51 results about "Texture perception" patented technology

The invention relates to the technical field of medical image analysis, computer vision and deep learning, in particular to a texture perception and multi-scale feature adaptive fusion hip joint osteophyte detection method. According to the method, firstly, a bone texture feature extraction module is used for carrying out feature extraction and enhancement on a hip joint X-ray image, a parallel double-branch structure is adopted, gradient and space structure features are extracted through a Sobel operator and pooling operation, and feature maps are fused; then, the fused features are input into a double-backbone network, the first backbone network extracts local fine textures and long-range dependence features by combining convolution, self-attention and a gating mechanism, and the second backbone network extracts multi-scale semantic features through hierarchical grouping and depth separable convolution; and double-trunk output is dynamically weighted and fused through an adaptive fusion module, features are optimized through a multi-scale semantic fusion module, and finally the position and confidence of osteophyte are output.

The invention discloses a video anti-shake method and system based on multi-scale fusion and adaptive smoothing, relates to the technical field of video image processing, and aims to effectively solve the image quality problem caused by shake in a video shooting process. Gradient histograms and wavelet energy distribution characteristics of video frames are extracted through graying and normalization processing, and the gradient histograms and the wavelet energy distribution characteristics are input into a jitter type recognition network to recognize translation, rotation and Z-axis jitter probabilities. And further extracting motion, frequency domain and edge features, and generating multi-modal coupling features through combination of a dynamic feature interaction network and a dot product attention mechanism. And constructing a motion trajectory by using the features, optimizing the trajectory by using a texture perception double-layer smoothing strategy, introducing an adaptive penalty term into a dynamic planning cost function, and outputting a smooth motion compensation parameter. And finally, processing the boundary region through motion compensation and image extrapolation to generate an anti-shake video frame. Through multi-scale feature fusion and a self-adaptive smoothing strategy, the video anti-shake effect is effectively improved, and the method is suitable for complex scenes.

The invention discloses a cloth surface flaw detection method and device based on texture perception and anomaly detection. The method comprises the following steps: acquiring a surface image of detected cloth; inputting the surface image of the detected cloth into a deep learning network model; a multi-scale feature map is extracted through the backbone network; processing the feature map through the texture perception feature extraction module so as to fuse cross-channel and cross-space texture information; integrating anomaly detection branches through the check network, and outputting feature maps of different scales; performing frequency domain enhancement and spatial domain feature extraction operation and fusion on the features through the adaptive frequency domain convolution module; and outputting a detection result through the YoloHead detection head so as to judge whether the cloth has flaws or not. According to the method, the texture feature information in the cloth image can be effectively utilized, and the detection accuracy and robustness of the cloth surface flaws and the recognition capability of unknown flaws are improved.

The invention discloses a texture perception state space modeling method for an image restoration task, and the method comprises the steps: 1, constructing a region selection mechanism based on texture complexity, and enabling the region selection mechanism to be used for distinguishing a flat region and a high-texture region in an image; 2, introducing a texture modulation mechanism, and performing explicit adjustment on a state transition matrix in the state space model; 3, enhancing the context modeling capability of the model through a multi-direction sensing module; and 4, by combining position embedding and a sequence modeling structure, the capability of the model in the aspects of image structure understanding and spatial information maintenance is improved. The method can effectively alleviate the problem of information loss when a traditional image restoration method processes texture details, improves the structure restoration capability of a complex region, gives consideration to the restoration quality and the calculation efficiency, is suitable for multiple image restoration scenes such as image super-resolution, image rain removal, low-light image enhancement and the like, and improves the image restoration efficiency. And the method has good engineering adaptability and actual deployment value.

The invention discloses a soil organic matter spectrum prediction method based on texture perception residual superposition, and the method comprises the steps: converting the classified texture into a dummy variable for model training, thereby directly inputting the texture category and spectrum information into a trained model during application, and obtaining the soil organic matter content. The method does not need to test the texture, does not weaken the advantages of the in-situ spectrum of the soil, and can meet the demand of simply and efficiently predicting the organic matter content of the soil. According to the method, a mapping relation between different textures and residual error predicted values is established by training a second model, so that the residual error model provided by the invention can accurately capture difference values between baseline predicted values under different textures and real soil organic carbon content, and therefore, compared with the prior art, systematic errors can be displayed and corrected, and the accuracy and the reliability of the method are improved. And the model prediction performance is more stable, and the organic carbon content of the soil can be accurately predicted in a larger range of soil with strong heterogeneity.

