275 results about "Motion estimate" patented technology

The invention provides a medical image denoising and segmentation integrated model trained based on a conductible diffusion method, and belongs to the field of medical image processing, and the model comprises an improved denoising and diffusion module which is used for receiving an initial medical image, predicting an original clean signal of the initial medical image based on an improved denoising and diffusion probability model, and obtaining a final denoised medical image; the joint motion and segmentation module is used for receiving the initial medical image, extracting features through a shared encoder, and performing joint learning through a motion estimation branch and a segmentation branch to obtain segmentation data; the cascade training mechanism carries out end-to-end training on the improved de-noising diffusion module and the joint motion and segmentation module through a derivable connection, gradient back propagation is realized by using a joint loss function, and cascade training is completed. According to the method, the problem that the quality of segmented medical images is reduced due to the fact that denoising and segmentation tasks cannot be collaboratively optimized due to the fact that a traditional denoising method cannot be guided in sampling and is difficult to carry out cascade training with a segmentation model is solved.

A computer-implemented method includes converting by a pose tokenizer, based on a learned codebook, pose parameters of a body into a sequence of discrete pose tokens; randomly masking a portion of the sequence of discrete pose tokens; predicting the randomly masked sequence of discrete pose tokens based on multi-scale features extracted from a monocular image by an image conditioned masked transformer; optimizing the sequence of discrete pose tokens by aligning a re-projected three-dimensional (3D) pose with an estimated two-dimensional (2D) pose; directly regressing, from the multi-scale features, a shape parameter of the body and a weak perspective camera parameter; and generating a 3D mesh reconstruction of the body based on the shape parameter and the weak perspective camera parameter.

The invention discloses a motion carrier self-motion estimation method based on multi-radar fusion, a carrier and a medium, and relates to the technical field of motion carrier positioning. The method comprises the following steps: performing consistency check among radars based on self-motion estimation results of the radars, and judging whether the radars with abnormal self-motion estimation results exist or not according to check results; if not, the self-motion estimation results of all radars are fused, and a final self-motion estimation result is output; if so, identifying an abnormal radar from the radars according to at least one quality index; and discharging the self-motion estimation results of the radars identified as abnormal, and based on the self-motion estimation results of the remaining radars not identified as abnormal, performing fusion or directly outputting the self-motion estimation results as the final self-motion estimation result. According to the method, the abnormal source can be automatically identified and isolated, and the robustness and the function security level of the system in a real complex environment are remarkably improved.

The invention relates to the field of digital image processing, in particular to a super-resolution imaging method based on focal plane splicing and adaptive fusion. According to the method, sub-pixel offset among nine CCDs is preset through hardware, and nine frames of low-resolution image sequences with accurate displacement are obtained in push-broom. A central image is taken as a reference frame, high-precision mapping is realized based on hardware offset, motion estimation errors are avoided, effective pixels are screened by calculating robustness weight, an anisotropic Gaussian kernel function with a self-adaptive local structure is constructed so as to maintain image edge and detail features, and each frame is accumulated to a high-resolution grid in a weighting mode, so that a high-resolution image is obtained. And a sample compensation mechanism based on cumulative robustness is introduced, a fusion strategy is adaptively adjusted in an information insufficient area, and finally a high-resolution image is generated through normalization. The method significantly improves the imaging quality, suppresses artifacts and noise, and is suitable for the field of satellite remote sensing.

The invention discloses an ultra-high-definition video stream adaptive coding method based on deep learning visual saliency, and the method comprises the steps: carrying out the five-scale Gaussian filtering processing and image pyramid construction of a video frame, and combining Sobel gradient, Laplacian edge and local binary pattern feature extraction to generate a multi-scale feature map; a pre-training saliency detection network is adopted, and a smooth saliency thermodynamic diagram is generated through processing of a feature adaptation layer, a residual encoder, a self-attention mechanism and a transposed convolution decoder; dividing the video frame into a high region, a middle region and a low region according to the saliency thermodynamic diagram, and establishing a regionalization coding parameter table; performing differentiated prediction modes, motion estimation and quantization strategies on different salient regions; and organizing coded data according to an H.265 / HEVC standard, and embedding the saliency thermodynamic diagram into supplementary enhancement information for transmission. According to the method, the important region concerned by the user can be intelligently identified, a differentiated coding strategy based on content semantics is realized, and the coding efficiency is remarkably improved.

