91 results about "Sparse image" patented technology

The invention discloses a sparse view angle-oriented three-dimensional Gaussian visual positioning method, which belongs to the technical field of positioning, is used for visual positioning, and comprises the following steps of: extracting global image features and local image features of a sparse image, and constructing a feature database; performing nearest neighbor search on the feature database and the RGB image to obtain a sparseness index, calculating a camera pose of a pseudo view angle, rendering a color image and a depth image under the pseudo view angle by using a training main model, extracting global features and local features and storing the global features and the local features into the feature database, constructing a 2D-3D corresponding relation in combination with a target color image, and performing dynamic inner point screening and pose solving. And obtaining a positioning result. According to the method, visual angle deficiency of a key area is intelligently completed, the balance and coverage of feature expression in a three-dimensional scene are effectively improved, and dynamic updating and mismatching elimination of a 2D-3D matching relation are realized, so that the positioning precision and the system stability are remarkably improved, and the method has higher robustness and actual availability under a sparse training condition.

The invention discloses a pig three-dimensional reconstruction method based on sparse multiple views, and the method carries out the optimization of the following two aspects on the basis of a 3DGS three-dimensional model: (1), introducing an adjacent Gaussian anti-pooling strategy, which increases the density of Gaussian distribution in a scene in a more reasonable manner, effectively improves the geometric detail expression capability of the scene, and improves the robustness of the scene; the defects of the 3DGS model in processing complex details are overcome; (2) geometric depth constraint is introduced, depth information of a real or pseudo view is utilized, consistency of rendering depth and estimated depth is optimized through a Pearson's correlation coefficient, the understanding ability of the model to a scene geometric structure is improved, the problem of geometric blur under a sparse view angle condition is effectively relieved, and the method is suitable for being used in a scene. And the reconstruction quality of the sparse multi-view 3DGS model is further improved. According to the method, efficient and accurate pig three-dimensional reconstruction can be realized under the condition of a sparse image visual angle, and the reconstructed pig three-dimensional model is better ensured to still have relatively high stability and precision under different visual angles.

The invention belongs to the technical field of image encryption, and discloses a medical image compression and encryption method and system based on a memristor FHN neuron model, and the method comprises the steps: fusing n color or gray medical images of any size into an M * N * 3 fusion image; sparse representation is carried out on the fused medical image in combination with discrete wavelet transform, and redundant data are reduced; initial conditions and control parameters of an m-FHN chaotic system are generated through an SHA-512 hash value of an original image, and strong association of a secret key and a plaintext is ensured; the m-FHN system is iterated to generate three groups of chaos sequences, and the chaos sequences are quantized to obtain a pseudo-random matrix for diffusion and scrambling operation; performing forward diffusion, index scrambling and backward diffusion operation on the sparse image in sequence to obtain a final compressed and encrypted image; a receiving end acquires an initial parameter and a control parameter bound with a plaintext through a secure channel, and then performs inverse backward diffusion, inverse index scrambling, inverse forward diffusion and inverse discrete wavelet transform on a ciphertext image in sequence to obtain a decrypted image.

The invention discloses a million-frame-level industrial vision system and method based on event driving and compressed sensing, and the system is characterized in that an event camera imaging module in the system captures the brightness change of each pixel in a field of view of the event camera imaging module in an asynchronous manner, and generates an event containing a pixel coordinate, a timestamp and change polarity for each change; a compressed sensing coding module constructs sparse image vectors for events in a time window, and the sparse image vectors are projected to low-dimensional observation vectors through an observation matrix phi; the sparse image reconstruction module is used for optimizing an objective function through sparse constraint and total variation regularization; a dynamic ROI compression module controls a compression mask function according to the event density and a gradient threshold. The method can break through the limitation of the traditional frame rate, has the advantages of high precision, high efficiency, low power consumption, strong robustness and the like, and has a wide industrial application prospect.

