1603 results about "Spatial domain" patented technology

The invention relates to the technical field of computer vision detection, in particular to an unmanned aerial vehicle target detection method based on frequency-space joint attention and dynamic fusion, and the method comprises the steps: obtaining an unmanned aerial vehicle image data set, carrying out the preprocessing, and dividing a training set and a test set; constructing a target detection model, inputting the training set into the target detection model to extract image features, sequentially performing frequency domain detail enhancement, spatial domain salient region extraction and multi-scale feature adaptive fusion based on the image features, and establishing a feature sequence; screening the feature sequence to obtain an initial target query, and finishing target classification and positioning on the initial target query through a decoder; training a target detection model by using the training set, and inputting the test set into the trained target detection model to generate a detection result; on the premise that the real-time reasoning advantage of RT-DETR is kept as much as possible, the problems that in an unmanned aerial vehicle scene, a target is prone to missing detection, the scale change is large, the background is complex, and the target is fuzzy are effectively solved, and the detection precision is improved.

The invention discloses a semantic segmentation method for a low-resolution road scene, and aims to solve the problems of difficulty in small target recognition, fuzzy details, texture information loss and the like existing in a low-resolution image in the conventional semantic segmentation technology. The method comprises the following steps: (1) collecting a low-resolution road scene image and a corresponding semantic tag; (2) constructing a semantic segmentation model consisting of an edge guidance module (BGM), a double-domain feature decomposer (DDFD), a domain alignment attention fusion module (DAAFM) and a double-layer attention context aggregation module (HACAM); (3) designing a joint loss function to carry out multi-scale supervision on semantic regions, edges and middle features; (4) carrying out model training by utilizing the road scene image; and (5) outputting a semantic segmentation result map and an edge prediction map. The boundary perception capability is enhanced by introducing learnable pixel difference convolution, the extraction precision of a small target and a global structure is improved by combining frequency domain and spatial domain feature alignment, and context semantic relationship expression is optimized by fusing a channel and a spatial attention mechanism. The method effectively improves the semantic segmentation precision and boundary restoration capability of the model in a low-resolution complex road environment, and is suitable for intelligent analysis tasks of road images in scenes of automatic driving, intelligent traffic, severe weather and the like.

The invention relates to an underwater image enhancement method based on wavelet Mama, which aims at the problems of color shift, low contrast ratio and fuzzy details of an underwater image, extracts shallow layer features of an underwater low-quality image, inputs the shallow layer features into a multi-scale coding network, and performs joint enhancement on low-frequency color information and high-frequency detail features by using a wavelet Mama unit. Global semantic features are obtained by combining down-sampling layer-by-layer compression, and global modeling of color offset correction and contrast enhancement is completed; the spatial resolution is recovered through up-sampling, and reconstruction and enhancement of texture details and color information are realized in combination with jump connection and a wavelet Mama unit; and finally, the features are mapped to an image domain and fused with input image residual errors, and an enhanced underwater image with natural color, clear texture and balanced contrast is generated. According to the method, frequency domain-space domain joint feature modeling is realized through the wavelet Mama unit, and the color authenticity, the structural definition and the detail perceptibility of the underwater image are remarkably improved.

The invention provides a modified metal surface defect detection method and device and a medium, and the method comprises the steps: obtaining a multi-angle reflection image sequence of a modified metal surface under the irradiation of a multi-spectral light source, and generating a defect sensitive parameter set based on a preset modified metal material characteristic database and in combination with the spectral reflectivity distribution information of the multi-angle reflection image sequence; performing cooperative feature enhancement on the multi-angle reflection image sequence and the defect sensitive parameter set, and enhancing the feature contrast of a defect area and a normal area through weight distribution to obtain an enhanced defect feature set; joint anomaly detection of a spatial domain and a spectral domain is carried out on the enhanced defect feature set, a potential defect region of the modified metal surface is obtained through identification, and a defect region feature descriptor is generated; and performing defect morphological quantitative analysis according to the defect region feature descriptors, and determining the type, position and severity level of the modified metal surface defect. According to the invention, the comprehensiveness and reliability of a defect detection result can be improved.