The invention provides a plastic toy surface defect detection method based on machine vision, and the method comprises the steps: firstly collecting and standardizing a plastic toy surface multi-parameter original image, and carrying out white balance correction and histogram equalization to improve the image quality; secondly, decomposing image frequency domain features by applying multi-scale wavelet transform, and enhancing defect area spatial positioning and texture sensing capabilities by combining cross guidance of frequency domain and spatial domain attention mechanisms; and inputting the fused features into a lightweight convolutional neural network to extract a high-discrimination feature vector, executing defect classification and position regression, and introducing an adaptive mechanism to dynamically optimize a decomposition scale and an attention strategy according to recognition confidence and detection history. The method is suitable for automatic surface quality detection under a complex background.

The invention discloses a high-resolution optical remote sensing image building change detection method, system and equipment based on texture frequency domain perception and a medium, and the method comprises the steps: obtaining a public building change detection data set LEVIR-CD which comprises double-time-phase images T1 and T2, cutting the data set into non-overlapping image pairs, and dividing the image pairs into a training set, a verification set and a test set according to a proportion; constructing a texture frequency domain sensing network, wherein the texture frequency domain sensing network comprises a twin MIT-B0 encoder, a texture sensing frequency domain attention module and a multi-layer perceptron decoder; training the texture frequency domain sensing network; performing result prediction on the test set by using the trained texture frequency domain sensing network to obtain a pixel-level prediction result; performing evaluation index calculation on each category and overall quality of the pixel-level prediction result, and evaluating network change detection performance; systems, devices, and media for implementing the method; according to the method, the precision and reliability of building change detection are effectively improved, and more reliable technical support is provided for application in related fields.

The invention relates to the field of artificial intelligence, and discloses an artificial intelligence assisted neodymium-iron-boron magnet defect detection system which comprises the following steps: acquiring a magnet image and preprocessing process parameters; extracting texture enhancement features through multi-scale texture perception; adaptively generating or adjusting a defect detection model based on the process parameters; and carrying out defect classification positioning, discrimination and optimization. The system comprises an image acquisition module, a process parameter acquisition module, an image preprocessing module, a multi-scale texture perception feature extraction module, an adaptive model generation and selection module, a defect detection module, a discrimination output module and a model optimization module. Defects and background textures can be effectively distinguished, the false detection rate is greatly reduced, the robustness, universality, detection precision and stability of the system are improved, automation and intelligence are achieved, and efficiency and quality consistency are improved.

The invention discloses a small-size visual tactile sensor based on a UV mark, and relates to the field of sensors. The visual tactile sensor solves the problem that the existing visual tactile sensor cannot realize high-precision force and texture perception on the same sensor at the same time, independently or in a time-sharing manner. A UV fluorescence labeling layer which is transparent under visible light and develops under ultraviolet light is arranged on the contact surface of the elastomer; the composite light source module comprises a UV light source unit and an RGB light source unit which can be independently controlled; the UV light source or the RGB light source is turned on through time-sharing switching, so that the image acquisition module can acquire mark point displacement images used for calculating contact force distribution or photometric stereo images used for reconstructing contact surface textures in a time-sharing manner. According to the invention, the problem that a traditional sensor cannot realize lossless switching of force and texture sensing functions on a single device is fundamentally solved by using the invisibility characteristic of the UV mark and a dual-light-source time-sharing working mode. The method is used for robot touch sensing.

