234 results about "Remote sensing image processing" patented technology

The application discloses a kind of unmanned vehicle multispectral remote sensing water fine classification extraction method, it is related to remote sensing image processing technical field, the joint feature matrix including spectral feature, gray texture feature and elevation difference feature is creatively constructed in the present application, effectively eliminates redundant interference information, provides high-quality input with very distinguishing degree for multilayer perception machine model.Simultaneously, illumination geometry and digital elevation model are deeply coupled in the feature construction process, not only can accurately identify and reverse inhibit the shadow pseudo water body feature projected by complex terrain or building, break through the failure limitation of traditional single elevation filtering in flat shadow area, but also cooperate with the standardization closed operation process based on morphological dilation and corrosion filtering, eliminate the small holes and jagged artifacts in prediction result, realize the high-fidelity restoration of water body boundary, so as to improve the classification accuracy of complex water body such as narrow river, fragmented pit pond and urban waterlogging.

An optical remote sensing image processing system and training method, relating to the fields of computer vision and image processing technology, alleviates the difficulties in balancing high accuracy and high efficiency in saliency enhancement in existing optical remote sensing image processing technologies, which suffer from high computational costs, incomplete structures, and unclear boundaries. The optical remote sensing image processing system includes a basic feature extraction network module for extracting basic features from the optical remote sensing image to be enhanced; a multi-directional feature mining and aggregation module for obtaining corresponding feature map sequences based on the basic feature map sequences; a cross-scale edge information fusion module for fusing the feature map sequences through cross-scale edge scanning; and a saliency enhancement module for obtaining a refined saliency map. This invention is applicable to remote sensing and UAV image analysis. It can quickly identify salient areas on the Earth's surface, such as buildings, ships, and disaster areas.

This invention relates to the field of remote sensing image processing technology, specifically disclosing a building change detection method based on a dual-branch encoder and multi-feature fusion. By modeling the building body and edges separately, this invention elevates edge information to an equal level of importance with body information, providing a new design approach to solve the long-standing problems of boundary adhesion and ambiguity in building change detection, and facilitating the handling of irregular boundaries. A feature cross-fusion module effectively promotes the fusion of building integrity, ensuring the semantic consistency and accuracy of the results. In the decoder section, a hierarchical feature fusion noise removal module maximizes the identification and removal of abnormal image patches. This invention achieves efficient and high-precision building change detection by inputting the acquired dual-temporal remote sensing image (including the preceding and following temporal images) into the constructed building change detection model and outputting the building change detection results.

The present application provides a kind of straw coverage detection method and device of cross-scale multi-source data fusion, applied to remote sensing image processing technical field, above-mentioned method includes: the ground photograph is input to visual big model and is carried out semantic segmentation, obtains the straw coverage of corresponding ground scale range;Based on the straw coverage of ground scale range, the scale range adaptation is carried out to unmanned aerial vehicle image, and unmanned aerial vehicle sample image is obtained;Based on the image similarity calculation of unmanned aerial vehicle image block corresponding ground photograph and unmanned aerial vehicle sample image, the overall similarity of each unmanned aerial vehicle image block is obtained;Select a fixed proportion of target unmanned aerial vehicle image block to generate new sample;Based on unmanned aerial vehicle image straw coverage sample set, construct straw coverage regression model;Satellite remote sensing image is input to straw coverage regression model, and the straw coverage extraction result of target area is obtained;Through the present application, the straw coverage of large area range can be realized accurate extraction.

This invention proposes a method for correcting abnormally high values ​​in remote sensing satellite nighttime light imagery, belonging to the field of remote sensing image processing technology. Addressing the problem of low accuracy in existing nighttime light image correction techniques, this invention acquires remote sensing satellite nighttime light imagery and preprocesses it; acquires target area boundary data and adjusts the preprocessed light imagery; statistically analyzes all light values ​​in the adjusted light imagery to identify abnormal light value intervals; performs isolated analysis on the light values ​​within the abnormal intervals to determine abnormally high values; classifies the abnormally high values ​​into at least one distribution combination based on their distribution pattern; uses a local mean fitting method to calculate correction values ​​based on the normal light values ​​surrounding the abnormally high values; and replaces each abnormally high value with its corresponding correction value to generate a corrected nighttime light image of the target area. This invention achieves high accuracy in nighttime light image correction.