The invention discloses a shock wave overpressure field global measurement method based on multi-view image fusion, belongs to the technical field of explosive shock wave measurement, and is suitable for weapon equipment power evaluation and blasting safety analysis. The method comprises the following steps of: synchronously acquiring a time sequence image of the whole explosion process through a distributed multi-view high-speed imaging system, preprocessing the image by adopting pixel-by-pixel comparison, square operation enhancement and normalization processing, and positioning a shock wave edge contour; the blasting center coordinate is positioned through binocular parallax, the shock wave initial radius is determined by combining spatial domain analysis, and the key feature points of the front and rear edges of the wavefront are detected by using a dynamic search window and a radial gradient field. Based on multi-view constraints, a three-dimensional point cloud is generated through direct linear triangulation, and a three-dimensional wave front form is reconstructed in combination with least square spherical fitting. And finally, constructing a wavefront radius-time evolution model, and deducing a quantitative relationship between the instantaneous propagation velocity and the peak overpressure in combination with a Ranki ne-Huton iot relationship, thereby realizing the global high-precision calculation of the overpressure field.

The invention discloses a cross-modal target detection method based on learnable Fourier transform, and mainly solves the problem of insufficient fusion of a visible light image and an infrared image in a complex scene due to inter-domain difference in the prior art. According to the implementation scheme, the method comprises the steps that bimodal features are extracted through a double-flow CSPDarknet53 network; a target position guiding module is utilized to enhance target area representation and suppress background interference; the features are converted to a frequency domain, and amplitude texture information of the visible light image and phase contour information of the infrared image are adaptively enhanced through a learnable frequency domain feature enhancement module; suppressing noise through global filtering and then inversely transforming back to a spatial domain; and finally, outputting a target detection result of the multi-modal image by the detection head. According to the method, frequency domain physical characteristics are fully utilized, full complementation and adaptive fusion of cross-modal features are realized, the detection precision and robustness of vehicles, pedestrians and other targets under low-illumination and complex backgrounds are remarkably improved, meanwhile, high calculation efficiency is kept, and the method can be applied to the fields of automatic driving, intelligent monitoring and the like.

The invention provides an end-to-end tiny target detection method, and aims to solve the problems of missing detection and false detection of tiny targets caused by interference of sparse features, halo, noise and the like. According to the method, a TINYDETR model is constructed, and the TINYDETR model is composed of an HGNetv2 backbone network, an LGFSI module, an SO-CSFF module and a decoder with an auxiliary prediction head. Wherein the LGFSI module realizes global-local information interaction through joint modeling of a frequency domain and a spatial domain, and background interference is effectively suppressed; the SO-CSFF module enhances the fusion of shallow details and deep semantics through a bidirectional feature flow mechanism, and enhances the feature expression of a tiny target. After the model is trained and optimized, high-precision detection of a tiny target can be realized.

The invention discloses an overlapped cervical cytoplasm region segmentation method based on deep learning and a conditional diffusion model, and relates to the technical field of artificial intelligence analysis of medical images. According to the method, accurate segmentation of the overlapped cytoplasm region in the cervical cell image is realized through a morphological prior guided conditional diffusion process. The method comprises the following steps: constructing a multi-scale cervical cytoplasm mask pair image; designing a cytoplasm specific data enhancement and preprocessing process; building a multi-branch cervical cell morphology perception condition diffusion network; using a self-adaptive multi-scale combination loss function to optimize training; and a hierarchical classifier is adopted to freely guide sampling for reasoning. According to the method, the frequency domain and space domain features are fused, a cellular morphology and statistics priori knowledge base is established, and a strategy of generating complete cytoplasm by adopting non-overlapped parts is adopted, so that the problem that the traditional method is difficult to segment in complex backgrounds and overlapped regions is successfully solved, and reliable technical support is provided for early screening of cervical cancer.

The invention discloses a flexible stone texture defect identification method based on a multi-scale convolutional neural network, and the method comprises the following steps: collecting images of the surface of a flexible stone, and carrying out the batch classification; selecting a first image of each production batch as a batch first sample, and generating batch configuration parameters; performing texture feature extraction by using the batch configuration parameters and the to-be-detected image to generate a texture map; respectively inputting the to-be-detected image into a spatial domain convolution branch and a frequency domain convolution branch of the space-frequency neural network model, and extracting spatial domain features and frequency domain features according to the scale control information; the spatial domain features and the frequency domain features are fused; and generating candidate areas based on the fused features, performing positioning and confidence evaluation, removing the candidate areas with confidence smaller than a preset threshold, and generating a flexible stone texture defect detection result. According to the method, the surface defects of the flexible stone can be accurately detected, the detection efficiency and robustness are improved, and the manual detection cost is reduced.

