29 results about "Remote sensing image segmentation" patented technology

The application discloses a kind of based on paradigm-crossing feature fusion and alignment remote sensing image segmentation method and system, comprising: the initial feature is extracted to the input remote sensing image and is preprocessed;Input paradigm-crossing feature fusion and alignment network, through sparse channel enhancement and spatial alignment and spatial pixel refining and channel alignment, fusion multi-modal, cross-scale remote sensing image structure information, obtain first stage fusion feature;Input multi-stage paradigm-crossing enhanced feature extraction network, through multi-level information interaction and dynamic gate mechanism, fusion local details and global context information, gradually extract out the joint feature map of semantic and spatial structure collaborative expression;Through segmentation head, generate final semantic segmentation result, and calculate composite loss based on real label;The application is by constructing multi-stage feature extraction network and paradigm-crossing feature alignment mechanism, effectively fusion local texture, spatial context and multi-modal information, while guaranteeing the computing efficiency, strengthen segmentation performance.

The application discloses a kind of based on attention enhancement and dense multi-scale ground feature classification network model, to solve the problem of insufficiently fine remote sensing image segmentation result caused by " same spectrum different things " and " same thing different spectrum " phenomenon.The method is based on DeepLabv3+ network, in order to better process remote sensing image, the deficiency of its encoder and decoder stage is improved in model structure.In the encoder stage, the application designs a kind of attention enhancement dense hollow pyramid pooling to replace the original hollow space pyramid pooling structure, and simultaneously, the double attention mechanism is introduced in global feature, which can help remote sensing image to achieve balance between feature representation capability and spatial positioning accuracy.In the encoder stage, the multi-level feature map of image is used to upsample the image by using dense connection mode.

This invention discloses a remote sensing image segmentation method based on an integrated cross-attention mechanism. The method employs a deep residual network ResNet101 to extract features from RGB remote sensing images, obtaining an initial feature map. A cross-attention mechanism is introduced, using the original image and the initial feature map as input, to mine the regional associations within the RGB remote sensing image, enhance key region features for target recognition, and perform feature enhancement on the initial feature map, outputting a focused feature map. A deep learning model, DeepLabV3, is used to extract multi-scale features from the focused feature map. The Awfully Hollow Spatial Pyramid Pooling (ASPP) module captures contextual features under different receptive fields and fuses them with low-level detail features from ResNet101, resulting in a final feature map with rich context and clear boundaries, outputting the semantic segmentation result. This invention improves the segmentation capability of complex scenes through the cross-attention mechanism, and by utilizing image space and contextual information, it can effectively improve the segmentation accuracy of complex urban and rural features.

The application discloses a plantation remote sensing image segmentation and recognition method and system, relates to the technical field of remote sensing image processing, and comprises the following steps: acquiring multi-temporal remote sensing images and laser radar point cloud data and registering, extracting stand height information and crown structure information, using the crown structure information to constrain and reconstruct spectral characteristics to obtain structure spectral coupling characteristics; calculating spectral differences and texture changes, combining stand height time series changes to construct stand state evolution characteristics; fusing to obtain fusion characteristics; constructing a double-channel semantic segmentation model to train and perform pixel-level joint classification to obtain an initial classification result; based on the crown structure information, a matching constraint rule is established to modify the initial classification result to obtain a final classification result, and high-precision recognition of degraded forest land tree species is realized.

The application discloses a kind of multi-dimensional attention mechanism's remote sensing image segmentation method, selects UNet3+ as basic segmentation framework, by introducing dynamic attention mechanism and light structure design is improved in view of, aims at improving the precision and efficiency of building segmentation in high-resolution remote sensing image.The method has carried out key improvement in the following three aspects: firstly, in the feature coding and enhancement path, the multidimensional context attention module (MDCA) proposed in the application is embedded in the skip connection of original UNet3+, the module fuses spatial and channel double attention, dynamically models global context dependency and channel importance, so that the network can adaptively focus on the building area and fine boundary, enhance the discrimination ability to multi-scale target and complex background.

This invention discloses an iterative optimization method and related apparatus for single-tree crown segmentation based on confidence decoupling and prior-driven principles. The method includes: inputting remote sensing image data into a single-tree crown segmentation model to output a coarse segmentation result; performing confidence assessment on the coarse segmentation result to generate a confidence assessment result; generating prior information from the confidence assessment result using a prior encoder, and fusing the prior information with the original high-dimensional features to generate fused features; inputting the fused features into a neural network decoder for the next optimization segmentation process, outputting the next optimized single-tree crown segmentation result, and returning to the confidence assessment step, until the number of optimization iterations reaches a preset number, at which point the final optimized single-tree crown segmentation result is output. In this embodiment, the boundary precision and regional consistency of remote sensing image segmentation in complex forestry scenarios are significantly improved.