The invention relates to the technical field of steel wire rope state detection, in particular to a steel wire rope diameter measuring method and system based on event compensation correction. According to the technical scheme, the system comprises an imaging module, a boundary initial extraction module, a dynamic motion estimation module, a dynamic correction compensation module and a diameter calculation module. The imaging module comprises a traditional camera, an event camera, an optical component, a synchronous triggering device and a spectroscope. The traditional camera is used for collecting frame images of the steel wire rope. According to the method, on the basis of complementary advantages of an event camera and a traditional camera, systematic measurement deviation under the dynamic working condition is solved from the mechanism through an event-driven dynamic geometric compensation model, and quasi-static imaging dependence is broken through. The method does not need extra constraint or increase of frame rate, control cost and hardware complexity, avoids the problems of reduction of signal-to-noise ratio and the like, realizes high-precision stable measurement under high-speed and vibration working conditions, adapts to online monitoring of multiple industrial scenes, and is remarkable in practicability and application value.

Systems and techniques are described herein for interpolating image data. For instance, a method for interpolating image data is provided. The method may include processing a first image frame and a second image frame using a motion estimator to generate first motion vectors, wherein the motion estimator comprises a machine-learning model trained to generate motion vectors based on image frames; projecting the first motion vectors to generate second motion vectors; and generating a third image frame based on the first image frame, the second image frame, and the second motion vectors.

A method for scale-aware depth estimation using multi-camera projection loss is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes training a scale-aware depth estimation model and an ego-motion estimation model according to the multi-camera photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the scale-aware depth estimation model and the ego-motion estimation model. The method also includes planning a vehicle control action of the ego vehicle according to the 360° point cloud of the scene surrounding the ego vehicle.

The motion estimation of an anatomical structure may be performed using a machine-learned (ML) model trained based on medical training images of the anatomical structure and corresponding segmentation masks for the anatomical structure. During the training of the ML model, the model may be used to predict a motion field that may indicate a change between a first training image and a second training image, and to transform the first training image and a corresponding first segmentation mask based on the motion field. The parameters of the ML model may then be adjusted to maintain a correspondence between the transformed first training image and the second training image and between the transformed first segmentation mask or a second segmentation mask associated with the second training image. The correspondence may be assessed based on at least a boundary region shared by the anatomical structure and one or more other anatomical structures.

The invention discloses a ViT model lightweight method for video action recognition, which comprises the following steps of: performing motion estimation in a data processing stage, calculating to obtain motion intensity and time redundancy scores of tokens, and performing window division on video frames according to the scores. Afterwards, a window-global token merging strategy is adopted to effectively merge redundant tokens, the first three layers of the model process local information through adaptive window merging, and from the fourth layer, the model repeatedly executes global merging according to the depth of the layers so as to realize gradually enhanced feature representation; therefore, the number of tokens is reduced, the complexity of the ViT model in space-time self-attention calculation is reduced, and the problem of high calculation resource consumption caused by space-time information redundancy of the current ViT model in a video task is solved. Calculation overhead and energy consumption can be remarkably reduced in tasks such as video action recognition, action detection and time sequence event understanding, and meanwhile the characterization capacity of a key dynamic area is kept.

The invention provides a curvature-enhanced large-displacement image variational optical flow method for motion estimation, relates to the field of image processing, and aims to describe the local structure complexity of an image by introducing an image contour curvature. On the basis of the curvature, limited self-adaptive weighted adjustment is carried out on the brightness invariant constraint and the gradient invariant constraint on the data item level of the opto-rheological model, so that the interference of unreliable matching in a complex structure region on optical flow estimation is inhibited; the robustness of optical flow estimation in illumination variation, complex texture and large displacement scenes is improved; and the numerical stability and convergence of the model in the multi-scale calculation process are ensured.