The invention discloses a remote sensing image segmentation method fusing frequency modulation and spatial perception, and the method comprises the steps: obtaining and preprocessing an original remote sensing image, and generating a standardized input image; the image is input into a multi-scale frequency domain enhanced feature extraction network, features are extracted step by step according to a plurality of feature levels, each level realizes frequency adaptive semantic enhancement through frequency domain modulation transformation and spatial feature fusion, and deep feature expression is enhanced through feedforward neural network modeling and residual connection output and cross-level residual fusion introduction; the final multi-scale features are decoded through a decoding module, the spatial resolution is recovered, and a pixel-level segmentation result is generated; and constructing a composite loss function containing classification errors, boundary perception and frequency consistency items, and carrying out optimization training on the network. According to the method, semantic complementarity of a remote sensing image in a frequency domain and a space domain is fully mined, so that segmentation precision and robustness of a ground object target in a complex scene are improved, and the method has good generalization ability and engineering practicability.

The invention discloses a radar approaching rainfall prediction method based on frequency domain perception and conditional diffusion, and belongs to the technical field of image data processing, and the method comprises the steps: obtaining a radar echo data set, and pre-training a variational auto-encoder MVAE; the method comprises the following steps: constructing a convolution enhanced frequency domain Transform; constructing an improved denoising network based on a multi-layer convolution enhanced frequency domain Transform, generating an improved conditional diffusion model based on MVAE, and training to obtain an approaching rainfall prediction model; the method is used for approaching rainfall prediction. Through frequency domain-spatial domain collaborative modeling and efficient conditional diffusion architecture design, the method not only overcomes the core defects of prediction fuzziness and the like caused by unsmooth local and global feature fusion and signal-noise confusion in the prior art, but also enhances the adaptation capability to a complex meteorological scene, and improves the prediction accuracy. Therefore, high-frequency details and edge features of the convection system can be more accurately captured, the prediction precision of a weak echo region is remarkably improved, and the accuracy of short and temporary rainfall prediction is improved.

The invention belongs to the field of space target detection, and relates to a weak space small target detection method based on airspace guidance, which comprises the following steps: inputting a to-be-detected space target image sequence into a pre-established and trained weak space small target time sequence evolution feature sensing network based on airspace guidance to obtain a target prediction frame, small target detection in a dark space is realized; the dark space small target time sequence evolution feature sensing network extracts initial time-space features of an image sequence through a lightweight three-dimensional convolutional network, enhances target response and inhibits star clutters, models target time sequence evolution features and enhances target space region features by constructing a double-branch structure, and finally, the target time sequence evolution feature sensing network is constructed. A gating-based double attention feature fusion module is adopted to selectively enhance and fuse features output by the branch structure, and the joint expression ability of position and motion information is improved.

The invention discloses a power equipment defect intelligent identification method, system and device and a medium, and the method comprises the steps: collecting an original image of power equipment, and screening the original image of the power equipment to obtain a channel image; carrying out enhancement processing on the channel image and then calculating a gray scale difference value to obtain a gray scale image; converting the gray level image into a frequency spectrum image by adopting fast Fourier transform, and constructing a Gaussian filtering function to carry out convolution and inverse transformation on the frequency spectrum image to obtain a spatial domain image; and performing adaptive threshold segmentation on the spatial domain image, dividing the image into a defect area and a non-defect area, obtaining a segmented image, and performing morphological processing on the segmented image to obtain an electrical equipment defect identification result. According to the method, the problem of aliasing in traditional spatial domain processing is solved, the defect area is accurately extracted, short-time interference and real defects can be effectively distinguished, and the segmentation accuracy is improved.

The invention discloses an optical surface defect data detection method based on deep learning, and relates to the technical field of optical defect detection, and the method comprises the following steps: constructing an optical scattering physical model, inputting a collected optical surface image into the optical scattering physical model for multi-modal data synthesis, and generating multi-modal image data; constructing a deep learning feature extraction network, inputting multi-modal image data, and performing multi-scale feature fusion and enhancement through a bidirectional attention feedback mechanism to generate a deep feature map; performing spatial domain analysis on the depth feature map by using a deep learning region generation method, positioning coordinates of potential defect regions, and generating a candidate defect region coordinate set; through multi-modal data synthesis driven by an optical scattering physical model, the limitation of a single imaging mode is broken through, the scattering characteristics of defects under multi-physics field coupling are dynamically analyzed, the recognizable degree of weak defects in a complex scattering environment is enhanced, and the problem of defect missing detection is solved.