This invention discloses an open-vocabulary semantic segmentation method, system, and device based on inference-time adaptive approach: Based on given basic task information, a context-aware text prompt generator constructs task-driven text prompts, generating context-aware text descriptions for each candidate category; a text encoder and a visual encoder extract text features and visual features from the generated text descriptions and the input remote sensing image, respectively; a feature upsampling module obtains higher-resolution upsampled visual features based on the visual features; during the test inference phase, based on the visual features and the upsampled visual features, a visual-guided inference-time adaptive strategy is used to optimize the text features, obtain a semantic segmentation mask, and complete the semantic segmentation of the open-vocabulary remote sensing image. This invention improves the segmentation performance of remote sensing images by dynamically adjusting the text representation during the inference phase, alleviating text ambiguity, enhancing visual-linguistic alignment in uncertain prediction regions, and improving the overall performance of remote sensing image segmentation.

The application discloses a kind of remote sensing image multiscale feature fusion semantic segmentation methods based on SAM large model, comprising: remote sensing image data is input after pre-processing improved SAM image encoder, and global image embedding of global semantic and high-frequency details is generated and fused;Sparse prompt point information is generated to target area mark, and is coded into prompt embedding containing position and semantic information by SAM prompt encoder;Image embedding and prompt embedding are input into SAM mask decoder to generate preliminary segmentation mask;A small amount of parameter fine-tuning is carried out using Rein method to relieve SAM model remote sensing field deviation, and original mask decoder is replaced by MACU-Net decoder, multiscale feature fusion and target boundary recovery are realized, and high-precision high-robustness semantic segmentation result suitable for complex remote sensing scene is generated.The application solves the problems of high-frequency information loss, multiscale feature boundary blur and regional deviation in the original SAM model in remote sensing image segmentation.

This application provides a remote sensing image segmentation method and related equipment. The method includes the following steps: acquiring the remote sensing image to be segmented; using a trained deep learning network model to obtain the remote sensing image semantic segmentation result of the remote sensing image to be segmented; the deep learning network model includes an encoder-decoder architecture; the decoder includes a frequency-sensitive attention module, a context-aware Transformer block, and a decoding head; the output feature maps of different levels of the encoder are input into the corresponding frequency-sensitive attention module for frequency decomposition; the context-aware Transformer block performs cascaded context enhancement processing; the decoding head is used to fuse the results to obtain the remote sensing image semantic segmentation result. By designing a novel encoder-decoder architecture, the local feature extraction capability of CNN and the global context modeling capability of Transformer are effectively integrated.

The application provides a water body boundary identification method and device based on boundary perception collaborative optimization, belongs to the field of artificial intelligence remote sensing SAR image segmentation, and comprises the following steps: a deep learning model is constructed, a real-time double-branch semantic segmentation framework is adopted to meet the timeliness requirement of water body boundary identification; an auxiliary boundary prediction branch is introduced to highlight high-frequency semantic information, a boundary detection is taken as an optimization target, and a boundary perception loss is introduced to predict complex water body boundaries; a pixel attention module, a context fast aggregation module and a boundary attention guiding module are proposed to mine spatial detail information, context information and boundary information of a target image respectively, control effective learning of context semantic information, guarantee reliability and timeliness of extracted information, guide effective fusion of various information at a boundary area, jointly optimize original double-branch and auxiliary branches, and realize accurate identification of water body boundaries. The application can improve identification precision.

This disclosure presents a multimodal remote sensing image segmentation method, system, and electronic device. The method involves acquiring multimodal remote sensing images, preprocessing these images (including optical images and elevation images), extracting optical features from the optical images, and extracting elevation features from the elevation images. A graph Laplacian matrix is ​​constructed based on the optical and elevation features, and feature fusion is performed using this matrix to obtain target fusion features. A segmentation model is then invoked to predict the category probability based on the target fusion features, resulting in a predicted segmentation result for the multimodal remote sensing image. The target loss is determined based on the predicted segmentation result and the label segmentation result, and the segmentation model is trained based on this target loss. Finally, the trained segmentation model is invoked to segment the remote sensing image to be processed, resulting in a segmentation result for the remote sensing image to be processed. This method improves the segmentation accuracy and efficiency of multimodal remote sensing images.

