802 results about "Scale space" patented technology

The invention discloses a de-noising diffusion model driven texture enhanced infrared and visible light image fusion method and system, and relates to the technical field of image processing and computer vision. The method comprises the following steps: performing multi-scale space-time modeling on infrared and visible light images; enhancing high-frequency texture features of the infrared image through an edge detection convolutional network; based on a bidirectional multi-scale convolution module and a bidirectional attention fusion module, capturing a remote dependency relationship and encoding multi-scale information to ensure full utilization of global information and accurate capture of local details; and optimizing the structural fidelity and color intensity distribution of the fusion result based on an adaptive structural similarity loss function and multi-channel intensity and texture loss so as to improve the quality of the fused image. According to the method, the process of diffusion feature extraction is enhanced by fusing the de-noising diffusion model and the texture enhancement strategy. Meanwhile, a bidirectional multi-scale convolution technology and an attention mechanism are combined, so that comprehensive utilization of global information and accurate mastering of local details are ensured.

The invention provides a multi-mode large model-based precision metal part defect detection method and system. The method comprises the following steps of: acquiring laser scattering image data of a precision metal part in an electromagnetic shielding environment; performing multi-scale spatial analysis on the laser scattering image data to extract a multi-modal image feature set containing a crystal boundary topological structure of the surface of the precision metal part and scattering spot distribution gradient features of the subsurface; converting process parameters, corresponding to the precision metal part, in an existing metal heat treatment process database into heat historical feature vectors, wherein the heat historical feature vectors comprise temperature gradient distribution features and time sequence phase change features; performing fusion processing on the thermal historical feature vector and the multi-modal image feature set through a multi-modal large model to obtain a fusion processing result so as to generate defect detection data; according to the invention, the detection rate and the detection efficiency of micron-sized defects in a complex electromagnetic environment are improved.

The invention relates to the technical field of water conservancy project detection, and discloses a water conservancy project safety detection early warning method based on artificial intelligence. The method comprises the following steps: acquiring multi-modal monitoring data of a key part through a distributed sensor network, and extracting a dynamic feature sequence in a preset time period through space-time alignment and noise filtering; inputting the image into a deep neural network fused with an attention mechanism, constructing a multi-scale space-time correlation map through hierarchical feature learning, and generating a high-dimensional representation of an engineering structure state; historical accident case data is used as a supervision signal, a hybrid expert model is used for performing multi-task training on high-dimensional representation, and the contribution weight of each monitoring index to the safety risk is obtained; combining real-time environment parameters and structural response characteristics to construct a dynamic threshold adjustment model, adaptively updating an early warning threshold according to a risk probability, and screening out key risk factors of which the contribution weights are greater than the updated threshold; and on the basis of spatial and temporal distribution characteristics, through graph neural network node association reasoning, multi-source early warning information is fused to generate a graded early warning result.

The invention provides a power transmission and transformation project ecological influence space-time boundary determination method and system based on multi-source remote sensing information deep fusion interpretation, and belongs to the technical field of power transmission and transformation project management. The method comprises the steps of data acquisition, data preprocessing and multi-source data integration, multi-scale space-time analysis, ecological influence index construction, remote sensing ecological index model construction, ecological influence space-time boundary determination, dynamic monitoring and early warning system platform establishment and long-term monitoring and evaluation. By integrating satellite remote sensing, unmanned aerial vehicle aerial photography and ground monitoring data and combining an image fusion algorithm, a principal component analysis method and a random forest algorithm technology, the method is beneficial to promoting accurate evaluation of the influence of the power transmission and transformation project on the ecological environment, visualizes the space-time boundary of the ecological influence, breaks through the limitation of a traditional evaluation method on time and space coverage, and improves the evaluation efficiency of the power transmission and transformation project. And a scientific method system for analyzing and evaluating the ecological influence of the power transmission and transformation project is further improved.

The invention relates to the technical field of airport safety monitoring, and discloses an airport video data real-time analysis system. The system comprises a video stream spatial-temporal feature modeling module, a behavior trajectory map construction module, an abnormal region association analysis module, a risk level semantic judgment module and a situation structure visualization module. According to the method, multi-scale spatial-temporal feature analysis is carried out on an airport monitoring video stream, a multi-dimensional behavior trajectory map is established, abnormal behavior region association is analyzed, risk level semantics are judged, and finally an airport global risk situation thermodynamic distribution map is generated. According to the system, the whole process processing from video data acquisition to risk situation visualization is realized, the abnormal behavior area can be accurately identified, the risk level and category are clear, comprehensive and visual situation information is provided for airport safety management, and the intelligent level of airport safety management is improved.

