; the two-frame features are sent to a multi-level feature enhancement module, an intra-frame modeling unit and a cross-frame interaction unit are cascaded and matched with channel reforming and residual error correction, and enhanced features are obtained; constructing a four-dimensional cost body on a low resolution, performing probability normalization along a target coordinate dimension, weighting a target coordinate grid according to a probability to obtain a corresponding coordinate, and subtracting the corresponding coordinate from a source coordinate to obtain an initial optical flow; and carrying out attention-guided space fusion on the initial optical flow and context and local correlation, sending the fused optical flow to a differential Mama-based autoregressive refinement module, carrying out iterative updating according to a small number of fixed steps, recovering to a target resolution through convex combination up-sampling, and outputting a final optical flow. According to the method, the optical flow field can be accurately estimated under the conditions of low complexity and low time delay.
Owner:ZHEJIANG UNIV OF TECH

Two-section infrared and visible light image registration method, system and device

The invention discloses a two-stage infrared and visible light image registration method, system and device. The method comprises the following steps of image preprocessing, contour extraction, angular point detection, feature description and matching, affine transformation estimation, multi-scale optical flow estimation, optical flow constraint and loss function, reverse resampling and fusion and error evaluation. According to the invention, rough registration is carried out by using contour angular point features, so that a preliminary alignment result can be quickly obtained; refined alignment is carried out in combination with an unsupervised optical flow network, and sub-pixel-level registration precision is achieved. The contour angular points are based on shape information of an image target, are natural and are not influenced by spectral differences, and the matching stability is enhanced through main direction and angle features. The unsupervised depth optical flow model estimates a pixel displacement field by learning consistency characteristics of an input image, and does not need to depend on annotation data. The combination can effectively eliminate the difference between infrared light and visible light, and improves the robustness and adaptability of registration.
Owner:HANGZHOU DIANZI UNIV

Slope monitoring method based on optical flow estimation and binocular vision

A slope monitoring method based on optical flow estimation and binocular vision belongs to the technical field of deformation monitoring and measurement, and adopts the technical scheme that a binocular stereoscopic vision system is built, and camera acquisition parameters are calibrated; transmitting the image to a server in real time through the Internet of Things; distortion correction and stereo matching are carried out to obtain a depth map; monitoring points are manually or automatically arranged on the corrected image, and dense optical flow estimation tracking pixel point movement is carried out; world coordinates of observation points and movement conditions of each frame are obtained, and displacement changes of slope monitoring points are obtained by combining coordinates before and after displacement; and obtaining a displacement rate by combining monitoring time and displacement, judging slope safety, obtaining a displacement track, and performing linear interpolation to obtain a slope deformation cloud picture, thereby realizing the monitoring purpose. The slope displacement monitoring method has the advantages that slope monitoring can be carried out more flexibly and efficiently, the safety of workers is improved, the slope monitoring cost is reduced, real-time slope displacement monitoring is achieved, and the intensive degree of slope monitoring points is greatly improved.
Owner:DALIAN UNIV OF TECH

Implicit image enhancement and optical flow estimation method based on multi-mode collaborative optimization

The invention discloses an implicit image enhancement and optical flow estimation method based on multi-mode collaborative optimization. The method comprises the following steps: firstly, acquiring an RGB image in a normal illumination scene and a depth map of a corresponding view angle; and calculating corresponding three-dimensional point cloud data according to the depth map and the camera internal reference. And synthesizing low-illumination image data by using the RGB images in the normal illumination scene. Decomposing high-frequency features and low-frequency features of the low-illumination image by using a high-low-frequency feature enhancement network to enhance the low-illumination image, and then extracting image features and context features of the low-illumination image; and extracting 2D image features and 3D point cloud features by using a 2D-3D feature fusion network, and performing alignment fusion to obtain image features and context features of a normal RGB image for supervising the feature extraction process of the high and low frequency feature enhancement network. And finally, based on the image features and context features of the low-illumination image, constructing a 4D correlation volume table, and reasoning the optical flow by using GRU.
Owner:HANGZHOU DIANZI UNIV