The invention discloses a three-dimensional Gaussian splashing method and system for sparse view curve reconstruction, and the method reconstructs a three-dimensional curve scene through a sparse image: firstly, obtaining a dense point cloud and a camera pose, extracting a two-dimensional line segment graph, employing a line segment guide Gaussian initialization strategy, and obtaining a three-dimensional curve scene; generating an initial Gaussian set on the basis of the dense point cloud and the two-dimensional line segment graph; structure perception Gaussian pruning is executed in the optimization process of the initial Gaussian set, and spatial outliers and visibility redundant gauss are removed; and finally, calculating the total loss containing sparse regular terms through the difference between the rendered image and the sparse image, and iteratively optimizing Gaussian parameters until the total loss converges, thereby obtaining a final three-dimensional curve reconstruction result. According to the method, the problem of geometric prior deficiency under a sparse view is solved through line segment guide initialization, overfitting and artifacts are effectively inhibited by using structure pruning and sparse constraint, and high-quality three-dimensional curve reconstruction is realized.

The invention discloses a sparse view angle three-dimensional Gaussian language field construction method and system for humanoid robot grabbing. Comprising the following steps: acquiring an RGB image set and a user natural language instruction under a sparse view angle; reconstructing a three-dimensional point cloud through stereo matching, and initializing a three-dimensional Gaussian primitive field after noise elimination and measurement alignment; two-dimensional semantic features are embedded into the field, joint optimization is carried out through a double-path semantic supervision module, and a three-dimensional Gaussian language field with consistent semantics is constructed; wherein the dual-path semantic supervision comprises an object perception path and a global context path, the local semantic consistency and the overall semantic relationship are constrained respectively, and the final semantic representation of each Gaussian primitive is obtained through weighted fusion; and finally, candidate grabbing postures are generated, semantic reordering is carried out in combination with a language instruction, and the optimal grabbing posture is screened through geometric-semantic joint scoring. Under the sparse image set input condition, the execution accuracy of a robot grabbing task under a complex instruction can be improved.

Disclosed are systems, apparatuses, processes, and computer-readable media for generating images based on sparse images using a multiview image generative machine learning model. A disclosed method includes determining, using a machine learning (ML) model, a plurality of 3D features from one or more two-dimensional (2D) images based on respective pose information associated with each 2D image of the one or more 2D images, wherein the respective pose information is relative to a target pose of a target 2D image; combining, using the ML model, the plurality of 3D features into a plurality of multiview features; and generating the target 2D image including the target pose based on the plurality of 3D features and the plurality of multiview features.

The invention discloses a sparse photo synthesis 3D model reconstruction method based on a deep neural network. The method comprises the following steps of S1, obtaining a sparse image set and performing preprocessing; s2, performing feature extraction to obtain an image feature tensor; s3, constructing a three-dimensional cost body corresponding to the main view under a 1 / 16 spatial resolution hierarchy; s4, calculating scores of the auxiliary views relative to the main view, and selecting an optimal auxiliary view image; s5, performing cost aggregation on the three-dimensional cost body by using a three-dimensional convolutional neural network; s6, calculating depth variance, and constructing a new three-dimensional cost body; s7, repeating the step S6, and generating a dense depth map under a 1 / 4 resolution hierarchy; and S8, completing reconstruction of the 3D model based on the dense depth map. According to the method, the cascade neural network and the visual angle self-adaptive strategy are adopted, high-quality three-dimensional reconstruction under the sparse image condition is achieved, and the method has the advantages of being high in efficiency, excellent in precision and high in robustness.

The invention relates to a method for acquiring photos by using a closeness-density unmanned aerial vehicle to improve the precision of a nerf algorithm, and belongs to the technical field of three-dimensional reconstruction and neural rendering. The method comprises the following steps: collecting multi-view photos in a target scene in a sparse density path through an unmanned aerial vehicle; preprocessing the collected photos, extracting image features and generating sparse point clouds; inputting the extracted features and point cloud data to call a sparse image set to train a NeRF model, and generating high-quality three-dimensional scene reconstruction; by analyzing the deviation between a reconstruction result and a real scene, an unmanned aerial vehicle acquisition path and camera parameters are optimized; according to the optimized path, photos are collected again, the NeRF model is iteratively updated, unmanned aerial vehicle photo collection optimization based on the sparse image set is achieved, the reconstruction precision of the NeRF algorithm is improved, and the method is suitable for a high-precision three-dimensional modeling scene.