The invention provides a space-time decoupling feature fusion method based on space-time bidirectional Vision Mama, and the method comprises the steps: S1, extracting multi-scale space detail features from an input time sequence image through employing a plurality of cascaded 2D CNN blocks, and obtaining a feature graph; s2, a bidirectional space-time Mama structure is applied to the feature maps of the low and middle layers so as to compensate for loss of time information in the 2D CNN block; wherein for the feature map obtained in the step S1, time sequence features are extracted by applying time bidirectional Vision Mama, and then space features are extracted by using space bidirectional Vision Mama. The invention further provides a space-time decoupling feature fusion system based on the space-time bidirectional Vision Mama. According to the method, efficient and accurate feature extraction and information fusion are performed on a special time sequence multi-band multi-channel remote sensing image, and efficient and high-precision semantic segmentation of crops on a large-area scale remote sensing image is realized.

The invention belongs to the field of deep learning and machine vision, and discloses a surface defect detection method based on YOLOX multi-scale network reconstruction, and the specific technical scheme is as follows: a surface defect detection data set is converted into a YOLO standard input format, and a reconstruction feature extraction network performs deep information mining on an image in a series connection mode; in a channel aggregation path, generating a channel attention graph through operations such as global average pooling, convolution and activation, and combining the channel attention graph with a graph after space refinement to realize multi-scale information fusion in a channel dimension; in a multi-level multi-scale space, reconstructing a multi-scale fusion network Neck based on YOLOX features, realizing a space center on the top layer of a feature pyramid, and simultaneously adjusting all previous shallow layer features by using the obtained features containing the space explicit visual center; a decoupling head is introduced to process classification and positioning tasks respectively; inputting the training set for model training, and loading the model for surface defect detection.

The invention relates to the technical field of face recognition, in particular to a face recognition method and system for a dynamic environment, and the method comprises the steps: collecting a face video stream through a multispectral imaging device, and carrying out the preprocessing of dynamic noise reduction, distortion correction and the like; constructing a multi-scale space-time fusion feature extraction network to extract dynamic space-time features and fuse cross-modal features; establishing an environment disturbance simulation generation model to generate a virtual sample, and performing domain adaptive alignment; designing an online incremental feature updating mechanism to optimize parameters of the feature encoder; deploying a heterogeneous graph neural network to carry out multi-modal decision fusion; and a hierarchical verification architecture is adopted to complete identity recognition. The system comprises a data acquisition and preprocessing module, a multi-scale space-time fusion feature extraction module and the like. According to the method, the problem of face recognition in a dynamic environment is effectively solved, the recognition accuracy, robustness, real-time performance and reliability can be remarkably improved in the scenes of complex illumination, posture expression change, shielding, background noise and the like, and the method has a wide application prospect.

The invention relates to a deep learning-based historical urban style integrity evaluation method and system. The method comprises the following steps of: obtaining urban street view image data of a plurality of point locations; extracting a sky ratio and a green vision rate of an urban street scene image according to the urban street scene image data, respectively taking the sky ratio and the green vision rate as a street profile scale spatial feature and a natural element spatial feature, and calculating a signage color number and a color harmony degree of the urban street scene image as building color spatial features; calculating a traditional material proportion and material consistency of the urban street scene image as material mechanism spatial features; for the urban street view image data, obtaining an expert score obtained based on an ELO scoring algorithm; and constructing and training an evaluation model based on an artificial neural network based on the various spatial features and the small-scale expert scoring data set, and realizing historical urban style and appearance integrity evaluation by using the evaluation model.

The invention relates to the technical field of surveying and mapping information processing, and discloses a surveying and mapping information intelligent analysis and visualization system based on the Internet of Things. According to the system, a building space data acquisition terminal acquires geometric feature point cloud and environmental parameters of the surface of a building structure in real time through distributed Internet of Things nodes; the multi-source heterogeneous data fusion engine performs space-time alignment processing on the geometric feature point cloud to generate a building total-factor topological skeleton with an absolute coordinate system; the three-dimensional topological relation reconstruction module is used for extracting a spatial constraint relation of building components according to the topological skeleton and establishing a hierarchical building information model capable of being edited in a parameterized manner; and the dynamic visual rendering platform is used for generating a multi-scale spatial index based on the hierarchical building information model, and driving real-time light and shadow effects and interactive sectioning analysis. According to the system, full-process automatic processing and dynamic visualization of building surveying and mapping data are realized.