The invention discloses a digital media image super-resolution reconstruction method based on deep learning, and the method comprises the following steps: S1, obtaining a to-be-reconstructed low-resolution digital media image, and carrying out the normalization processing of the low-resolution image; s2, constructing a multi-module collaborative deep learning network; s3, the deep learning network is trained by adopting a multi-loss function, and the multi-loss function comprises content loss, texture perception loss, adversarial loss and detail fidelity loss; and S4, carrying out reverse normalization processing on the high-resolution feature map output in the step S2. The noise suppression capability is high, noise in a low-resolution image can be suppressed in a targeted manner through a structure combining noise region positioning and attention gating, and noise amplification in a reconstruction process is avoided; details are completely reserved, and the multi-scale feature fusion module fully captures image structure information of different scales.

This invention relates to the field of shield tunnel segment inspection technology, and discloses a visual inspection-based shield tunnel segment assembly machine assembly quality inspection device and method, including: achieving autonomous perception and rapid recovery of calibration parameters when they fail due to vibration or temperature drift through time-efficiency monitoring and sliding window optimization technology; overcoming calibration bottlenecks through texture perception and active exploration trajectory planning technology; solving the calibration instability problem caused by the lack of natural textures by artificially creating multi-view geometric constraints using micro-motion trajectories; achieving intelligent decision-making and adaptive adjustment in the active exploration process through information gain-driven convergence judgment and global optimization technology; significantly enhancing parameter estimation confidence through global optimization integrating multi-source data; and constructing an unattended autonomous calibration management system through result encapsulation and closed-loop feedback technology, enabling persistent storage of calibration parameters, accumulation of prior knowledge, and real-time timeliness monitoring.

The invention discloses a camouflage target detection method based on edge semantic collaboration, and the method comprises the steps: an encoder which extracts multi-scale features from an original input image; the decoder comprises an adaptive edge texture perceptron AETP, a double-flow feature enhancer DSFA and a multi-feature modulation module MFMM; an adaptive edge texture perceptron AETP receives the multi-scale features, and extracts edge features by using multi-scale deformable convolution fusion and cross attention guidance; a double-flow feature enhancer DSFA performs feature enhancement on the multi-scale feature based on the edge feature to obtain a multi-scale enhanced feature; a multi-feature modulation module MFMM modulates the enhanced features of each scale based on the edge information to obtain a prediction image; the last level of prediction image is a camouflage target detection result. According to the method, a dynamic coupling edge-texture perception method is adopted, so that the capability of detecting a camouflage object in a challenging scene by the model is greatly improved.

The invention discloses a visual odometer method with mine weak texture perception enhancement and a related device. The method comprises the following steps: acquiring a mine frame stream image; evaluating the brightness of the mine frame stream images, and screening out mine frame stream images which need or do not need image restoration processing; processing the mine frame stream image needing to be subjected to image restoration processing by adopting a multi-stage image illumination restoration method; adopting an ORB feature point extraction framework, performing texture measurement on the mine frame stream restored image and the mine frame stream image which does not need to be subjected to image restoration processing based on a Tamura theory, and obtaining feature point distribution density; improving the quadtree homogenization based on the sensing condition of the mine frame stream image texture; performing pre-integration and initialization on the IMU data by using all the IMU data in a time period from a previous frame to a current frame in the mine frame stream image; carrying out tight coupling on the matching motion tracking information of the mine frame stream image and the IMU motion information, and calculating the relative pose of the equipment main body carrying the speedometer.

The invention relates to a small target detection method and system based on adaptive texture perception and frequency domain-cross-layer collaborative optimization, and the method comprises the steps: providing a cross-scale texture guide module, independently capturing the spatial distribution characteristics of heterogeneous features through a multi-scale texture extraction unit, and constructing scene-level texture prior through an additive fusion mechanism; a frequency domain detail enhancement module is provided, features are mapped to a complex frequency spectrum space through real number fast Fourier transform, dynamic reweighting is carried out on medium-high frequency components by using an adaptive weight vector, and target contour information is explicitly enhanced in combination with inverse transform and a residual connection mechanism; a cross-layer feature stabilization module is designed, context clues of different granularities are captured through lightweight multi-scale receptive field extension, and a dynamic channel gating modulation mechanism is introduced to perform active intervention on a feature evolution path. Compared with the prior art, the method has the advantages of characteristic enhancement, stable positioning, balanced detection precision and operation efficiency and the like.