Generative ai-based video aspect ratio enhancement

A method includes obtaining, using at least one processing device of an electronic device, a video including multiple scenes at a first aspect ratio. The method also includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation for each of the multiple scenes to select an image frame having a largest missing area. The method further includes performing, using the at least one processing device, outpainting on the image frame having the largest missing area to generate a first outpainted image frame at a second aspect ratio different from the first aspect ratio. In addition, the method includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation using the first outpainted image frame to generate additional outpainted image frames in the multiple scenes at the second aspect ratio.
Owner:SAMSUNG ELECTRONICS CO LTD

Water area detection method based on multi-modal fusion perception

The invention discloses a water area detection method based on multi-modal fusion perception, so as to improve the accuracy and real-time performance of urban waterlogging monitoring. The method comprises the following steps: combined feature extraction of optical flow and visual attributes: collecting continuous image frames, and extracting visual and motion features by using an optical flow estimation network and a convolutional neural network (CNN) in a combined manner to realize accurate perception of water area changes; feature fusion driven by a space-time attention mechanism: constructing the space-time attention mechanism, fusing multi-level features, and forming unified space-time feature representation so as to enhance the detection capability of the ponding area; constructing an end-to-end waterlogging detection model: designing a deep learning network fusing classification and regression tasks, and realizing accurate identification and positioning of a waterlogging ponding area; real-time ponding range tracking and change analysis: based on a dynamic monitoring technology, analyzing an expansion trend of a ponding area, and providing accurate early warning information to support emergency decision making; according to the method, static visual features and dynamic motion features of a water body are extracted in parallel, a multi-modal feature fusion strategy is adopted, and an end-to-end intelligent detection model is constructed. Experimental verification shows that the method has high detection precision and real-time performance in a complex electromagnetic environment, the reliability and intelligent early warning capability of urban waterlogging monitoring are remarkably improved, and powerful technical support is provided for urban water area management and disaster prevention and control.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Dynamic object suppression video image stabilization method based on depth information and global consistency

The invention discloses a dynamic object suppression video image stabilization method based on depth information and global consistency, and the method comprises the steps: extracting key points in a video, carrying out the optical flow estimation, and obtaining the depth information of the key points; a static weight and a motion vector residual error are calculated based on the motion information, the depth information and the global homography matrix of each key point, a dynamic weight is obtained based on an attention mechanism, the dynamic weight and the static weight are fused to obtain a comprehensive weight, and a weighted motion residual error is calculated based on the comprehensive weight and the motion vector residual error; spreading the motion information to grid vertexes, obtaining dense residual motion based on weighted motion residual prediction, and accumulating the dense residual motion to obtain a track; and carrying out smoothing and motion compensation on the track and outputting a stable video sequence. The problem that in a complex scene, motion of a dynamic object causes distortion and inaccuracy of a stabilization result is solved, interference of the dynamic object can be effectively suppressed, and the effect and robustness of video image stabilization are improved.
Owner:WUHAN UNIV OF SCI & TECH

Dynamic gesture recognition method based on space-time interaction and rate perception

The invention discloses a dynamic gesture recognition method based on space-time interaction and rate perception. The method comprises a space-time decoupling feature extraction module, a rate feature injection module and a space-time feature injection interaction module. The space-time decoupling feature extraction is formed by three-dimensional convolution, an Inception module and a multi-scale Transform, and the rate feature injection module realizes visual rhythm feature extraction based on similarity calculation and an optical flow estimation algorithm, performs feature enhancement on an initial feature by using the visual rhythm feature, and performs feature extraction on the initial feature. The spatial-temporal feature injection interaction module is composed of a spatial feature injection module and a time feature interaction module, and the spatial feature injection module and the time feature interaction module are realized based on an attention mechanism. The space-time decoupling feature extraction is a backbone network, and other modules are embedded in the backbone network and play roles of feature injection, feature enhancement and the like. The method relates to the fields of man-machine interaction, dynamic gesture recognition algorithms, deep learning, computer vision and the like, and has the advantages of comprehensive features and accurate recognition.
Owner:SICHUAN UNIV

Fine optical flow estimation system fusing multi-scale kernel selection and super-resolution technology