The present application relates to the technical field of remote sensing image processing and artificial intelligence, in particular to a state space model driven remote sensing image change caption generation method, the method comprises the following steps: obtaining image data and word mapping table of remote sensing image intelligent interpretation; extracting double time phase features through a double time sharing branch feature extractor; constructing a joint input sequence of a decoder according to the difference enhanced features, multi-scale visual features and text sequences; taking the constructed joint input sequence as input, calculating word probability distribution by autoregressive calculation based on a pre-trained language model decoder, completing prediction and cyclic iteration according to the word mapping table, and obtaining complete image change description sentences; the present application solves the problem of losing high frequency details in long sequence modeling of state space model through frequency domain modulation, and effectively suppresses background noise interference by using difference perception aggregation, thereby improving the accuracy of remote sensing image difference description generation.

The application provides a building label alignment method, device, equipment, storage medium and program product, and relates to the technical field of remote sensing image processing. The method comprises the following steps: obtaining a remote sensing image and a label to be aligned; inputting the remote sensing image and the label to be aligned into a pre-trained label alignment model, performing multi-step iterative reasoning, and obtaining target base position labeling and target roof position labeling output by the label alignment model; the label alignment model is obtained by performing noise training on an initial model based on a sample remote sensing image, a sample building label corresponding to the sample remote sensing image, and a sample correction vector corresponding to the sample building label. Through the above method, the model has good label correction capability and noise removal capability, effectively improves the accuracy of label alignment, and is more suitable for actual remote sensing image application scenarios.

This invention discloses a method and network model for reconstructing missing soil moisture data based on cross-attention, belonging to the fields of remote sensing image processing and artificial intelligence. It involves collecting SMAP, ERA5-Land soil moisture products, and various auxiliary prediction factor data. The auxiliary data is resampled to 9km and preprocessed using multi-source data. A CASTNet model is then constructed. After inputting the preprocessed data into the model, feature extraction, refinement, and enhancement are sequentially performed through modules for spatiotemporal automatic completion, multi-factor feature refinement, and multi-scale attention enhancement. Finally, the model is trained based on a combined loss function composed of global and local losses, and the trained model is used to fill in the missing areas of soil moisture remote sensing data. The CASTNet model contains three cascaded core modules, each implementing preliminary spatiotemporal feature completion, multi-factor feature fusion refinement, and multi-scale feature enhancement, respectively. This invention fully leverages the complementary information of multi-source data, improving the accuracy of soil moisture data reconstruction and ensuring the spatiotemporal continuity and integrity of the reconstructed data.

The application discloses a remote sensing change detection method based on a teacher-student framework and multi-space distillation, relates to the technical field of remote sensing image processing, and comprises the following steps: constructing a text prototype library and a visual prototype library; performing zero sample prediction on an image to be detected to generate text guided features; extracting multi-scale feature maps, global semantic features and spatial level features by a student network; calculating absolute differences, similarity differences and text guided differences to splice initial change features; respectively calculating channel attention and spatial attention of the initial change features to fuse multi-scale fusion features to splice spliced features; and inputting the decoder to obtain a binary change detection map. The method effectively improves the precision of remote sensing image change detection and provides important technical support for the application in the fields of city planning and environment monitoring.

This invention belongs to the field of remote sensing image processing technology and discloses a method and system for spatiotemporal fusion of remote sensing images. This method introduces Mamba modules in both the spatial and frequency domains to enhance the extraction and modeling capabilities of multi-scale features and structural information. In the spatial domain, the Mamba module is used to capture the local structure and geometric details of the image; in the frequency domain, the Mamba module is introduced for feature extraction of the high-frequency subbands after wavelet transform, thereby more fully exploring the contextual dependencies and structural features of high-frequency information. Through channel attention and spatial attention mechanisms, dual-domain interactive fusion is achieved, improving the spatial clarity and spectral consistency of the fused image. It possesses strong generalization and adaptability, fully utilizing information from both the spatial and frequency domains, and improving the accuracy and efficiency of acquiring remote sensing images.

The application belongs to the technical field of remote sensing image processing and deep learning, and relates to a space-frequency domain neural network remote sensing image semantic segmentation method based on Mamba. The method introduces a space domain and frequency domain dual domain attention module, respectively uses a linear attention mechanism for space domain feature representation and an attention mechanism for frequency domain representation; a boundary perception head is designed to enhance the boundary representation with graphic information features in the feature extraction stage, and the perception ability of the model to the boundary is improved; and a supervised contrast learning strategy is combined to enhance the aggregation ability of semantic information in the feature representation in the decoder stage. Through the synergistic effect of the above modules, the application effectively overcomes the problems of single optimization method and fuzzy boundary segmentation of the existing Mamba model without modifying the hardware optimization code and increasing the model parameter quantity, and significantly improves the segmentation accuracy and running efficiency of the remote sensing image semantic segmentation model.