The invention relates to the technical field of machine vision, and discloses a surveying and mapping geographic information analysis method and system based on machine vision and a medium. The method comprises the following steps: preprocessing multi-source remote sensing data to obtain a standardized surveying and mapping data set, and extracting ground feature edge and texture information to obtain a multi-scale spatial feature and a semantic segmentation result; carrying out multi-source data integration to obtain a unified geographic element representation diagram, and carrying out geographic element identification on the unified geographic element representation diagram to obtain a surveying and mapping geographic element set; performing Bayesian inference of spatial uncertainty quantization and parameter uncertainty quantization on the surveying and mapping geographic element set to obtain a comprehensive uncertainty evaluation result; and constructing vectorized geographic information based on the surveying and mapping geographic element set and the comprehensive uncertainty evaluation result. According to the method and the device, the edge information of the geographic elements is effectively reserved, the identification precision of the geographic elements is improved, the geographic information expression is more structured, and automatic updating is realized.

The invention discloses a scene text recognition method based on optimized multi-modal vision and language processing, which comprises the following steps of: firstly, normalizing image data; and then inputting the preprocessed data into the optimized visual model. The visual model extracts multi-scale space and semantic features through a convolution-Transform hybrid neural network, and enhances the feature expression ability by using a multi-scale attention mechanism; the language model corrects character probability vectors output by the visual model, and learnable position codes are introduced to optimize representation of the features. Through designing a bidirectional multi-modal interaction module, visual and language features are fused, and a self-adaptive fusion mechanism is used to generate high-quality multi-modal joint feature representation. In the application stage, the optimized model is deployed through an efficient reasoning framework, and the speed and accuracy of scene text recognition are remarkably improved.

The invention provides a land geographic surveying and mapping model generation method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining a geographic surveying and mapping data set containing a satellite remote sensing image, surface elevation and the like in a target region, then carrying out the topographic feature interpretation, and generating a topographic semantic, surface coverage and surveying and mapping task correlation feature set; then calling a geographic space encoder to carry out multi-scale space modeling on the related feature set to obtain a geographic space representation vector set, fusing the geographic space representation vector set with a preset geographic entity topological graph dynamic feature to generate a geographic entity related feature set, and carrying out multi-scale space modeling on the geographic entity related feature set; and finally, training a geographic surveying and mapping analysis model according to the geographic entity associated feature set and the surveying and mapping task associated feature set, generating a geographic surveying and mapping optimization strategy, and feeding back the geographic surveying and mapping optimization strategy to a surveying and mapping terminal to trigger surveying and mapping parameter dynamic adjustment operation so as to realize more optimized land geographic surveying and mapping model generation.

The invention discloses a remote physiological signal estimation method and system based on a diffusion model, and relates to the technical field of non-contact physiological signal detection. The training process of the diffusion model is as follows: forward diffusion is performed on an original rPPG signal to obtain a noise rPPG signal; performing feature extraction on the face video to obtain a multi-scale space-time diagram; the noise rPPG signal and the multi-scale space-time diagram are fused; carrying out backward diffusion on the fused data to obtain de-noised data; outputting a predicted rPPG signal according to the denoised data; performing model training by minimizing the difference between the predicted rPPG signal and the original rPPG signal; and performing remote physiological signal estimation by using the trained diffusion model. According to the invention, the accuracy of rPPG signal estimation is improved.

The invention discloses a fine-grained zero-sample medical image classification method based on cross-modal feature alignment, and the method comprises the steps: 1, carrying out the partitioning of a full-section pathological image, and extracting the features of a local image block; 2, a cross-modal alignment module is used for designing a local window attention mechanism to enhance space interaction between image blocks; the semantic enhancement module is used for constructing a pathology prompt template based on a large language model to generate fine-grained category description, and expanding the distance between categories in a semantic space; and 4, performing weighted fusion on the image block features through coordinate sensing, and generating final slice-level classification prediction. According to the invention, through multi-scale space interaction of the cross-modal image block alignment module and semantic enhancement of the semantic refinement module based on the visual language model, the classification precision of the fine-grained medical image is significantly improved, and the limitation of the existing method on feature alignment and semantic differentiation is effectively solved; and an efficient solution is provided for zero-sample medical image classification.