The present invention discloses a three-dimensional Gaussian visual positioning method for sparse perspective, which belongs to the field of positioning technology and is used for visual positioning. The method comprises extracting global image features and local image features of a sparse image and constructing a feature database; performing nearest neighbor search on the feature database and the RGB image to obtain a sparsity index, calculating the camera pose of a pseudo-perspective, rendering a color map and a depth map under the pseudo-perspective using a trained main model, extracting global features and local features and incorporating them into the feature database, constructing a 2D-3D correspondence relationship in combination with the target color map, performing dynamic inlier screening and pose solving, and obtaining a positioning result. The present invention intelligently supplements the perspective loss of key areas, effectively improves the balance and coverage of feature expression in three-dimensional scenes, realizes dynamic updating of 2D-3D matching relationships and elimination of false matches, thereby significantly improving positioning accuracy and system stability, and having stronger robustness and practical usability under sparse training conditions.

A computer-implemented method of generating training data to be used to train a machine learning model for generating a segmentation mask of an image containing overlapping particles. Training data is generated from sparse particle images which contain no overlaps. Generating masks for non-overlapping particles is generally not a problem if the particles can be identified clearly; in many cases simple methods such as thresholding already yield usable masks. The sparse images can then be combined to images which contain artificial overlaps. The same can be done for the masks as well which yields a large amount of training data, because of the many combinations which can be created from just a small set of images. The method is simple yet effective and can be adapted to many domains for example by adding style-transfer to the generated images or by including additional augmentation steps.

This application discloses a method, apparatus, device, medium, and product for constructing a spatiotemporal action detection dataset, relating to the field of dataset construction. The method includes cropping surveillance video into short video clips and extracting images to obtain dense image files, sparse image files, and detection image files; detecting all targets in the dense image files and sparse image files using a target detector; traversing the sparse image detection results, annotating target behaviors, and obtaining a target behavior detection dataset; tracking targets in the dense image detection results and sparse image detection results using a target tracker to obtain a target identity dataset; and matching the target behavior detection dataset with the target identity dataset to obtain a spatiotemporal action detection dataset. This application can improve the efficiency and quality of dataset production.

The present invention discloses a synthetic aperture radar (SAR) sparse imaging and autofocusing method, comprising the following steps: S1: assuming that a SAR transmits a continuous wave signal from an ideal array element position and receives an echo, and that the SAR's moving platform has no motion error, an ideal observation matrix and an ideal echo can be obtained; S2: in actual situations, the SAR's moving platform may experience random three-dimensional jitter, and an actual SAR echo containing motion error is obtained, and a mapping relationship between the actual echo and the ideal echo is established; S3: constructing a sparse imaging and autofocusing model; and S4: solving the sparse imaging and autofocusing model using an augmented Lagrangian function and an alternating direction multiplier method to achieve SAR sparse imaging and autofocusing. The present invention introduces an ADMM algorithm within the augmented Lagrangian multiplier, utilizing the structured sparsity of the target and significantly improving image reconstruction quality in weakly sparse scenarios.

The application provides a SAR image target detection method based on SAR image sparse enhancement and Bayesian saliency detection; comprising: step one: inputting a matched filter SAR image, obtaining initial values of regularization parameters of a SAR sparse enhancement method by calculating gray statistical characteristics of the image; step two: solving a convolution sparse feature enhancement algorithm model based on L1 norm by using an alternating direction multiplier method, and obtaining a SAR sparse enhancement image; step three: calculating a Bayesian saliency map of the SAR sparse enhancement image, binarizing the saliency map by using a threshold detection method, and realizing final target detection. The method can reduce SAR speckle noise by using a sparse image enhancement method, reduce background gray values, highlight target regions by using a SAR image saliency detection method, further reduce background pixel values, and finally realize efficient detection of ground and sea surface targets of interest.

The application discloses an industrial CT image reconstruction method and device, electronic equipment and storage equipment, comprising obtaining projection image data and preprocessing to obtain target image data; based on the pre-trained U-Net variant lightweight network, the target image data is processed to obtain fine gradient direction prediction data and structure level similarity data, the U-Net variant lightweight network is trained based on the projection image data and the true value image data, and the loss function of the U-Net variant lightweight network comprises a structure similarity loss; based on the target image data, the fine gradient direction prediction data and the structure level similarity data, the target function is iteratively updated by using an alternating direction multiplier method to obtain reconstructed image data, and the target function is a high-order regularization function constructed based on the second-order total generalized variation and the structure level non-local mean of the iterative image data. The application can inhibit the streak artifact and photon noise of sparse images, so as to meet the requirements of fast scanning and sparse image reconstruction quality.