The application discloses a kind of diffusion prior-based adversarial generative remote sensing image super-resolution method, belong to remote sensing image processing technical field.The application divides super-resolution reconstruction into two independent stages of degradation removal and information regeneration: first, through degradation removal network, low-resolution remote sensing image is executed to carry out degradation suppression processing such as denoising, deblurring, artifact suppression, eliminate the content-independent degradation interference caused by imaging and transmission;Again, the degraded removal image is input into the generation network to realize high-resolution information regeneration, the generation network is initialized using the pre-trained diffusion model parameters to have the prior distribution characteristics of remote sensing image, and the content consistency and detail authenticity of the generated image are ensured by combining the adversarial optimization of the discriminant network and the pixel-sensing joint fidelity constraint in the training stage;Inference stage only needs one forward mapping to output high-resolution results, while supporting visual language model semantic text condition guidance, to realize controllable adjustment of generation results.

The invention discloses a farmland tree remote sensing image optimization method, relates to the technical field of remote sensing image processing, and solves the problems that in an existing optical image processing technology, a data processing flow is too complex in an optical image processing process, and wrong division and missing division are likely to occur, so that farmland tree images in optical images are not clear, and the image quality is poor. Therefore, the application of optical images in agricultural operation activities is restricted. A farmland tree remote sensing image optimization method comprises a data acquisition stage, a vegetation and non-vegetation distinguishing stage, a vegetation type distinguishing stage, a farmland tree and non-farmland tree distinguishing stage and a farmland tree remote sensing image optimization stage. The method is suitable for the fields of farmland tree remote sensing monitoring, ecology, remote sensing technology, geographic information systems and the like.

This invention discloses a semi-supervised remote sensing image feature extraction method, device, and readable medium based on visual distillation, belonging to the field of remote sensing image processing technology. The method includes the following steps: S1, dataset construction and preprocessing; S2, semi-supervised segmentation model initialization; S3, pseudo-label generation; S4, visual distillation and feature extraction; S5, feature optimization; S6, joint model training and inference. This invention, employing the aforementioned semi-supervised remote sensing image feature extraction method, device, and readable medium based on visual distillation, significantly improves the integrity, continuity, and accuracy of remote sensing image feature segmentation using only a small amount of labeled data, while reducing the model's dependence on large-scale labeled samples.

The application discloses a hydrological remote sensing image target recognition method based on a deep semantic model, relates to the technical field of remote sensing image processing, and comprises the following steps: obtaining a primary semantic code of a hydrological remote sensing image through a deep semantic network, calculating a semantic attribution probability distribution according to the primary semantic code, generating an initial attention guide signal, dynamically adjusting the weight of a specific perception path in the network, realizing first feature re-extraction to obtain refined features, calculating a feature compensation vector based on the confidence deviation generated by matching the features with a standard feature library, correcting the refined features to obtain enhanced features, and inputting the enhanced features into the network again for analysis to obtain a final recognition result. Through the attention adjustment of the semantic guide and the feature compensation based on the confidence feedback, the method effectively improves the recognition accuracy of complex hydrological ground object targets and the model robustness.

This application belongs to the interdisciplinary field of satellite remote sensing and artificial intelligence technologies, and provides a satellite remote sensing image processing method and system. Based on satellite-ground collaboration, after the ground system completes the construction of the training dataset and the initial fine-tuning of the model, the satellite system optimizes and deploys the fine-tuned multimodal large model on the satellite computing platform, sequentially performing image acquisition, preprocessing, ground feature identification, and data filtering and downlink. Incremental model updates are then achieved through satellite-ground data interaction. This application improves processing efficiency, accuracy, and stability, and can be widely applied to satellite remote sensing scenarios such as disaster monitoring, agricultural yield estimation, and land surveys.

The application discloses a remote sensing image change detection method, system, device, medium and product based on a multi-task deep learning network model, relates to the field of remote sensing image processing, and comprises the following steps: acquiring double-time multi-source space data of a target area; the double-time multi-source space data comprises double-time optical images, double-time SAR images and a double-time digital elevation model; dividing the target area into multiple height levels according to the double-time digital elevation model and generating a height coding map; based on the double-time multi-source space data and the height coding map, a pre-trained multi-task deep learning network model is used to output a change detection map, a change type map and a height change map, so that remote sensing image change detection is realized; the multi-task deep learning network model comprises an encoder, an alignment and fusion module, a four-dimensional neighborhood difference convolution module and a stereo gradient enhancement decoder. The application can realize high-precision and quantifiable remote sensing image change detection in a stereo scene.