This invention relates to the field of remote sensing image segmentation technology, specifically to a method and system for river and lake remote sensing image segmentation based on convolutional neural networks. The method includes: acquiring and preprocessing multi-source remote sensing images to construct a multi-scale image pyramid; performing preliminary extraction of target-level images based on a water body spectral feature library to generate candidate water body masks; constructing a convolutional neural network with a dilated convolutional encoder and a skip connection decoder; concatenating the candidate masks with the original image channels as network input for training and optimization; using the trained model to infer new remote sensing images, outputting a probability map, and then post-processing to obtain the final water body segmentation result. This method improves the accuracy of water body segmentation and its adaptability to complex scenes by integrating spectral prior knowledge with deep learning.

The application relates to the technical field of remote sensing image segmentation, and provides a remote sensing image segmentation method based on wavelet band enhancement and related equipment, which comprises the following steps: performing wavelet transform decomposition on a target remote sensing image to obtain a plurality of band components of the target remote sensing image; performing feature projection on each band component to obtain a corresponding band feature of each band component; splicing all the band features to obtain frequency volume information, and performing deep feature interaction and fusion on the frequency volume information to obtain final features of the target remote sensing image; and performing mask segmentation based on the final features to obtain a mask segmentation result of the target remote sensing image. The method can improve the precision of interactive segmentation of remote sensing images.

The application discloses an image segmentation method and system based on local-global fusion and channel modulation, and relates to the technical field of image segmentation. The specific steps are as follows: a local-global fusion attention module and a depth estimation module are combined to encode an input remote sensing image, and a multi-scale fusion feature map is output; the multi-scale fusion feature map is subjected to feature compression and segmentation, cross fusion, channel modulation and adaptive weighting, and a modulation feature map is output; the spatial resolution of the modulation feature map is restored through step-by-step upsampling and convolution, and a pixel-level class prediction map is generated through segmentation. The application optimizes the spatial distribution consistency of features, helps to improve the class consistency of the overall segmentation result, reduces the class confusion phenomenon, and is especially suitable for complex remote sensing image segmentation tasks containing multiple classes and multiple scales.

This invention discloses a remote sensing image semantic segmentation method based on global dependency and local detail collaboration, belonging to the field of remote sensing image segmentation technology. It includes: acquiring remote sensing images and preprocessing them to obtain a dataset; constructing a remote sensing image semantic segmentation model, including a ConvNeXt-based backbone network feature extraction module, an LA-Mamba decoding module, a multi-scale spatial feature fusion module, and a prediction output module connected sequentially; training the remote sensing image semantic segmentation model based on the dataset; acquiring the remote sensing image to be segmented, and performing semantic segmentation using the trained remote sensing image semantic segmentation model to obtain the segmentation result. This invention significantly improves segmentation performance while maintaining accuracy by designing an LA-Mamba module and a multi-scale spatial feature fusion module in the decoding stage to achieve complementary modeling of local details and global context.

The invention discloses a remote sensing image multi-scale feature fusion semantic segmentation method based on an SAM large model, and the method comprises the steps: preprocessing remote sensing image data, inputting the preprocessed remote sensing image data into an improved SAM image encoder, and generating global image embedding fusing global semantics and high-frequency details; generating sparse prompt point information for a target area mark, transmitting the sparse prompt point information into an SAM prompt encoder, and encoding the sparse prompt point information into prompt embedding containing position and semantic information; inputting image embedding and prompt embedding into an SAM mask decoder to generate a preliminary segmentation mask; a Rein method is adopted to carry out fine tuning on a small amount of parameters to relieve offset of the SAM model in the remote sensing field, an original mask decoder is replaced with an MACU-Net decoder, multi-scale feature fusion and target boundary recovery are achieved, and a high-precision and high-robustness semantic segmentation result adaptive to a complex remote sensing scene is generated. According to the method, the problems of high-frequency information loss, multi-scale surface feature boundary blur, region offset and the like of the original SAM model in remote sensing image segmentation are solved.