The invention discloses a fine optical flow estimation system integrating multi-scale kernel selection and a super-resolution technology. Belongs to the technical field of image processing and particularly relates to the technical field of fine optical flow estimation. The problem that the RAFT network estimation precision is reduced is solved. The system comprises a feature extraction network module, a super-resolution iteration updating module and a context network module. The feature extraction network module is used for extracting features of two adjacent frames of images and inputting the extracted related features into the super-resolution iteration updating module; the context network module is used for extracting context features of a previous frame of image in two adjacent frames of images and inputting the extracted context features into the super-resolution iteration updating module; and the super-resolution iteration updating module fuses the related features and the context features to obtain an optical flow vector diagram with super-resolution and outputs the optical flow vector diagram.
Owner:CHANGCHUN UNIV

Optical flow estimation method based on state space model, program, equipment and storage medium

The invention belongs to the technical field of computer vision, and particularly relates to an optical flow estimation method based on a state space model, a program, equipment and a storage medium. According to the invention, an image feature enhancement network based on a CNN-Mama hybrid module and a Mama feature cross enhancement module are designed, and a neural network of a CNN-Mama hybrid cyclic regression framework is designed. The global information of the input image is efficiently extracted by using the image feature enhancement network of the CNN-Mama hybrid module, so that not only can the remote dependency relationship between pixels of the input image be explored, but also the linear complexity can be maintained. According to the method, the Mama feature cross enhancement module is utilized to obtain global motion features, global texture information is aggregated in a motion boundary, information enhancement of the texture features is realized, and finally, the precision of optical flow estimation is improved.
Owner:HARBIN ENG UNIV

Traffic scene multi-target detection method and system based on deep learning

The invention provides a traffic scene multi-target detection method and system based on deep learning, and relates to the technical field of traffic, and the method comprises the steps: carrying out the semantic prior driven multi-scale feature extraction of a multi-frame image, and carrying out the point-by-point fusion; obtaining a motion field through optical flow estimation and feature similarity calculation, and executing motion compensation to obtain a moving target mask; obtaining a static target boundary by using boundary regression decoupling and geometric consistency constraint; and finally, moving and static target results are combined, and quadratic regression is executed based on consistency evaluation. The dynamic and static targets in the traffic scene can be effectively detected, the boundary regression precision is improved, and the false detection rate caused by shielding is reduced.
Owner:JIANGSU TESHI INTELLIGENT TECH CO LTD

Optical flow speed estimation method and system based on image scale invariance

The invention discloses an optical flow speed estimation method and system based on image scale invariance, and relates to the technical field of image processing, and the method comprises the steps: collecting image data through a camera, carrying out the preprocessing, constructing a pyramid according to the preprocessed image data, and generating a descriptor; calculating a matching error based on the generated descriptor, constructing an optical flow estimation model through the matching error, and then outputting a preliminary result; according to the method, the image pyramid structure and the multi-layer descriptor generation technology are combined, the problems that an existing optical flow estimation method is insufficient in precision and poor in robustness in a dynamic scene are solved, in the generation process of the pyramid structure, the robustness of the optical flow estimation method is improved, and the robustness of the optical flow estimation method is improved. According to the method, a weighting method based on feature complexity and edge response intensity is adopted, the image feature extraction precision under multiple scales is effectively improved, and accurate estimation of the optical flow speed on different scales is ensured.
Owner:CHENGDU BOBEI TECH CO LTD

Unmanned aerial vehicle dynamic environment sensing method based on visual large model, electronic equipment and storage medium

The invention relates to an unmanned aerial vehicle dynamic environment sensing method based on a visual large model, electronic equipment and a medium, and the method comprises the steps: carrying out the instance segmentation and optical flow estimation of multiple frames of original images based on the visual large model and an optical flow estimation network, and obtaining a dynamic mask and inter-frame optical flow information; performing feature point classification on the depth information, the dynamic masks and the inter-frame optical flow information corresponding to the multiple frames of images to obtain a classification result; constructing a re-projection error model based on the classification result to obtain an estimated pose; evaluating the quality of the feature points based on the estimated pose to obtain an optimized pose; and constructing a feature point global map based on the world coordinates of the continuous frame road sign points and the optimized poses. Through a multi-information fusion and step-by-step optimization mechanism, the method has relatively high robustness, can adapt to various dynamic environments, and improves environment perception performance and operation reliability in different scenes.
Owner:CIVIL AVIATION UNIV OF CHINA