The present disclosure provides an object shape and texture perception method for underwater robots and a corresponding device. The underwater tactile sensor comprises: a contact module for contacting the surface of an underwater object to deform, the deformation causing displacement of a multi-color marker point field on the upper surface of the contact module; a binocular camera module for capturing the displacement of the multi-color marker point field to obtain a tactile image, wherein the tactile image comprises a left-eye tactile image and a right-eye tactile image; a waterproof module for realizing the waterproof function of the underwater tactile sensor; wherein the multi-color marker point field comprises: a plurality of marker point groups arranged in sequence, each marker point group comprising j marker points of different colors, the spatial order of the j color marker points in each marker point group being fixed, and j being an integer greater than 1.

The present invention relates to the technical field of data protection and medical image processing, and in particular to a method for protecting an image segmentation dataset based on contour and texture perception perturbations, comprising: preprocessing to obtain a standard image; performing multi-scale convolution and channel attention mechanism processing to complete encoding, and performing cross-layer feature aggregation to complete decoding; cropping the decoding result based on a segmentation mask image to obtain a contour perturbation; obtaining a texture feature map of the standard image, cropping the initial perturbation based on the texture feature map to obtain a texture perturbation; optimizing the loss functions of the contour perturbation and the texture perturbation; obtaining an optimal contour perturbation and an optimal texture perturbation based on an optimized contour perturbation generator and a texture generator; and fusing the standard image, the optimal contour perturbation, and the optimal texture perturbation to obtain a protected medical image. The present invention can protect a medical image segmentation dataset.

The invention discloses a symbol music generation method based on texture perception and adaptive representation alignment. The method is characterized by comprising the steps of conditional decoupling and extraction of multi-scale music element features, conditional coding, texture perception FLUX music model construction, adaptive representation alignment, MIDI file generation and the like. Compared with the prior art, the method has the advantages that the structural advantage and multi-scale information of the symbol music are fully utilized, the texture consistency, chord accuracy and style controllability of the generated music are remarkably improved, the training and reasoning cost is reduced, and the generalization ability and practicability of the model are further improved. Through the three-in-one design of'conditional decoupling, texture perception diffusion and self-adaptive expression alignment ', the problems of semantic loss, inconsistent texture, uncontrollable chord and the like caused by neglecting of internal association of music in a traditional method are effectively solved, and the method is efficient, reliable and easy to implement and has good application prospects in the fields of automatic composition, interactive music creation and the like.

The invention provides an intelligent structure design generation method and system, and is suitable for a generative design task in the field of complex structure design, the method introduces a semantic interpretation mechanism based on a sketch graph structure, combines multi-scale texture perception and a graph neural network embedding strategy, and can improve the structure design efficiency under the premise of not depending on a traditional topological optimization solution framework. And efficient generation and diversified control of the structural form are realized. According to the method, through gesture sketch input, fuzzy structure intention map construction, wavelet scale regulation and control and structure solution set evolution screening strategies oriented to man-machine collaboration, the controllability of understanding is enhanced, the diversity of understanding sets is remarkably improved, and therefore the requirements for multi-target comprehensive optimization of aesthetics, technology, mechanics and the like in actual design are met.

The application discloses a cloth surface defect detection method and device based on texture perception and anomaly detection, and comprises the following steps: acquiring a detected cloth surface image; inputting the detected cloth surface image into a deep learning network model; extracting a multi-scale feature map through the backbone network; processing the feature map through a texture perception feature extraction module to fuse texture information across channels and spaces; integrating an anomaly detection branch through the neck network and outputting feature maps of different scales; performing frequency domain enhancement and spatial feature extraction operations on the features through an adaptive frequency domain convolution module and fusing the features; and outputting a detection result through the YoloHead detection head to determine whether the cloth has defects. The application can effectively utilize texture feature information in the cloth image, improve the detection accuracy, robustness and recognition ability for unknown defects of the cloth surface defects.