Systems and methods for reducing latency through motion estimation and compensation techniques are disclosed. The systems and methods include a client device that uses transmitted lookup tables from a remote server to match user input to motion vectors, and tag and sum those motion vectors. When a remote server transmits encoded video frames to the client, the client decodes those video frames and applies the summed motion vectors to the decoded frames to estimate motion in those frames. The server instructs the client to receive input from a user, and use that input to match to cached motion vectors or invalidators. Based on that comparison, the client then applies the matched motion vectors or invalidators to effect motion compensation in a graphic interface. In this manner, latency in video data streams is reduced.

The invention discloses an FPGA point cloud registration acceleration method and system based on a scanning line auxiliary distance projection structure, and the method comprises the steps: carrying out the projection of a source LiDAR point cloud according to a distance and an azimuth angle, taking the Euclidean distance from a point to a sensor in an azimuth angle partition as a distance domain, dividing the distance domain into distance scale segmentation domains, and distributing distance scales, counting points in a distance scale segmentation domain, accumulating according to the distance scale to obtain an initial position, forming an SA-RPS-Index initial index array, executing counting sorting on source LiDAR point clouds, rearranging points which belong to the same distance scale segmentation domain and are positioned in the same distance scale into a continuous memory, generating an SA-RPS-Point point array, and storing the SA-RPS-Point point array in the SA-RPS-Index initial index array in the SA-RPS-Index initial index array in the SA-RPS-Index initial index array in the SA-RPS-Index initial index array. A scanning line auxiliary distance projection structure is obtained in combination with an SA-RPS-Index initial index array, each query point in a target LiDAR point cloud is marked to extract a candidate point, the distance between the candidate point and the query point is calculated, a PNN-C triple and an ENN-C edge corresponding point set are obtained in combination with K neighborhood and scanning line attributes, rigid body transformation between a source point cloud and a target point cloud is solved, and the target point cloud is obtained. And obtaining a motion estimation result.

The invention relates to the field of weather prediction, and particularly discloses an intelligent hail monitoring and early warning method and system based on morphological learning, equipment and a medium, and the method mainly comprises the steps: obtaining the multi-source data of hail cloud, and carrying out the recognition and extraction of the key morphological features of the hail cloud based on the multi-source data; a space-time evolution model is constructed, the space-time evolution model comprises a ConvLSTM space-time prediction model and optical flow method motion estimation, and predicted hail cloud key morphological characteristics are output based on the space-time evolution model; and the multi-feature fusion module is configured to perform multi-feature fusion on the key morphological features of the hail cloud, the multi-feature fusion comprises weighted fusion and an attention mechanism, a loss function is set for optimization, and a hail prediction result is obtained. According to the method, the hail cloud form change under different hail disasters is learned through the form learning network according to the form change in the time sequence change process of the hail cloud, the hail is dynamically predicted in combination with the form change, and accurate and dynamic prediction of the hail is achieved.

The invention relates to the technical field of video processing, and provides a diffusion model-based video super-resolution reconstruction method for an unmanned aerial vehicle in order to avoid the problems of optical flow alignment errors and limited computing power of the unmanned aerial vehicle, comprising video compression and fuzzy degradation modeling and video diffusion converter model construction. Carrying out iterative optimization and observation consistency correction; and reducing the potential representation after iterative optimization into a high-resolution video frame through a decoder to complete super-resolution reconstruction. And meanwhile, the bandwidth requirement is reduced, and the weak network adaptability is better. Due to the adoption of the technical scheme, accurate reconstruction of a high-resolution video is realized in a low-dimensional potential space. Therefore, the problem of edge artifacts caused by motion estimation errors in a traditional method is thoroughly solved, and the definition and the natural sense of a reconstructed video are remarkably improved.