Vehicle monitoring method based on frame difference and deep learning fusion

The invention discloses a vehicle monitoring method based on frame difference and deep learning fusion, and relates to the technical field of vehicle monitoring, cameras and environment sensors are deployed in a monitoring area, and videos and multi-source data are acquired by means of vehicle-road cooperation; a self-adaptive frame difference method is used, morphology and optical flow estimation are matched, a threshold value is determined according to the environment, and vehicle features are extracted; constructing a deep convolutional neural network with an attention mechanism, and training a model by using various data in combination with migration and reinforcement learning; fusing the two types of features based on a graph attention network to form high-quality fusion features; a space-time diagram convolutional network is combined with an LSTM to track a vehicle and predict a trajectory, a behavior pattern library is constructed to judge abnormity, and classification analysis is performed in combination with an SVM and a knowledge graph. According to the invention, the frame difference and deep learning are fused, the monitoring accuracy is improved, and the vehicle can be accurately identified and detected; the real-time performance is enhanced, the data is quickly processed, and the environmental influence is reduced; traffic management is assisted, and a safe and efficient traffic environment is created.
Owner:YIREN (SHANGHAI) TECH CO LTD

Rock mass fracture identification method based on boundary detection neural network model

The invention relates to the technical field of rock mass fracture recognition, in particular to a rock mass fracture recognition method based on a boundary detection neural network model. According to the method, an innovative deep learning framework is provided for boundary recognition, the characteristics of a refinement strategy and sub-pixel convolution are combined, and a leading result is obtained on a data set. The research shows that the CED model can improve the performance of middle-level and high-level visual tasks including optical flow estimation, target suggestion generation, semantic segmentation and the like. According to the method, a novel architecture is provided to solve the precision problem of a CED algorithm, a reverse refining path is supplemented for an HED network to improve the recognition precision, and the path uses efficient sub-pixel convolution to merge features step by step; the CED provided by the invention can generate an edge image which is well aligned with an image boundary.
Owner:中国建设基础设施有限公司 +1

River surface flow velocity measurement method and system based on physical constraint and multi-modal fusion

The invention discloses a river surface flow velocity measurement method and system based on physical constraint and multi-modal fusion, and relates to the technical field of multi-modal data processing, a target area is determined, and river surface image sequence data, depth information and environment data of the target area are acquired; preprocessing the collected data, embedding redundant codes in data representation, and synthesizing to form a basic data set; and based on the basic data set, performing preliminary optical flow estimation on the river surface image sequence data by using an optical flow method. According to the method, optical flow information, depth information and environment data are fused, comprehensive utilization of multi-source data is achieved, in the data fusion process, redundant codes in data representation are combined for error detection and correction, error points in the data are effectively recognized and corrected, the reliability and accuracy of the data are improved, and the data fusion efficiency is improved. And by utilizing a multi-modal data fusion and error correction mechanism, the robustness of the system is remarkably enhanced, so that the system can stably operate in a complex and changeable river environment.
Owner:LANZHOU UNIVERSITY OF TECHNOLOGY

Optical flow estimation method and system fusing Mama and visual basis model knowledge

The invention belongs to the technical field of computer vision and deep learning, and particularly relates to an optical flow estimation method and system fusing Mama and visual basic model knowledge. The method comprises the following steps: performing down-sampling feature extraction on two adjacent frames of input images by using a convolutional neural network to obtain local texture features; performing down-sampling on the first frame image to obtain context features; meanwhile, extracting global semantic features of two adjacent frames of images by using a pre-trained visual model, and performing adaptive fusion enhancement through an adaptive semantic texture feature fusion module to obtain an image coding feature pair after semantic enhancement; constructing a related volume through pixel-by-pixel dot product operation; and finally, based on the obtained related volume and context features, iteratively optimizing the output optical flow through a loop iteration updating module. The method solves the problems that in a low-texture, repeated-texture or sheltered area, feature expression is unstable, self-adaptive modeling capacity is lacked, different scenes are difficult to generalize, and model performance and efficiency cannot be balanced.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1

Remote sensing image change identification method and system fusing time sequence alignment and semantic perception