A method for performing Learned Image Compression (LIC) using a hybrid Learned Sparse Image Representation (LSVR) and Learned Continuous Visual Representation (LCVR) encoding is described. The method, implemented by a video encoding device, includes encoding an image into a bitstream as a set of code indices representing a set of basis elements according to LSVR; encoding the image into the bitstream as a series of continuous real numbers according to LCVR; determining, via a neural network (NN), a degradation-aware latent, which approximates degradation that occurs to the image during LCVR encoding; encoding the degradation-aware latent into the bitstream; and storing the bitstream.

The embodiment of the invention discloses an image processing method and device, electronic equipment and a computer program product. The method comprises the following steps: acquiring a first grey-scale map and a blurring intensity map corresponding to a to-be-processed image; processing light source points contained in the first grey-scale map to obtain a light spot reference map; generating a second sparse image according to the light spot reference image and the first sparse image; and according to the second sparse image and the blurring intensity image, performing point diffusion processing on each target pixel point in the to-be-processed image to obtain a target blurring image corresponding to the to-be-processed image. According to the image processing method and device, the electronic equipment and the computer program product, the calculated amount of image blurring can be reduced, the edge of the light spot in the obtained target blurred image is sharper, the definition and layering sense of the light spot are improved, and therefore the visual effect of the target blurred image is improved.

The invention belongs to the technical field of image processing, and provides a double-branch color point cloud 3D texture grid reconstruction method and device and electronic equipment, and the method comprises the steps: carrying out the multi-view projection and grid reconstruction of an input color point cloud, and obtaining a multi-view sparse image and a texture-free 3D grid; performing multi-view consistency repair on the multi-view sparse image to generate an initial UV texture map; based on a back projection and weighted hybrid algorithm, performing texture repair on the initial UV texture map to generate a complete UV texture map; performing texture resolution enhancement processing on the complete UV texture map to obtain a final UV texture map; and pasting the final UV texture map back to the surface of the texture-free 3D grid to generate a 3D texture grid. According to the scheme, through collaborative optimization of the double-branch frame in the image space and the texture space, the texture definition and the global consistency are improved by utilizing multi-view consistency repair, and the definition of the texture map is improved through texture repair and texture resolution enhancement.

The application discloses a sparse-view three-dimensional Gaussian language field construction method and system for humanoid robot grasping. The method comprises the following steps: acquiring an RGB image set under sparse-view and a natural language instruction of a user; reconstructing a three-dimensional point cloud through stereo matching, initializing a three-dimensional Gaussian primitive field after noise elimination and metric alignment; embedding two-dimensional semantic features in the field, jointly optimizing through a double-path semantic supervision module, and constructing a semantic-consistent three-dimensional Gaussian language field; wherein the double-path semantic supervision comprises an object perception path and a global context path, which respectively constrain local semantic consistency and overall semantic relationship, and the final semantic representation of each Gaussian primitive is obtained through weighted fusion; finally, candidate grasping postures are generated, semantic reordering is performed in combination with the language instruction, and the optimal grasping posture is selected through geometric-semantic joint scoring. The method can improve the execution accuracy of the robot grasping task under complex instructions under the condition of sparse image set input.

The present application belongs to the technical field of photoelectric countermeasure, and relates to a detection technology for a hidden camera device, and particularly provides a long-distance detection method for a hidden camera device based on sparse representation, which is used to overcome the problem of low recognition accuracy in the prior art; in the present application, after sparse representation of an image through wavelet transform, a measurement matrix group is obtained by compressing and projecting the sparse image using a random measurement matrix; a measurement matrix without static background and dynamic background information is obtained by performing a series of difference addition operations on the matrix group; then, the orthogonal matching pursuit algorithm is used to reconstruct and recover the measurement matrix to obtain a recovered image; finally, the cat-eye target area is screened out according to the image pixel value and the connected area area judgment method, so as to realize the cat-eye effect target recognition method based on sparse representation; in this way, the image data redundancy is greatly reduced, the recognition accuracy of the long-distance cat-eye target is effectively improved, and the anti-detection of the hidden camera device is realized, so as to eliminate the potential information leakage danger.