This application belongs to the field of large-scale model cross-protocol conversion technology, specifically involving a method and system for intelligent extraction and cross-protocol conversion of ultra-large remote sensing images. The method includes the following steps: S1. Standardized interception and preprocessing of heterogeneous requests from different clients; S2. Establishment of a single-request channel based on dynamic client instances; S3. Bidirectional protocol reconstruction and streaming data translation of heterogeneous large models; S4. End-to-end monitoring and resource recovery; S5. Intelligent dynamic tiling and spatiotemporal context reorganization for ultra-large remote sensing images. This application constructs an intelligent protocol identification and conversion mechanism that automatically identifies the original protocol format and maps it uniformly to the target model protocol for ultra-large remote sensing image processing requests initiated by different clients. Throughout the conversion chain, the system ensures the preservation and consistency of the input original image logic and the output parsed result format, improving the compatibility, flexibility, and scalability of intelligent mapping systems when processing ultra-large-scale remote sensing data.

This invention discloses a method and apparatus for estimating the height of monocular remote sensing images based on semantic distribution and region modulation, belonging to the field of computer vision and remote sensing image processing technology. The method first obtains a multi-scale feature map through bidirectional multi-scale feature extraction; then, it uses a height interval semantic modeling module to introduce global height semantic information to modulate the height interval representation, obtaining a preliminary height prediction; finally, it employs a region-aware pixel-level height modulation module to explicitly model the height region to which a pixel belongs and generate modulation parameters, performing differential correction on the preliminary prediction. This invention can significantly improve the accuracy, spatial consistency, and robustness of building height estimation, and is suitable for applications such as urban modeling and remote sensing mapping.

This invention discloses a YOLO-based remote sensing image detection method for river anomalies, belonging to the field of remote sensing image processing technology. This scheme utilizes a YOLO network optimized with a multi-task loss function to achieve high-precision comprehensive identification of various river anomalies, such as personnel, shoreline garbage, and water pollution, greatly enriching the dimensions of intelligent water environment monitoring. Furthermore, after capturing polluted water areas, this invention creatively introduces a topological anchoring mechanism combining concentration gradient inverse estimation with semantic maps of shoreline physical materials. This not only accurately extracts physical vector trajectories pointing to the source along the gradient direction of water color, but also, by assigning differentiated probability weights to different shoreline materials for hidden sewage outlets, and combining this with a distance decay mapping algorithm, accurately maps and locks the final predicted sewage outlet coordinates to the shoreline material where pipelines are most easily hidden according to physical principles, breaking through the blind spots of traditional visual algorithms that easily violate physical principles.

The application belongs to the technical field of deep learning and remote sensing image processing, and specifically discloses a city land use mapping method based on multi-modal data collaborative perception, which comprises the following steps: performing parcel division on high-resolution remote sensing images of a research area to obtain irregular city parcels and remote sensing spectral features thereof; setting street sampling points along a road network, extracting street perception features and extracting interest point semantic features; constructing a heterogeneous graph structure based on the street sampling points, the street perception features and the interest point semantic features falling into the same parcel, and then extracting parcel-level multi-source geographic features; inputting the remote sensing spectral features and the parcel-level multi-source geographic features into a full sparse topic model for semantic alignment and fusion to generate fused parcel feature representations; and performing classification based on the fused parcel feature representations to output city land use mapping results. The application can realize high-precision and high-robustness city land use recognition under the condition that multi-source data is unevenly distributed or sparse.

The application discloses an image generation method based on a diffusion model, and relates to the field of computer vision and remote sensing image processing. Through a direction and size perception attention mechanism, the application realizes the cooperative and accurate control of the target position, direction and size in remote sensing image generation, and the geometric consistency of the generated image and the input layout is significantly improved. Based on a complete layout rebalancing, conditional generation and quality screening process, the application can automatically and high-quality synthesize a data set, and the accuracy of a downstream rotating target detector is obviously improved on multiple benchmark data sets, effectively solving the problems of data scarcity, uneven distribution and high labeling cost in remote sensing detection tasks, and providing reliable data support for remote sensing target detection tasks. The method can be used for generating synthetic remote sensing data sets with consistent layout and accurate geometric properties, and is especially suitable for generating remote sensing target detection training data containing various orientations and sizes.