The invention relates to the technical field of remote sensing image change detection, in particular to a remote sensing image change recognition method and system fusing time sequence alignment and semantic perception, and the method comprises the steps: obtaining remote sensing images of different time phases in the same region, carrying out the multi-scale feature extraction, and achieving the feature alignment through optical flow estimation under the same scale, performing weighted fusion in combination with an attention mechanism to obtain a fused multi-scale feature group; further through multi-scale convolution and channel and spatial attention enhancement context and detail expression, generating a high-resolution feature map, and finally outputting a pixel-level change recognition map for indicating whether a corresponding geographic position is changed or not; by means of the synergistic effect of optical flow estimation and an attention mechanism, false changes caused by geometric displacement, shadow drifting and seasonal spectral difference can be effectively inhibited, and the stability and reliability of a detection result are improved; and meanwhile, under the support of multi-scale convolution and attention weighting, the recognition capability of the small target and the boundary region is enhanced.
Owner:CHANGZHOU UNIV

Neural ordinary differential equations for optical flow estimation

Techniques are described for optical flow estimation. For example, a computing device can obtain images including at least a first image and a second image. The computing device can process the first image and the second image using a first neural network to obtain a set of features representing the first image and the second image. The computing device can predict, based on the set of features, a latent representation of a change in an optical flow between at least the first image and the second image using a neural ordinary differential equation that uses a second neural network to generate a predicted latent representation. The computing device can estimate the optical flow based on the predicted latent representation to generate an estimated optical flow, wherein the optical flow is associated with movement of pixels from at least the first image to the second image.
Owner:QUALCOMM INC

Heart motion feature extraction method based on optical flow estimation

The invention discloses a heart motion feature extraction method based on optical flow estimation, and relates to medical image processing. Preprocessing the input four-dimensional space-time cardiac magnetic resonance imaging data, namely, scaling pixel values; inputting two frames of images which are continuous in time into a feature encoder and a context encoder for feature extraction, wherein the two frames of images are divided into a reference frame and a moving frame; calculating the correlation between the feature maps through a correlation volume calculation module, constructing a correlation pyramid, and extracting the feature maps to provide matching information for subsequent optical flow estimation; the motion feature iteration enhancement module iteratively and continuously refines an optical flow estimation result through a deformable convolution and global motion aggregation (GMA) module; model parameters are optimized based on a weighted sum of luminosity consistency loss, smoothness loss, and gradient consistency loss. Edge features are adaptively captured through deformable convolution, global and local features are fused by using a GMA module, optical flow prediction errors are effectively reduced, motion estimation quality is improved, and key features of a heart edge region are maintained.
Owner:XIAMEN UNIV

Space-time consistency data generation method for visual target tracking

The invention relates to the technical field of computer vision, in particular to a space-time consistency data generation method for visual target tracking. The method comprises the following steps: firstly, training a path generator on a target tracking training set, learning a motion law of a target in a time sequence by using optical flow estimation and conditional variation coding technologies, and generating a target motion track conforming to physical constraints; and then, based on the generated target trajectory, introducing a space-time consistency attention mechanism to guide a text-video generation model, and under the condition of keeping basic model parameter freezing, constraining the position, scale and continuity of a target in a generation frame through an attention network, thereby synthesizing a video frame sequence with real motion features. According to the method, target tracking video data with real motion characteristics and high time sequence consistency is generated, and the robustness of the model to complex motion, illumination change and shielding conditions can be improved in different scenes.
Owner:QINGDAO UNIV OF TECH

Multi-scale Res2RAFT particle image velocity measurement method based on global attention mechanism optimization

The invention relates to the field of particle image velocimetry (PIV), in particular to a multi-scale Res2RAFT particle image velocimetry method based on global attention mechanism optimization. The invention aims to solve the problem that an existing optical flow network is insufficient in prediction of a fine-grained displacement field in a complex flow field, especially in application in multi-scale vortex and turbulent flow fields. By designing an optical flow estimation structure with multi-scale feature extraction and global information interaction, Res2RAFT can more accurately capture fine flow features in a complex flow field, and the flow field prediction precision and adaptability in a PIV task are improved. According to the Res2RAFT particle image velocity measurement method provided by the invention, the defects of a traditional PIV method in processing an underwater complex flow field are overcome, high-resolution displacement field prediction of the flow field is realized through fine multi-scale feature extraction and a global attention mechanism, and the Res2RAFT particle image velocity measurement method has a wide application prospect.
Owner:ZHEJIANG SCI-TECH UNIV