The application discloses a kind of based on in-vivo micro intelligent terminal system image digestive tract length calculation method, device, storage medium and equipment.The method comprises: feature point extraction and matching are carried out to the image set of preprocessed in-vivo micro intelligent terminal system, obtain two-dimensional feature point set, carry out depth value detection, obtain depth map, obtain three-dimensional feature point set according to depth map and the two-dimensional feature point set;Three-dimensional plane fitting is carried out according to three-dimensional feature point set, obtain the plane equation corresponding to each adjacent two frames of images respectively, obtain the depth difference and lateral displacement difference between each adjacent two frames of images, and the depth difference and lateral displacement difference constitute three-dimensional displacement vector;The cumulative calculation of all three-dimensional displacement vectors corresponding to image set is carried out, and the length of digestive tract is obtained.The method can eliminate the dependence on external hardware, improve system integration, based on three-dimensional plane fitting motion estimation, enhance the robustness in non-rigid environment, realize the continuous and accurate measurement of length.

A method for motion estimation in CT systems is provided. The method includes dividing projection data, obtained by scanning a heart using the CT system, into a plurality of partial-angle-reconstruction (PAR) bins, reconstructing a plurality of PAR volumes from the PAR-binned projection data, obtaining, based on the plurality of reconstructed PAR volumes, a number of short-scan volumes, determining, based on the obtained number of short-scan volumes, a plurality of nodes throughout the heart, estimating, for each of the determined plurality of nodes, a plurality of model parameters of a motion model, and generating, based on the plurality of model parameters estimated for each of the plurality of nodes, parameters of a global motion model at each voxel of a volume of the heart. The method also includes reconstructing, based on the generated motion parameters of the global motion model at each voxel of the volume of the heart, a motion-compensated short-scan volume.

The embodiment of the invention discloses a coding and decoding method and device, a codec, a code stream, equipment and a storage medium, and the decoding method comprises the steps: determining a first difference value of a sample value between a first reference block pointed by a first candidate MV of a current block and a second reference block pointed by a second candidate MV of the current block; determining a second difference in sample values between the template of the current block and the template of the first reference block; determining a third difference in sample values between the template of the current block and the template of the second reference block; performing motion estimation on the current block at least according to the first difference value, the second difference value and the third difference value to obtain a first prediction MV and a second prediction MV of the current block; and performing motion compensation on the current block according to the first prediction MV and the second prediction MV to obtain a prediction block of the current block.

The invention relates to the technical field of industrial visual inspection, and discloses a self-supervised motion estimation method for fiber laying thermal imaging, which comprises the following steps: acquiring continuous thermal imaging frames and a main motion direction, forming a thermal imaging frame pair, inputting the thermal imaging frame pair into a preset motion estimation network to obtain an inter-frame displacement field, the method comprises the following steps: extracting directional components in a fiber laying area, performing area aggregation, forming original velocity estimation values according to a main motion direction, constructing a velocity statistical table based on a plurality of continuous original velocity estimation values, forming a domain migration result, triggering physical constraint solution to obtain target effective parameters, and performing target effective parameter calculation. And correcting the original speed estimation value according to the target effective parameter to obtain a stable speed estimation value, and performing displacement accumulation on the stable speed estimation value to form a paving layer displacement reconstruction result, thereby suppressing displacement drift under the condition of equipment platform switching and material system switching, and ensuring the paving layer displacement reconstruction consistency.

The invention relates to a mobile robot motion estimation method based on pose decoupling. The method comprises the following steps: multi-sensor synchronization and decoupling state modeling; performing attitude-position decoupling pre-integration based on an IMU (Inertial Measurement Unit); visual observation modeling and reprojection constraint construction are carried out; carrying out pose optimization solution based on the decoupling factor graph; pose recovery, motion track output and local re-initialization are carried out; compared with the prior art, the method has the advantages that independent modeling and decoupling estimation are carried out on the pose rotation component and the translation component, the propagation effect of rotation errors to translation solution in traditional visual motion estimation is effectively inhibited, and the stability of translation estimation is remarkably improved. Under visual degradation scenes of weak texture, low parallax, illumination variation, motion blur and the like, estimation drift can be reduced, track continuity and consistency can be improved, and robustness of the system to abnormal matching and noise disturbance can be enhanced; besides, the decoupling mechanism provided by the invention has good universality, can be integrated with various types of visual SLAM or visual-inertial fusion frames, and provides more reliable motion estimation capability for stable autonomous navigation of the mobile robot in a complex environment.