The invention discloses a medical image classification method and system based on multi-scale spatial state modeling, and the method comprises the steps: firstly dividing an input medical image into a plurality of non-overlapping image blocks, and mapping the non-overlapping image blocks to a feature space through a learnable linear projection layer to obtain an initial feature map; then, multiple layers of stacked MS-SMamba blocks are used for carrying out layer-by-layer feature extraction, each MS-SMamba block comprises a main branch, an auxiliary branch, a dynamic gating fusion network, a residual error connection unit and a feedforward network, and long-range dependency relation capture and multi-scale feature fusion are achieved; and finally, processing the last-layer output feature map through a global feature aggregation and classification module, generating a global feature vector, and outputting a classification result. According to the method, the capturing capability of complex pathological features in the medical image is improved, the calculation efficiency and clinical applicability are improved, and the method is suitable for scenes such as disease screening and auxiliary decision making in medical image diagnosis.

The invention relates to the technical field of deep learning image recognition, in particular to an unmanned aerial vehicle small target detection method based on deep learning, and the method comprises the steps: embedding a parallel block perception attention module in a C2f module of YOLOv8; a large separable nuclear attention mechanism is fused in the SPPF module of the YOLOv8; the original nearest neighbor interpolation is replaced by CARAFE dynamic up-sampling; the Soft-NMS is adopted to replace the NMS; reconstructing a Neck part of the backbone network; a dynamic target detection head is combined with a scale sensing module, a space sensing module and a task sensing module; a WFS-IoU loss function fusing Wise-IoU, Focaler-IoU and Shape-IoU is designed, aiming at the core bottlenecks of feature loss, poor scale adaptability, dense target processing defects and the like in small target detection of the unmanned aerial vehicle, the balance between precision and efficiency is realized through multi-module collaborative optimization and lightweight design, and the detection accuracy is improved. And an efficient and reliable detection solution is provided for aerial photography application of the unmanned aerial vehicle.

The invention discloses an epilepsy detection method based on a multi-scale space-time diagram attention fusion network, and the method comprises the steps: carrying out the preprocessing of an electroencephalogram signal, obtaining time domain data, and constructing a macroscopic multi-scale fusion module and a microscopic multi-scale fusion module which are completely identical in structure; performing sequence decomposition on the time domain data to obtain a macroscopic change sequence and a microcosmic change sequence of the electroencephalogram signals; the macroscopic change sequence is input into a macroscopic multi-scale fusion module for time sequence feature extraction, and meanwhile, the microscopic change sequence is input into a microscopic multi-scale fusion module for time sequence feature extraction; respectively carrying out downsampling operation on the two types of change sequences, and carrying out layer-by-layer feature extraction by using a graph attention mechanism; the two types of features are added and fused to obtain space-time dynamic fusion features, the space-time dynamic fusion features are input into a global dependency extraction module, and the global dependency extraction module captures a global dependency relationship of the electroencephalogram signals by using a sparse attention mechanism; and performing epilepsy detection classification by using the classifier. The electroencephalogram signals are decomposed into a plurality of scales, and the electroencephalogram signals of each scale are processed, so that mutual interference among features is avoided; a sparse attention mechanism is adopted to carry out modeling long-time dependence.

The invention relates to the technical field of power equipment state monitoring, and particularly discloses a transformer fault diagnosis method and system based on image recognition, and the method comprises the steps: collecting a transformer multi-mode image sequence in real time, and carrying out the definition and part integrity evaluation and screening to form an initial image set; performing multi-scale space registration on the initial image set and a transformer normal state standard template to generate a reference image, and reversely deriving a displacement vector field based on pixel-level difference; carrying out smooth optimization and geometric reconstruction on the displacement vector field under the geometric constraint of the transformer structure, and generating a correction image with a real structure; fault feature enhancement is carried out in a gradient domain of the corrected image, a fault area is identified through matching of multichannel feature extraction and a transformer typical fault feature library, and a diagnosis report integrating fault types, confidence coefficients and geometric parameters is generated; according to the method, the problem of image geometric deformation caused by shooting condition differences is effectively solved, and the accuracy and reliability of fault identification are improved.