The invention provides a tunnel surrounding rock dynamic grading and blasting parameter optimization method and system, and relates to the technical field of data processing.The method comprises the steps that geological parameters of a current tunnel face are collected in real time through a multi-source sensing system deployed on the tunnel face; based on the acquired geological parameters, identifying a plurality of characteristic sampling points with geological representativeness in a tunnel face spatial domain; four non-coplanar feature sampling points are selected to construct an initial tetrahedron, the point, farthest from the surface of the current convex hull, in the remaining points is included in sequence through an iterative extension method, the surface of the convex hull is recalculated till all the feature sampling points are enveloped, and a convex polyhedron evaluation area boundary is formed. According to the invention, data full-process connection and function collaboration can be realized.

The invention provides an unmanned aerial vehicle full-time perception image reconstruction method based on multi-mode cooperative reinforcement learning and degeneration decoupling. A frequency perception feature modulation model, a dual-mode dual-domain transformation module and a dynamic bidirectional guide mechanism are included. According to the system, firstly, feature information of different frequency bands is adaptively separated and modulated through a frequency sensing feature modulation model, and decoupling and compensation of composite unknown degradation are achieved; realizing cross-domain interaction and information fusion of visible light and infrared characteristics in a spatial domain and a channel domain by using a bimodal dual-domain transformation module; and finally, realizing collaborative enhancement of cross-modal degradation perception through a bidirectional dynamic guide mechanism, and generating an unmanned aerial vehicle visible light reconstruction image and an infrared super-resolution image with higher structural consistency and texture fidelity. According to the method, deep fusion and degeneration decoupling of multi-modal information can be realized in a complex degeneration environment, and the imaging quality and the environmental adaptability of an unmanned aerial vehicle full-time sensing system are remarkably improved.

The invention provides a dense overlapping target detection method based on a wavelet enhancement sparse hybrid expert model. The method comprises the following steps: firstly, extracting multi-layer features through a backbone network to capture multi-scale spatial representation; secondly, discrete wavelet transform is introduced to each level of features, spatial features are decomposed into a frequency domain, collaborative modeling of frequency domain and spatial domain features is realized, the reservation capability of detail and texture information is improved, a lightweight dynamic hypergraph aggregation module is introduced into the deepest layer of features, a hyperedge structure is adaptively learned, and the feature fusion is realized; modeling a high-order incidence relation in a local area in an explicit manner; and thirdly, in the decoding process, candidate queries are screened and reweighted through an IoU perception query selection mechanism, and a dynamic routing mechanism of sparse hybrid experts is introduced, so that query self-adaptive specialized representation learning is realized, and the target detection precision and reliability in a complex scene are effectively improved.

The invention discloses a remote sensing image multi-scale segmentation method based on frequency spectrum information processing and Mama spatial modeling, and the method comprises the steps: carrying out the preprocessing of a remote sensing image, and obtaining an input image; inputting the input image into the trained remote sensing image segmentation model; the remote sensing image segmentation model comprises an initial convolutional layer, a spectral domain information processing unit branch, a Mama layer branch and a segmentation head; performing feature extraction on the input image through the initial convolutional layer to obtain initial image features; combining a frequency spectrum domain information processing unit branch and a Mama layer branch, and performing feature extraction on the initial image features to obtain fusion features; and performing up-sampling decoding and pixel-level classification on the fusion features through the segmentation head, and outputting a multi-scale segmentation result corresponding to the remote sensing image. According to the method, the spectral domain and the spatial domain are combined for feature extraction, and the common problems of fuzzy details, unclear boundaries, insufficient multi-scale target expression and the like in remote sensing image segmentation are solved.

Some embodiments of a method may include: obtaining a reference 3D Gaussian frame, a camera position C, and a time t; extracting a multi-scale feature for each 3D Gaussian of one or more 3D Gaussians using a neural network block, wherein the multi-scale feature represents multi-scale spatial information about a dynamic object or scene; predicting 3D motion based on the multi-scale features and the time t; predicting a 3D Gaussian frame for time t by manipulating the one or more 3D Gaussians in a spatial domain based on the predicted 3D motion; and outputting the 3D Gaussian frame for time t.