This invention provides a motion estimation-based method for accelerating video recognition, comprising: identifying keyframes and non-keyframes in a video sequence; extracting features from keyframes using a Bayer domain basic model to obtain perceptual features; calculating motion vectors between non-keyframes and a reference frame (the frame preceding the non-keyframe) using a fast motion estimation module, wherein the fast motion estimation module employs a pyramid block structure and performs multi-level matching search from coarse to fine under a GPU parallel architecture; deforming the features of the reference frame using the motion vectors to obtain propagation features; predicting the perceptual residual of the current frame using a perceptual residual correction network, numerically correcting the propagation features using the residual, and outputting the corrected propagation features, wherein the perceptual residual correction network is a lightweight network structure; and performing video recognition based on the corrected propagation features. This invention achieves faster and more efficient video recognition.

The application discloses a motion estimation method, device and computer equipment. The method comprises the following steps: determining a target coding block in a target video frame; performing motion vector prediction on the target coding block by using an advanced motion vector prediction method to obtain a predicted motion vector of the target coding block; selecting a plurality of reference coding blocks of the target coding block from history coding blocks of a video sequence to which the target video frame belongs and which have been completed coding, wherein the history coding blocks comprise coding blocks that are not adjacent to the target coding block in time domain and coding blocks that are not adjacent to the target coding block in space domain; obtaining a motion vector of each reference coding block in the plurality of reference coding blocks, and taking the obtained motion vectors of the plurality of reference coding blocks as a plurality of candidate motion vectors of the target coding block; taking a pixel position pointed by a motion vector with the minimum rate-distortion cost in the plurality of candidate motion vectors and the predicted motion vector as a search starting point, and performing motion estimation on the target coding block by using the search starting point, so that the efficiency of motion estimation can be improved.

Described herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and a motion estimating neural network (122, 700, 800, 900, 1000) configured for outputting trajectory data (130) in response to receiving a trial motion trajectory (128) as input. The execution of the machine executable instructions causes a computational system (104) to: receive (200) measured k-space data (124) descriptive of a subject (318); perform (202) motion estimation of the subject between the sequence of discrete acquisitions by solving an optimization problem to determine a calculated motion trajectory of the subject in the predefined coordinate system, wherein the optimization problem is modified using the trajectory data; and reconstruct (204) a final motion corrected magnetic resonance image (136) from the measured k-space data and the calculated motion trajectory in the predefined coordinate system.

In various embodiments, when reference picture resampling is applied to achieve better coding efficiency, methods and devices adapt temporal filtering of a noise-reduced input video prior to encoding according to a resolution ratio. According to one embodiment, temporal filtering strength values are fine-tuned at a pre-processing module according to the resolution ratio of the RPR mode. According to another embodiment, temporal filtering is deferred after rescaling when the RPR mode is enabled, and filtering strength values are fine-tuned according to the resolution ratio of the RPR mode. A third embodiment proposes to refine motion estimation in the encoder by setting the block size of motion estimation in temporal filtering according to the resolution ratio of the RPR mode.

A video motion estimation method including obtaining a plurality of image frames in a video, and performing scenario classification processing on the plurality of image frames to obtain a plurality of image frame sets. The method further includes extracting a contour feature and a color feature of a foreground object of each image frame, and determining a search range corresponding to each image frame set. The method further includes determining a starting search point in each predicted frame. The method further includes, for each image frame set, performing motion estimation processing in a search region corresponding to the search range of each predicted frame set based on the starting search point of the respective predicted frame, a reference block in at least one reference frame of the respective image frame set, and the color feature of the foreground object, to obtain a motion vector corresponding to the reference block.