The application belongs to the technical field of camouflage target detection, and provides a camouflage target detection method and system based on confidence awareness evaluation pruning, which comprises the following steps: acquiring a target image to be detected; extracting confidence information in the acquired target image; dividing the acquired target image into a first target image and a second target image according to the extracted confidence information and a double-threshold strategy; processing the obtained first target image by using a double-path feature compensation mechanism to obtain a first target compensation image; performing recursive token backfilling on the obtained first target compensation image and the second target image to obtain backfilling sparse image features at each stage; fusing the obtained backfilling sparse image features at each stage to generate a camouflage target detection result of the target image, thereby completing the camouflage target detection based on confidence awareness evaluation pruning.

The application discloses a snapshot multispectral camera demosaicing method and device based on a binary tree coating array, according to a multispectral original image, a plurality of single spectral band mosaic images are extracted according to spectral bands, and a pseudo panchromatic estimation image is estimated according to the multispectral original image; a difference value between each spectral band sparse pseudo panchromatic estimation image and an original spectral band sparse image is calculated, and the difference value at all pixel positions is calculated; then, the difference value image after filtering and interpolation is added to the pseudo panchromatic estimation image, to obtain a demosaicing reconstruction result based on the pseudo panchromatic estimation image; and the color and spatial correlation between adjacent spectral bands is utilized to enhance the spatial high-frequency information of a binary tree low node spectral band image based on a binary tree high node spectral band image. The above method can solve the artifact problem caused by the weak spectral correlation of a wide spectral distribution filter, reduce the artifact of a reconstructed image, and improve the spatial resolution of the image after demosaicing.

The application provides a global sparse texture filtering method based on edge structure preservation, including introducing a texture inhibition function in a penalty term, and constraining the gradient of an output image, the texture inhibition function inhibits texture, noise and unnecessary detail information in the image by setting two threshold values, then using the inhibited gradient as the input of the denominator of the penalty term, so that the penalty term can sufficiently distinguish texture and structure; sparse regular L1 norm is used to constrain the penalty term, non-convex optimization is converted into a convex optimization problem by introducing a sub-gradient, and an alternating direction multiplier method is used for iterative solution, so that better edge preservation is achieved; sparse L p Norm is used to constrain the penalty term and a preconditioned conjugate gradient method is used to accelerate and improve the calculation efficiency, so that more robust and sparse image smoothing effect is achieved. The application can improve the robustness of the algorithm in distinguishing texture and structure, retain better semantic information, and achieve better edge structure preservation and smoothing performance.

The invention discloses an image restoration method and device based on AI and CG algorithms, and relates to the technical field of image restoration. The method comprises the steps that a real image, a damaged image, an AI reference image, a difference image and a damaged image of the difference image are acquired, an AI repair image serves as prior information and is combined with wavelet transform, TV operator and L1 norm prior information, a wavelet coefficient model of the repaired difference image is constructed, and a CG algorithm is utilized to calculate and obtain a repaired difference image wavelet coefficient; after inverse wavelet transform is carried out, a repaired difference image is obtained; and finally, utilizing the repaired difference image and the AI reference image to obtain a repaired image. The method solves the problems that the AI platform is not high enough in repairing precision due to the parameter generalization problem, and the traditional modeling method is fuzzy in repairing, and improves the image repairing precision of the AI platform and the traditional modeling method. Moreover, the method provided by the invention is suitable for sparse image restoration, such as SAR images, and is also suitable for smooth natural images and the like.

The invention provides a mirror image file programming method and device, electronic equipment and a computer program product. The method comprises the steps of obtaining first data contained in a to-be-programmed first mirror image file; the first data is fill data; the first mirror image file is a sparse image; filling the first data with second data to obtain third data; determining a first programming mode corresponding to the third data according to the second data and a first value; the first programming mode at least comprises writing in a first storage medium or erasing a first offset address and size in the first storage medium; the first value is 0; the first storage medium is an emmc storage medium; and programming the third data to a first storage medium according to the first programming mode. The programming efficiency of the mirror image file can be improved, so that the programming time consumption of the mirror image file is reduced.