The invention relates to a hyperspectral image classification method and device based on a state space model. The hyperspectral image classification method based on the state space model comprises the following steps: sequentially carrying out feature extraction and serialization processing on hyperspectral image data to obtain a shallow feature projection vector; performing global-local feature extraction on the shallow feature projection vector by adopting a neural network based on a state space model to obtain a fused feature projection vector; and carrying out pixel-by-pixel classification and dimension rearrangement on the hyperspectral image data in sequence to generate a classification result of the hyperspectral image data. According to the hyperspectral image classification method based on the state space model, long-range dependence modeling is achieved through the neural network based on the state space model with linear complexity, the calculation complexity is effectively reduced, and through feature fusion and residual error connection, the classification accuracy of the hyperspectral image is improved. And the perception capability of the neural network on different scale space-spectrum structures in the hyperspectral image is effectively enhanced.

The invention discloses a complex scene-oriented target identification method, system and device and a medium, and relates to the technical field of computer vision. The method comprises the following steps: inputting a to-be-detected image into a target recognition model for processing to obtain a target recognition result; the target identification model is constructed based on a dual-channel coding network and a weighted optimization loss function; the dual-channel coding network comprises a MobileNet channel and a wavelet channel; wherein the MobileNet channel is used for extracting multi-scale spatial features and is composed of a layered encoder and a multi-feature prediction decoder which are connected in sequence; the wavelet path is used for extracting frequency domain features and is composed of a global semantic wavelet coding module and a local wavelet fusion decoding module which are connected in sequence; and the multi-feature prediction decoder is also respectively connected with the global semantic wavelet coding module and the local wavelet fusion decoding module. According to the invention, the target identification precision and accuracy for complex scenes can be 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 method, a system, equipment and a medium for analyzing project progress based on a BIM model and an AI video, and relates to the technical field of constructional engineering management, and the method comprises the steps of collecting regional image data, and executing semantic segmentation and environment modeling. And constructing a multi-scale spatial feature network and a dynamic skeleton modeling engine, inputting the three-dimensional environment diagram, the structure recognizable region diagram and the obstacle probability distribution diagram into the multi-scale spatial feature network and the dynamic skeleton modeling engine, and outputting execution structure recognition and defect anomaly labeling. And triggering an engineering response mechanism based on the risk event scoring function and remotely and dynamically adjusting the construction path. According to the method, through a mode of combining semantic segmentation and three-dimensional environment modeling, high-precision structure identification of the construction site image is realized, and the problems of unclear structure identification and fuzzy component boundary in traditional video monitoring are effectively solved.

The invention provides a digital twin three-dimensional model construction method based on a generative large model, and the method comprises the steps: obtaining multi-source monitoring data of a power distribution network, and processing the multi-source monitoring data into a training data set; the method comprises the following steps: mapping multi-source monitoring data into a multi-scale tensor subspace through tensor wavelet structured transformation, adaptively extracting spatial features through a learnable wavelet kernel, and keeping the structural continuity of a physical field in combination with a geometric prior regular term; constructing and training a generative adversarial network through a training data set; inputting and analyzing the physical parameter vector of the target scene, and if the topological similarity score is lower than a preset threshold value, adjusting noise vector regeneration; and if yes, outputting a three-dimensional model tensor and importing the three-dimensional model tensor into a digital twin platform, and driving real-time physical field visualization. According to the method, characteristics of a multi-scale space structure and a nonlinear physical field can be reserved, the physical rationality and generalization ability of the generated model are remarkably improved, and depth identification of topological attributes (such as hole connectivity and surface defects) and local geometric defects of the three-dimensional model is realized.

The invention discloses a GNSS interference identification method based on spatial transformation, multi-scale feature fusion and KAN. The method comprises the steps of forming an interference signal data set; obtaining a time-frequency image training set and a time-frequency image test set; constructing a GNSS interference identification classifier composed of a spatial transformation module, a multi-scale feature fusion module and a KAN module; a trained GNSS interference identification classifier is obtained; and obtaining a final GNSS interference identification classifier. And finally, outputting the category of the GNSS interference signal acquired in real time by the GNSS interference identification classifier. According to the invention, the spatial transformation module is used to carry out translation, scaling and other operations on the interference signal time-frequency image, and the number of training samples is increased. And the multi-scale feature fusion module adopts parallel convolution kernels of different scales to extract multi-scale spatial features of the time-frequency graph, so that the richness of feature representation is increased, and the recognition accuracy is further improved. The KAN module uses a KAN to replace a traditional multi-layer perceptron to execute a final classification task, and a more complex nonlinear function can be fitted by using fewer parameters.