The invention discloses a map matching and forward and reverse projection wide remote sensing image segmentation and sample automatic generation method. The method comprises the following steps: step 1, taking an original image, metadata and coastline vector data as an input triple; data cleaning and normalization are carried out through an image preprocessing module; entering a geometric correction and registration module to generate a corrected image with an Alpha channel; 2, performing spatial indexing and matching on the coastline vector data and the corrected image; using a mask generation algorithm to automatically align and rasterize the vector data, and constructing a final true value mask of pixel-level alignment; 3, initializing a reverse mapping grid through a coordinate transformation processing module; calculating a nonlinear mapping relation from geographic coordinates to original sensor pixel coordinates by using a coordinate inverse transformation calculation module; and through resampling processing, accurately backfilling the semantic tag to an original image space, and outputting a final inverse transformation mask. According to the invention, high precision is ensured, and meanwhile, the order of magnitude of processing speed is improved.

The application provides a multi-type audio guided unmanned aerial vehicle remote sensing image segmentation method and system based on fine semantic embedding, relates to the intelligent processing of remote sensing images and the cross field of multi-modal artificial intelligence, and comprises the following steps: collecting remote sensing images, remote sensing related audio and voice data, and constructing a multi-type audio guided remote sensing image segmentation dataset; constructing a multi-type audio guided remote sensing image segmentation model based on fine semantic embedding, wherein the model comprises a remote sensing image feature encoding module, an audio feature encoding module, a fine semantic embedding module, an audio semantic request module and a mask feature decoding module; and training the multi-type audio guided remote sensing image segmentation model through the multi-type audio guided remote sensing image segmentation dataset until the training completion condition is met. This segmentation method improves the intelligent interactive processing capability of remote sensing images, and the coincidence degree of remote sensing images and audio semantics is improved through complete modeling and fine semantic embedding of audio semantics.

The application relates to a remote sensing image segmentation method, device and equipment based on spatial affinity learning. The method comprises the following steps: obtaining a multi-level feature map of a remote sensing training image through a feature extraction network and a neck network, inputting the multi-level feature map into a head network containing parallel detection and segmentation branches to obtain hierarchical classification and regression features, performing multi-level aggregation and enhancement on the two types of features through a spatial information enhancement unit, splicing the features into a bounding box feature, generating a mask feature from the multi-level feature map, guiding the enhancement of the mask feature through the bounding box feature through a double-flow residual feature fusion unit to enhance the spatial perception and semantic coherence of the mask feature, splicing the mask feature and relative coordinates to input a full convolution segmentation head to obtain an instance segmentation prediction result, calculating a detection and segmentation branch loss by taking the prediction result and a horizontal box label as input, training each module to obtain a segmentation network, processing a remote sensing image through the segmentation network to obtain a detection and segmentation result. The method improves the utilization rate of spatial information of box supervision, optimizes the box supervision remote sensing instance segmentation task, and reduces the gap with the full supervision method.

This invention relates to a remote sensing image segmentation method and system based on neighborhood spectral similarity, comprising the following steps: preprocessing the acquired raw remote sensing image to obtain remote sensing image data containing the reflectance of ground objects in each band; calculating a preset segmentation index based on the remote sensing image data containing the reflectance of ground objects in each band, and classifying the remote sensing image data based on a preset segmentation threshold to obtain a remote sensing image classification result. This invention, based on the preprocessed remote sensing image, fully utilizes the spectral similarity and similarity index of neighboring ground objects to segment the remote sensing image, greatly improving the segmentation accuracy. Therefore, this invention can be widely applied in the field of image classification.

This invention discloses a remote sensing image segmentation method based on global dependency and local texture fusion attention, belonging to the field of image processing technology. The method includes the following steps: inputting the remote sensing image to be segmented into a trained multi-scale global-local fusion remote sensing segmentation network to obtain a segmented image of the remote sensing image to be segmented; wherein the multi-scale global-local fusion remote sensing segmentation network adopts a symmetrical encoder-decoder structure, and introduces global dependency and local texture fusion attention modules at each scale layer. This invention can effectively fuse local texture details and global spatial dependencies, achieving high-precision segmentation and high-efficiency inference simultaneously in complex remote sensing scenes, and significantly improving the recognition ability of small targets, fine boundaries, and large-scale ground structures.

This application relates to a method, apparatus, computer equipment, storage medium, and computer program product for building roof recognition based on multi-source heterogeneous deep network fusion, which can be used in the field of image recognition technology. This application can improve the efficiency and accuracy of building roof recognition. The method includes: acquiring an optical image and a remote sensing image of a target area; the target area contains a building roof; inputting the optical image into an optical image segmentation model to obtain an optically segmented image of the building roof; inputting the remote sensing image into a remote sensing image segmentation model to obtain a remotely sensed segmented image of the building roof; fusing the optical and remotely sensed segmented images to obtain a fused segmented image of the building roof; and recognizing the fused segmented image to obtain the area information of the building roof.