The application discloses a hyperspectral and LiDAR data fusion vegetation stress grade evaluation method and system, a storage medium and a product, belongs to the technical field of remote sensing image processing and ecological environment monitoring, solves the problem that vegetation stress grade evaluation only depends on hyperspectral data, is easily interfered by terrain shadow and mixed pixels, and leads to misjudgment; only depends on LiDAR data, although three-dimensional structure information can be obtained, but the stress type cannot be identified. The application comprises obtaining multi-source data of a target region in vegetation and registration, wherein the multi-source data comprises hyperspectral images and LiDAR point cloud data; LiDAR feature maps and hyperspectral feature maps are extracted by using a double-branch encoder network after the registered multi-source data, and are aligned; the LiDAR feature maps and the hyperspectral feature maps are subjected to feature fusion through a terrain-gated feature interaction mechanism, and fusion features are obtained; a trained prediction network of multi-task learning is used to predict the fusion features, and the stress grade of each pixel is output. The application is used for vegetation stress grade evaluation.

This invention relates to a spatiotemporal fusion method for remote sensing images based on physical mechanism guidance and structure-texture guided masks, belonging to the field of remote sensing image processing technology. This method addresses the problems of infrared band prediction distortion, blurred boundaries of changing regions, and imbalance between local and global features in existing deep learning fusion methods. It decouples spectral features through physical block coding and enhances band differentiation using coordinate spectral attention. A structure-texture guided mask is used to affinely modulate low-resolution changing features to inject high-resolution texture, and selective pixel attention is combined to achieve multi-scale adaptive fusion. This invention significantly improves spectral fidelity, eliminates ghosting artifacts, balances detail and global consistency, and outperforms existing technologies in metrics such as RMSE and PSNR.

The application discloses a mangrove remote sensing image processing method based on a UAV, and belongs to the technical field of mangrove processing, and comprises the following steps: S1, a hyperspectral remote sensing image of a target mangrove area is shot by using a UAV; S2, spectrum processing and optimized inversion are performed on the hyperspectral remote sensing image, so that a corrected hyperspectral remote sensing image is obtained; and S3, feature extraction and feature enhancement are performed on the corrected hyperspectral remote sensing image, so that the probability that each pixel belongs to the mangrove is obtained, and a final mangrove area is determined. The application solves the problem of recognition difficulty caused by the large crown scale difference of the mangrove, improves the edge precision of a segmentation result, and makes the contour of the mangrove clearer and more accurate.

The application discloses a large-scale remote sensing image color correction method based on block local histogram matching, belongs to the technical field of remote sensing image processing, and aims at the problems of low calculation efficiency, neglect of local features and difficulty in maintaining overall color tone when existing methods process large-scale orthographic images. The correction is realized through five steps of adaptive image blocking, multi-scale statistical feature extraction, hierarchical nonlinear mapping model, high-precision seamless splicing and parallel computing framework optimization. The method can efficiently process massive data, takes into account local correction accuracy and overall color tone consistency, improves robustness through intelligent parameter adaptive adjustment, significantly eliminates image color differences, is suitable for multiple fields such as land resource investigation and city planning, and provides a high-quality solution for large-scale image splicing.

This invention provides a system and method for detecting rotating targets in remote sensing images, belonging to the field of remote sensing image processing technology. The detection system includes: a first construction module for constructing a feature extraction and fusion network; a second construction module for constructing a detection network; a third construction module for constructing a new YOLOv5 model; an acquisition module for acquiring a set of remote sensing images; a training module for training the new YOLOv5 model; a rotating target detection module for performing rotating target detection using the new YOLOv5 model to determine the labeling information of all predicted bounding boxes for each target category; and a post-processing module for deduplicating all predicted bounding boxes, determining the optimal predicted bounding box for each target category, and labeling it. This invention can quickly and accurately detect targets of different sizes and orientations in remote sensing image scenes, which is beneficial for subsequent data statistics and other work.

The present application relates to the technical field of remote sensing image processing, and particularly relates to a water body geomorphology extraction method, comprising the following steps: S1, obtaining remote sensing images for a target area and generating a pretreatment image; S2, extracting pixel reflectivity of a plurality of ground objects in each spectral band from the pretreatment image; S3, generating an extraction model according to all the ground object pixel reflectivity; and S4, generating an extraction image for labeling water body geomorphology by using the extraction model. The present application has the beneficial effect that the extraction model is set, the water body index model used in the prior art is optimized, so that water body and other easily confused ground objects such as shadows can be better separated in the process of extracting water body geomorphology, and the phenomenon of "pepper and salt" and other problems caused by extracting water body by threshold value only in the prior art is further avoided by using an object-oriented segmentation method, the process of water body extraction is simplified, and the water body extraction precision is improved.