The invention discloses a regional highway road network habitat quality evaluation method and system, and aims to construct a habitat feature library reflecting habitat spatial features and a biological utilization mode by integrating remote sensing image data and biological activity trajectory data. Identifying an ecological fault zone caused by road network cutting by adopting a space fracture analysis technology, quantifying the barrier strength of the road and determining an influence range; analyzing and extracting a key migration gallery by using a species migration network, and evaluating a landscape connectivity condition; a restoring force loss area is identified through ecological restoring force evaluation, and the habitat degradation dynamic state is revealed in combination with time sequence analysis; establishing a multi-scale space evaluation system, and fusing the quality grading sequence and gallery optimization information to generate a habitat quality evaluation matrix; and finally, a complete habitat quality grading scheme is formed through spatial interpolation and natural breakpoint grading, comprehensive evaluation of the habitat quality of the regional highway network is realized, and a scientific basis is provided for ecological protection planning and road construction decision making.

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 discloses a remote photoplethysmography (rPPG) signal processing method and system based on a long and short term space-time convolution network, and belongs to the crossing field of biomedical signal processing and computer vision. In order to solve the problem of signal distortion caused by illumination fluctuation, motion artifacts and skin color differences, the method constructs a multi-scale space-time modeling framework: extracting local space-time features of transient changes of facial capillaries by adopting a 3D convolutional network, capturing long-range periodic features of heart rate rhythm in combination with a 1D expansion convolutional network, and establishing a multi-scale space-time modeling framework; the spatial-temporal characteristics are dynamically fused through the self-attention weight and the gating residual structure, and the anti-interference capability is improved. In the preprocessing stage, a face area is positioned through MTCNN, motion artifacts are compensated by using an optical flow equation, and signal purity is enhanced by combining a skin color mask and a YUV color space. The system adopts a deep separable convolution and parallel acceleration strategy to realize light weight, and optimizes the network through time domain MSE loss and frequency domain KL divergence. Experiments show that the phase error of the method is reduced by 40% in a dynamic scene, the signal amplitude of a deep skin color group is improved by 60%, the method is suitable for non-contact health monitoring equipment, and the robustness and the measurement precision of the rPPG technology in a complex environment are remarkably improved.

The invention discloses a remote sensing image semantic segmentation method based on geometric perception diffusion guidance, and is applied to the technical field of remote sensing image semantic segmentation. Comprising a training stage and a testing stage, in the training stage, original remote sensing images, nDSM corresponding to each original remote sensing image and real semantic segmentation images are selected to form a training sample set, and a segmentation everything model based on geometric perception diffusion guidance is constructed and trained; comprising an enhanced visual converter encoder, a diffusion prompt module, a segmented everything image prompt encoder, a segmented everything image mask decoder and a prompt level supervision strategy. In the test stage, various channel components of a to-be-detected remote sensing image are input into the trained model, and the model network outputs a remote sensing image semantic segmentation prediction map corresponding to an original remote sensing image. According to the method, multi-modal remote sensing data can be effectively fused, a multi-scale space structure is captured, and full-automatic semantic segmentation is realized, so that the segmentation efficiency and accuracy are remarkably improved.

The invention belongs to the field of artificial intelligence and electroencephalogram emotion recognition, and provides a double-branch electroencephalogram emotion recognition method and system based on brain region topology and time-space, and the method comprises the steps: preprocessing a to-be-recognized electroencephalogram signal to obtain a plurality of electroencephalogram fragments, and extracting a difference entropy sequence of each electroencephalogram fragment and a Spearman correlation coefficient matrix between channels; based on the Spearman correlation coefficient matrix, utilizing a bridging dynamic graph attention network module to extract topological features of a brain region; processing the differential entropy sequence by using a multi-scale space-time mixed attention module to obtain multi-scale space-time features; carrying out residual mutual cross attention fusion on the topological features of the brain region and the multi-scale spatial-temporal features to obtain fusion features; and performing classification based on the fusion features, and determining an emotion recognition result corresponding to the electroencephalogram signal. According to the method, the accuracy and robustness of emotion recognition are improved by utilizing the spatial topology characteristics and the multi-topology time dynamic characteristics of the electroencephalogram signals, and the defects of modeling spatial dependence and time dynamic are overcome.