The invention relates to the technical field of deep learning and computer vision, and discloses a histogram interactive attention-based pavement crack segmentation network processing method and system, so as to enhance the edge detail fidelity and improve the crack segmentation precision. The method comprises the steps of image preprocessing, up-sampling, down-sampling, feature fusion and image reconstruction processing. Wherein global feature modeling in the intensity sub-boxes and among the sub-boxes is realized by constructing a histogram interactive attention module (HIA); a double-branch detail enhancement feedforward module (DDEF) is introduced to enhance spatial detail and high-frequency edge information expression; meanwhile, a Fourier jump enhancement module (FFSM) is adopted to jointly refine jump connection features in a spatial domain and a frequency domain. Through the synergistic effect of the modules, the network can realize continuous recovery and structural consistency modeling of a crack boundary in a complex pavement environment, so that the accuracy and the stability of a segmentation result are remarkably improved.

The invention belongs to the field of CT (Computed Tomography) tomography reconstruction technology and artificial intelligence, and discloses a finite angle CT reconstruction method based on combination of a three-dimensional conditional diffusion model and synchronous iteration. The CT is an imaging technology which utilizes X-rays to irradiate a target from different angles and acquire projection, and obtains an internal three-dimensional structure through reconstruction. Different from traditional CT depending on nearly full-angle scanning, the method only collects limited-angle projection, and achieves fault reconstruction under the limited-angle condition through a three-dimensional condition diffusion model of space domain-frequency domain two-way decoding and by means of structural generality priori of a workpiece. Meanwhile, projection and fault data consistency correction is carried out in combination with a synchronous iteration reconstruction technology, the advantages of an iteration method in the aspect of physical mechanism characterization are exerted, interpretable physical constraints are provided for a deep learning network, and therefore the reliability and precision of a reconstruction result are improved.

The invention provides a spatial domain identification method based on data interpolation and cell type deconvolution, and belongs to the technical field of bioinformatics. In order to solve the problems that gap information between adjacent points cannot be utilized in low-resolution spatial transcriptome data and prior information of cell types in a tissue space structure level cannot be fully integrated in a traditional method, the method comprises the following steps: acquiring a spatial transcriptome data set and a single-cell RNA sequencing data set, and performing data preprocessing on the acquired data sets; and carrying out data interpolation on the preprocessed spatial transcriptome data, and carrying out cell type deconvolution in combination with single-cell RNA sequencing data. And constructing a deep learning model based on the graph convolutional network. And training a deep learning model according to gene expression information, spatial position information and cell type information of the spatial transcriptome data after cell type deconvolution by using a self-supervised contrast learning strategy. And performing spatial domain identification on the to-be-detected data based on the trained model.

The invention discloses a camouflage target detection method and system based on a double-domain fusion enhanced network, and relates to the technical field of target detection. Through the nonlinear double-domain fusion module, in combination with nonlinear mapping of a spatial domain and a frequency domain, key difference characteristics of a frequency domain amplitude spectrum and a phase spectrum are captured, the problem that the detection performance is reduced in a scene of low contrast and the like depending on an RGB spatial domain is solved, and the target discrimination degree is improved; based on a lightweight scale perception modulation converter and a double-feature fusion module, multi-scale features are extracted, aligned and fused, a semantic relation is integrated by means of cross attention, and the problems of detail loss and boundary fuzziness caused by scale diversity are solved; the context feature enhancement module integrates cross attention and edge auxiliary injection, accumulates multi-layer feature integration, gives consideration to a global boundary and a local structure, effectively reduces false detection, missing detection and edge roughness, and further enhances robustness through multi-layer auxiliary supervision.

The invention relates to the technical field of medical image processing, in particular to an automatic blood vessel extraction method and system based on a CT image, and the method comprises the steps: 1, constructing a blood vessel local coordinate system, and carrying out the double-domain separation; 2, dynamic double-domain fusion, wherein contrast self-adaptive weighted fusion is carried out on the spatial domain enhanced image and the fundamental frequency blood vessel image; 3, direction constraint morphological reconstruction: constructing a structural element with a long axis parallel to the direction of the blood vessel according to the main direction vector v of the blood vessel; sequentially executing directional opening operation and directional closing operation along the direction of the main direction vector v of the blood vessel; and 4, anatomically-driven blood vessel repair and correction: tracking contours of adjacent slices along the direction of the main direction vector v of the blood vessel and fitting a repair path on the basis of a generated calcified region mask Mcal marked region, and correcting a topological structure at a bifurcation point according to a branching angle and hemodynamic constraint. The vascular structure can be accurately and stably extracted from the CT image by comprehensively utilizing restoration technologies such as spatial domain enhancement and frequency domain separation.