The invention discloses a texture perception 3D Gaussian expansion method for sparse view reconstruction. According to the method, a texture perception framework TA-GS for performing novel view synthesis by using a sparse input image is provided; a proposed texture-based Gaussian migration strategy utilizes texture strength to guide Gaussian primitives, so that fine-grained texture details are better represented under a sparse input view; the proposed depth alignment texture effectively captures local depth change and texture information, enhances geometric constraints and improves depth precision; in order to further enhance texture optimization, Phantom View regularization is introduced, a training view is enriched through interpolation, and texture regularization is applied, so that high-fidelity reconstruction of texture details and geometric structures is realized. The method is superior to the existing method in various indoor, outdoor and object-centered scenes, and has different image resolutions and input view counts.

This paper proposes a texture-aware image-based fine-grained smoke detection method. The method comprises: a feature extraction module for acquiring low-level, mid-level, and high-level local features; a self-attention expression module for deriving global smoke attention features from high-level local features; a global convolutional texture perception module for acquiring smoke object-level features and internal detail features from mid-level local features; and a feature decoding module for fusing all of these features and mapping them into a smoke probability map as the result of fine-grained smoke detection. This method can accurately capture smoke locations in images and reflect internal details of smoke puffs in an end-to-end manner, providing clues for subsequent tasks in early fire detection, such as analyzing smoke concentration and puff motion trends. It has promising application prospects in the field of fire safety.

The application discloses a face image reconstruction method, system and device based on adaptive texture and frequency domain perception, and a medium. A self-attention calculation is performed on coarse features by an adaptive texture perception module, then the attention matrix is used to search for a part with strong correlation in fine features, and then fine self-attention calculation is performed. A multi-dimensional perception module is used to enhance the expression ability of features in cross-space and cross-channel. A multi-frequency fusion module based on wavelet transform is used to fuse the middle and low frequency features from the encoder and the high frequency features from the decoder. The adaptive texture perception module enables the model to more finely restore complex regions in the image, the multi-dimensional perception module enhances important channel information in the features, and the multi-frequency fusion module eliminates high frequency noise in the original features, and fuses the effective middle and low frequency features with the restored high frequency details, thereby improving the restoration ability and generalization ability of the model for face images.

A dynamic alignment and edge feature calibration method for small and medium-sized target detection in a remote sensing image comprises the following steps: S100, in a feature extraction stage, extracting multi-scale texture information by adopting multi-scale texture sensing (MSTP), capturing a relationship among pixels, and simultaneously amplifying homogeneous details of an object to represent important textures; s200, in the feature processing stage, useful multi-scale features are reserved by selecting a BS-FPN composed of boundary enhancement DBS and C2f, and redundant features are further filtered; and S300, inputting the processed features into a task perception detection head TAD-Head for processing, and comprehensively integrating supervision information from a classification task and a positioning task through a cross-task perception mechanism to realize consistency detection of classification and positioning. According to the method, the problem of weak and small targets in the remote sensing image is solved by exploring high-frequency detail information characteristics of an object and enhancing the cross-task perception interaction capability.

The invention discloses a wafer defect detection method fusing feature-level and texture-level abnormal synthesis. The method comprises the following steps: obtaining self-adaptive normal features of a normal wafer sample at a normal branch through a frozen feature extractor and a trainable feature adapter; synthesizing global abnormal features by using Gaussian noise in the feature-level abnormal synthesis branch; synthesizing noise maps with different intensities through texture perception defect synthesis in the texture-level anomaly synthesis branch, synthesizing a local anomaly image through texture superposition, and obtaining local anomaly features through a feature extractor and a feature adapter; the three features of the three branches are jointly input into a neural network feature discriminator for end-to-end training; in the reasoning stage, normal branches are used for processing a test image to obtain adaptive features, the adaptive features are input into a neural network feature discriminator to obtain an abnormal score, whether the current test image has defects or not is judged, and abnormal positioning is conducted on the defects. The method provided by the invention can effectively improve the detection capability of weak defects and meet the real-time requirement of industrial production.