The application discloses a kind of remote sensing image segmentation methods based on multi-scale gating bottleneck convolution scanning, it is related to remote sensing image segmentation field, including: input remote sensing image, initial feature is extracted by initial convolution layer;By encoder, initial feature is carried out multistage down-sampling processing, and each level is sequentially carried out feature enhancement using multi-scale gating bottleneck convolution scanning unit, and the encoding feature of multilevel is obtained;At the deepest feature of encoder, introduce semantic bridging attention unit to carry out global semantic modeling and residual fusion, and obtain enhanced deep semantic feature;In decoder, gradually up-sampling processing is handled, and the feature after up-sampling processing is fused with the encoding feature of corresponding level, and the multi-level fusion feature is obtained;The fusion feature output by decoder is input into segmentation head, and the prediction probability graph is obtained.The method improves the segmentation continuity and class discrimination robustness of slender target, complex boundary and small-scale ground object in remote sensing image.

The application discloses a kind of remote sensing image semantic segmentation method and device, the method is under the general encoder-decoder network architecture, respectively strengthen the feature extraction capability of encoder and the feature fusion capability of decoder, in the encoder stage, for the extraction of inter-spatial position and inter-channel correlation, sparse spatial attention module and sparse channel attention module are proposed, to realize representation enhancement with a small amount of calculation cost;In the decoder stage, for the sampling loss and multi-level feature fusion problem, a multi-level feature fusion strategy of data-dependent upsampling is proposed, which reduces the loss in the feature recovery stage through a learnable way, ensures the fidelity in the representation conversion process.The application can not only be suitable for multi-resolution satellite remote sensing image and unmanned aerial vehicle remote sensing image segmentation, but also has high classification accuracy and running efficiency.

The application discloses a semantic-topology task decoupling and boundary guidance remote sensing image segmentation method. The method comprises a multi-scale feature encoder, a feature bridging module, a decoupling double-branch decoder and a high-frequency boundary guidance mask refinement module (GMRM). In the feature extraction stage, the bridging module constructs cross-dimension feature aggregation and global-local context representation through the enhanced ternary attention (ETA) of multi-view orthogonal gating and the adaptive window token aggregation block (TAB); the decoding stage performs semantic-topology decoupling, and independent decoders respectively reconstruct internal semantic regions and structural outlines; finally, the GMRM converts boundary prior into spatial weight, and performs nonlinear multiplication modulation and addition residual correction on the mask features. The application overcomes the feature competition conflict between region smoothing and edge sharpening, breaks the spatial topology adhesion bottleneck, and significantly improves the pixel-level precision and geometric integrity of target segmentation.

The present application relates to the technical field of remote sensing image processing, and specifically discloses a remote sensing image segmentation method, system and product based on a light-weight UMFormer. The present application is based on the light-weight and moderately accurate UMFormer, adopts a two-stage optimization strategy of first improving segmentation accuracy and then balancing light-weight efficiency, and realizes high-precision and light-weight segmentation of remote sensing images. The LEUMFormer model constructed adopts a DecoupleNet light-weight backbone network, suppresses channel redundancy, and realizes model light-weight on the basis of precision improvement. Through the MSAF module, linear complexity is realized to enhance and extract farmland multi-scale features and direction-sensitive structures. In the decoding stage, the SCIA module is introduced, the spatial structure and spectral channel features are dynamically fused through the double-branch parallel structure and adaptive gating. In addition, the BEH module is constructed to explicitly strengthen the subtle boundary at a very low computational cost, solving the problems of segmentation blur and fracture.

The application relates to a hybrid structure remote sensing image segmentation method based on a state space model, which comprises the following steps: obtaining a remote sensing image to be processed, inputting the remote sensing image to be processed into a hybrid structure remote sensing image segmentation model, and obtaining a segmentation result; the hybrid structure remote sensing image segmentation model is obtained by training a training set, and the training set comprises remote sensing images; the hybrid structure remote sensing image segmentation model is composed of a residual network submodel based on a convolutional neural network and an improved Mamba submodel to form a double-encoder structure, is used for extracting multi-scale features, is composed of a Transformer submodel based on a hybrid attention convolution module to form a decoder, is used for capturing global-range feature dependency through the multi-scale features, extracting local features and capturing spatial information, and generating the segmentation result; wherein the improved Mamba submodel is an original Mamba submodel into which a two-dimensional selective scanning module and a CSAM attention fusion module are introduced.