The invention relates to the technical field of time delay measurement, and provides a robot control end-to-end time delay measurement method and device and electronic equipment. The method comprises the following steps: acquiring a trigger timestamp of a robot motion instruction; based on a candidate displacement composite search strategy and a cost function early stop mechanism, performing global motion estimation on a monitoring video stream corresponding to the robot to obtain a global timestamp of global motion of a monitoring image in the monitoring video stream; the candidate displacement composite search strategy is used for adjusting a search sequence of candidate displacement between adjacent monitoring images based on motion space-time continuity; under the condition that the candidate displacement triggers a cost function early stop mechanism, the cost function early stop mechanism is used for terminating calculation of a cost function of the candidate displacement in advance; and determining an end-to-end time delay corresponding to the robot based on the global timestamp and the trigger timestamp. According to the embodiment of the invention, the end-to-end time delay of a complete link can be measured, and the accuracy and real-time performance of time delay measurement are improved.

This invention relates to an image denoising method, system, and readable storage medium. The method includes: performing Gaussian filtering and downsampling on a current frame image to obtain a first downsampled image; performing Gaussian pyramid decomposition to obtain a current frame image group; upsampling to obtain an upsampled image, and subtracting it from the current frame image to obtain high-frequency information; performing motion estimation and texture estimation at different scales on the current frame image group and a reference frame image group, and correcting them with guided filtering; performing spatiotemporal filtering on the first downsampled image and the reference frame image based on motion estimation weights; upsampling the denoised downsampled image to obtain a denoised upsampled image; and weighted fusing the denoised upsampled image and high-frequency information according to texture estimation weights to obtain a final image; downsampling the final image and performing Gaussian pyramid decomposition to obtain a reference frame image group for denoising the next frame image. This invention can preserve more texture details while increasing the image signal-to-noise ratio.

The application provides a curvature-enhanced large displacement image variational optical flow method for motion estimation, relates to the field of image processing, and aims to depict the complexity of local structures of an image by introducing the curvature of the image contour line, and to restrict the adaptive weighting adjustment of the brightness invariable constraint and the gradient invariable constraint on the basis of the curvature in the data item level of the variational model of the optical flow, so as to inhibit the interference of unreliable matching pairs on the optical flow estimation in the complex structure area, improve the robustness of the optical flow estimation under the scenes of illumination change, complex texture and large displacement, and guarantee the numerical stability and convergence of the model in the multi-scale calculation process.

The application provides an infrared small target cloud-penetrating continuous tracking method and belongs to the technical field of target detection and tracking. In the application, step one is a feature extraction process; firstly, a DLA-34 network is used to perform image feature extraction on an original image, and then a multi-scale apparent feature is extracted through an encoding network stacked by three convolution layers; a target prediction frame based on apparent matching is obtained through a hierarchical guided motion estimation module; step two is a training process; a loss function is constructed through a constraint probability cost volume; step three is an inference process; a measurement method based on apparent features for an infrared small target track is designed, the prediction frame is matched with a detection result, the matched track is replaced by the detection result, the un-matched track retains the prediction frame until successful matching, and the intermediate discontinuous part is filled after the track is successfully matched. The application can effectively adapt to scenes with lack of target spatial features, weak energy and unclear motion state, and can enhance the tracking performance of the infrared small target.

The invention relates to the technical field of data processing, and provides a target motion estimation method and device based on an optical flow method, and the method comprises the steps: collecting k continuous images corresponding to a to-be-detected target through an image collection device, and obtaining a to-be-detected target image set; determining optical flow field information of the to-be-detected target according to the to-be-detected target image in the to-be-detected target image set based on an optical flow method to obtain first optical flow field information; scene flow information of a to-be-detected target is determined according to equipment parameters of an image acquisition device and the first optical flow field information, first scene flow information is obtained, and the equipment parameters of the image acquisition device comprise the focal length and main point position information of the image acquisition device; and performing motion estimation on the to-be-detected target according to the first scene flow information to obtain a motion estimation result, so that the light flow information of the to-be-detected target can be adopted to perform motion estimation to obtain the motion estimation result, and the accuracy of determining the motion estimation result is improved.