The invention discloses a dialogue result determination method and device, equipment, a medium and a product. The method comprises the steps that image perception dialogue content is acquired; determining perception attributes of the image perception dialogue content in multiple perception domains through the trained unified perception understanding model, wherein the multiple perception domains comprise an aesthetics perception domain, a quality perception domain and a structure texture perception domain; and through the unified perception understanding model, based on the perception attributes, an evaluation result of the image perception dialogue content is generated, and the evaluation result comprises a classification evaluation task result and / or a question and answer evaluation task result. The trained unified perception understanding model can perform consistent reasoning in three perception domains of aesthetics, quality, structure and texture, can support a continuous scoring task and a discrete question and answer task at the same time, and keeps stability, controllability and cross-task consistency in the reasoning process. It is ensured that perception attributes can accurately reflect the essence of visual features, and clear semantic support can be provided for subsequent evaluation result generation.

This invention discloses an image watermarking method and system based on a texture-aware adaptive embedding diffusion model, relating to the field of artificial intelligence technology. It introduces a multi-scale watermark embedding mechanism in the decoding stage, achieving multi-scale watermark embedding from coarse to fine by injecting residual signals into latent variables at different levels. To achieve adaptive texture scheduling, a texture intensity-aware mechanism is proposed, utilizing the intermediate feature layer of the decoder to obtain the feature space texture using a hybrid metric of channel variance and spatial gradient, resulting in efficient computation and close resemblance to the generated semantics. A texture intensity pyramid is constructed based on the feature space texture map, adaptively weakening in smooth regions and enhancing in complex texture regions to ensure the watermark embedding is covert. To improve extractability and stability, the watermarked image processed by the distortion operator is input into the watermark extractor for dual attention extraction to obtain bit-level watermark messages, ensuring the robustness of the watermark under various attacks.

The present application relates to the technical field of concrete structure detection vision, in particular to a concrete structure surface crack automatic identification method based on computer vision, which comprises the following steps: obtaining a concrete structure surface image to be analyzed, separating a background texture layer, a suspected crack feature layer and a noise interference layer through multi-scale texture perception decomposition, constructing an initial crack feature field containing pixel-level position and direction information, inputting a space-time continuous crack reasoning calculation network, coupling neighborhood feature propagation and global path optimization to infer a complete crack topology skeleton, generating crack vector lines through pixel-level width regression and edge positioning, completing credibility verification in combination with background texture statistical characteristics and noise spectrum features, fusing collected visual angle information to inverse reconstruct a crack three-dimensional morphology, and calculating crack length, width, area and volume parameters. The present method can accurately separate image features and completely infer crack topology, thereby improving crack identification authenticity and morphology integrity.

The application provides a content security-based image recognition method and device, equipment and a storage medium, and relates to the technical field of computer vision, and the method comprises the following steps: acquiring an image to be recognized; inputting the image to be recognized into a multi-scale texture perception model to output an image category recognition result for representing whether the image is fake; wherein the multi-scale texture perception model is obtained based on image sample data and corresponding image category labels, and the multi-scale texture perception model is used for performing category recognition on the image to be recognized based on the correlation between any two channels of multi-scale texture features of the image to be recognized. The application can combine the multi-scale texture features and the subtle differences between different channels of the features to improve the image category recognition accuracy, and improve the robustness and generalization.

The invention discloses an RGB-T semantic segmentation method and system based on multi-attention guidance and hierarchical fusion, and relates to the technical field of image processing. The system is composed of a double-flow encoder, a discriminative local texture perception unit, a semantic-driven cross-modal fusion unit, a semantic enhancement unit and a multi-scale layered refinement decoder, and efficient fusion and analysis of multi-modal features in a complex traffic scene are achieved. According to the discriminative local texture perception method, saliency features are learned through multi-attention guidance and a self-adaptive gating mechanism, accurate modeling of shallow texture information is focused, and the distinguishing ability of a region of interest and a target edge is improved; according to the semantic-driven cross-modal feature fusion method, efficient aggregation of global contexts is realized through high-level semantic guidance and cross-modal feature interaction, and feature complementarity is enhanced, so that the semantic-driven cross-modal feature fusion method has significant advantages in analysis of small targets, long-distance targets and boundary regions. The decoder adopts a progressive fusion mode, an additional edge detection module does not need to be added, and the overall segmentation precision is improved.