The invention discloses a sparse image stripe defect complementing and repairing method and device, and relates to the technical field of image repairing. The method comprises the following steps: acquiring a sparse image with fringe defects; performing two-dimensional difference sparsification on the sparse image with the fringe defect to obtain a sparse difference domain; performing two-dimensional Fourier transform on the sparse difference domain to obtain a difference frequency domain; based on the difference frequency domain, constructing a difference frequency domain binary Hankel structure matrix; and constructing a sparse image completion model based on the differential frequency domain bifolding Hankel structure matrix, and solving the sparse image completion model in a distributed manner by using an alternating iteration ADMM algorithm to obtain a repaired sparse image. According to the method, stripe defects of the sparse image can be effectively processed, the repaired image does not have obvious stripe traces, a new theoretical method and an effective way are provided for sparse image repair, and the method has important significance on image processing in the fields of biomedical imaging, aerospace, astronomy and the like.

The invention relates to a multi-view three-dimensional reconstruction method based on a video diffusion model, and the method comprises the steps: extracting multi-scale point clouds from an original sparse image set, and fusing the multi-scale point clouds into a global three-dimensional point cloud image; the reconstruction track is segmented into a plurality of segments, each segment comprises one or more new view angles, and image generation is performed on each segment in sequence, including: projecting a corresponding point cloud in the global three-dimensional point cloud image to the current segment to obtain a rendering index map and a rendering color map, and screening a reference frame from a dynamic acquisition view library; inputting the reference frame, the rendered color map and the visibility mask of the rendered color map into a disordered context video diffusion model, and outputting an image sequence containing the new view angle complete image and the reference frame; and extracting the point cloud of the new view angle complete image to update the global three-dimensional point cloud image to guide the image generation of the next segment. The problems of poor geometric consistency and insufficient expansibility of a reconstruction result when an input view angle is sparse and disordered and long-distance displacement exists are solved.

The present invention proposes a sparse image view synthesis method based on time-domain filtered neural radiation fields. This method innovatively introduces a time-domain filtered neural radiation field model to solve the problem that the neural radiation field represented by the multi-layer perceptron has high rendering overhead and cannot reduce the aliasing noise of the synthesized image by oversampling. By applying filtering technology in the time domain, the computational burden required for oversampling is effectively shared over consecutive frames, thereby significantly improving the quality of the synthesized image and effectively reducing noise and aliasing without increasing the number of additional network inferences. In addition, in order to improve the geometric extraction capability of the neural radiation field, the method introduces a deep prior network and designs an inter-frame geometric consistency loss to enhance the expression capability of the neural radiation field in multiple views and improve the generalization performance of the network.

Provided are a depth completion method and apparatus using spatial-temporal information. The depth completion apparatus according to the present invention comprises a processor; and a memory connected to the processor, wherein the memory stores program instructions executable by the processor for performing operations comprising receiving an RGB image and a sparse image through a camera and LiDAR, generating a dense first depth map by processing color information of the RGB image through a first branch based on an encoder-decoder, generating a dense second depth map by up-sampling the sparse image through a second branch based on an encoder-decoder, generating a third depth map by fusing the first depth map and the second depth map, and generating a final depth map including a trajectory of a moving object included in an RGB image continuously captured during movement by inputting the third depth map to a convolution long term short memory (LSTM).

The invention discloses a rapid reverberation suppression method, system and device based on variational Bayes. The method comprises the following steps: generating a two-dimensional data matrix according to a three-dimensional sonar image sequence; a variational Bayesian algorithm is used to separate low-rank components and sparse components in a data matrix, and a generalized approximate message passing algorithm is used to avoid a matrix inversion step in a variational Bayesian iteration process so as to reduce low-rank sparse decomposition time; and reversely quantizing the two-dimensional sparse matrix into a three-dimensional sparse image sequence. The system comprises a data conversion module, a separation module and a reverse quantity module. The device comprises a memory and a processor used for executing the rapid reverberation suppression method based on variational Bayes. By using the invention, reverberation suppression can be quickly and stably implemented, so that a moving target can be detected. The method can be widely applied to the field of active detection of underwater moving targets.