The invention relates to the technical field of satellite internet, and discloses a low-orbit satellite phased array multi-beam interference modeling and suppression method and system, and the method comprises the steps: selecting a Kaiser window as a core filtering method, and achieving the optimization of beam characteristics through the dynamic adjustment of a shape parameter beta; generating an initial beam directional diagram based on a digital phase matching method, and multiplying the Kaiser window function coefficient by the excitation weight of the 64-array-element linear array element by element to realize spatial domain weighted filtering; the method comprises the following steps: constructing a training data set containing multi-scene interference characteristics, calculating a corresponding covariance matrix and an accurate inverse matrix thereof to form a sample pair, designing a deep neural network architecture, inputting a flattened covariance matrix vector, and learning a complex nonlinear mapping relation from the covariance matrix to the inverse matrix through a multi-layer full-connection structure; a mean square error is used as a loss function to constrain network output precision, and a multi-beam interference system model is constructed; according to the invention, stable and efficient communication of the low-orbit satellite system in a complex electromagnetic environment and under rapid channel change is ensured.

The invention relates to the field of nondestructive testing and automatic sorting of agricultural products, and discloses an X-ray-based walnut internal defect feature optimization detection method and device, and the method comprises the steps: collecting an X-ray image of a moving walnut, extracting a region of interest (ROI) through preprocessing, extracting and fusing spatial domain and frequency domain texture features to form a multi-dimensional feature set, and obtaining a feature set; an optimal feature combination is screened out through dimensionality reduction; and finally, the types of the internal defects of the walnuts are identified by a pre-trained classifier, and a result is output. The device comprises a feeding mechanism, a conveying mechanism, an X-ray detection mechanism, a sorting execution mechanism and a processing and control system electrically connected with all the mechanisms. The problems of single identification category and insufficient model stability and precision are solved, and high-throughput and automatic lossless sorting of walnuts is realized.

The invention discloses a multi-channel dynamic hypergraph sentiment analysis method and a multi-channel dynamic hypergraph sentiment analysis network fusing time sequence consistency, belongs to the field of artificial intelligence and multi-modal sentiment calculation, and aims to solve the problems existing in the existing sentiment analysis technology. The method comprises the following steps: S1, a multi-channel feature extraction step: extracting multi-channel features of a text mode and an audio mode through a heterogeneous pre-training model; s2, a local time sequence context fusion step based on a video number: fusing short-term emotional fluctuation based on a local context mechanism of the video number, and capturing long-range dependence across time dimensions through Transform; s3, a single-modal-multi-modal hypergraph collaborative prediction step: dynamically constructing a single-modal hypergraph and a multi-modal hypergraph in a training batch, and modeling a high-order relationship by adopting spectral domain-spatial domain hybrid convolution; and S4, a multi-level multi-branch supervision step: outputting a final emotion prediction result through joint optimization of an early MLP branch and a late hypergraph branch.

The invention relates to the technical field of image acquisition and testing, and discloses an image acquisition and testing method, device and equipment and a storage medium, and the method comprises the steps: collecting a standard test card image through an image acquisition card in a multi-stage standard illumination environment, and calculating sensitivity benchmark test data; executing time domain and space domain combined sampling processing to obtain super-sensitivity image data; performing brightness analysis and dynamic adjustment on the currently shot first scene image to obtain a first image acquisition parameter; acquiring a second scene image, and performing image grid division and contrast compensation on the second scene image to obtain an enhanced image after contrast compensation; according to the super-sensitivity image acquisition method and the super-sensitivity image acquisition device, the sensitivity limitation of the position depth of a traditional image acquisition card is broken through, and super-sensitivity image acquisition is realized.

The invention relates to the field of saliency target detection, and particularly discloses a multi-dimensional frequency domain and deformable attention fusion saliency target detection method, which comprises the steps of S1, inputting an infrared image to be detected; s2, performing multi-scale feature extraction and fusion to obtain low-level and high-level features; s3, phase spectrum analysis is carried out to extract frequency domain primary perception features; s4, fusing the frequency domain features to obtain frequency domain saliency features; s5, a deformable space attention module extracts space enhanced perception features; and S6, fusing the features to generate a prediction map and constraining the prediction map by a loss function. According to the method, the problems of insufficient frequency domain utilization, weak global context and detail retention and poor complex deformation target detection of an existing spatial domain method are solved, and the detection precision and robustness of a multi-scale and deformation target in a complex scene are effectively improved.

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.