1003 results about "Remote sensing image processing" patented technology

The invention relates to the field of remote sensing image processing, in particular to a high-resolution remote sensing image semantic segmentation method based on multi-scale feature fusion, which comprises the following steps: acquiring a public remote sensing image data set, preprocessing the image, and constructing a training and testing set of semantic segmentation; a CTMFNet is designed, an encoder is composed of a lightweight residual module and an MS-Transform, and local space details and global context information are extracted; rID is adopted to reduce spatial information loss, LSFE is introduced to improve spatial positioning capability, and feature calibration is carried out in space and channel dimensions through DecoderAttn to realize boundary fine segmentation; inputting the training sample into the network for training to obtain a converged optimal semantic segmentation model; and inputting the test set into the model to obtain a semantic prediction map, and outputting a fine segmentation result of the remote sensing image through multi-scale fusion and boundary restoration. According to the method, the precision and robustness of ground feature extraction are effectively improved, the calculation cost is remarkably reduced while high segmentation precision is kept, and the method has good practical value and popularization prospects.

The invention discloses a remote sensing image cultivated land segmentation method and system fusing context and boundary perception, and belongs to the technical field of remote sensing image processing and agricultural information. Constructing a cultivated land segmentation initial model composed of a backbone network, a feature enhancement module, a multi-scale feature fusion de-wharf module and a mask prediction module; training set data are input into the initial model, a composite loss function value is calculated, back propagation is executed, and a cultivated land segmentation model with boundary sensing ability is obtained through multi-round iterative optimization; and inputting the remote sensing image into the trained cultivated land segmentation model, and outputting a binary segmentation image representing the cultivated land position. Visual state space modeling and large receptive field convolution are combined, deep and shallow layer information is fused through feature injection, boundary perception supervision and composite loss are introduced, cultivated land boundary discrimination is improved, remote sensing image cultivated land high-precision extraction is achieved, and the method is suitable for agricultural interpretation and monitoring.

The invention provides a crop planting area intelligent extraction method and system based on multispectral remote sensing, and relates to the field of remote sensing image processing, and the method comprises the steps: obtaining and correcting a multiband remote sensing image; calculating a vegetation index and constructing a crop growth characterization index to extract canopy features; obtaining a multi-period feature map, calculating a spatial distribution entropy, and establishing an evaluation function to determine a time sequence fusion weight; a spatial constraint function is established based on the spectral distance, and a segmentation criterion is constructed by combining the spatial constraint function with time sequence features for classification iteration. According to the method, the accuracy and the discrimination degree of crop planting area extraction are improved, and crop identification requirements in a complex agricultural environment are met.

The invention relates to the technical field of remote sensing image processing, and discloses a remote sensing image adaptive identification method and system for territorial space planning, and the method comprises the steps: obtaining a multi-source remote sensing image data set of a research region, feature extraction, cloud detection, quality evaluation and adaptive preprocessing are carried out; carrying out prototype network coding, calculating a category prototype and probability, and supporting fine tuning of a set; carrying out multi-scale cavity convolution and category scale attention fusion; evaluating the adaptability score of the comprehensive fusion feature map set, and carrying out weighted fusion, classification and normalization; change detection is carried out, stable and change regions are segmented, and time sequence context features are extracted and constrained optimization is carried out; entropy is fused, a boundary is decided, uncertainty is estimated, and weighted fusion is carried out according to a change area; conditional random field optimization, confidence level grading and connected domain identification are carried out; the automation level, the adaptive capacity and the recognition reliability of remote sensing monitoring of territorial space planning are improved.

The invention relates to the technical field of artificial intelligence and remote sensing image processing, and particularly provides a hyperspectral image and laser radar data classification method based on a dynamic fusion network. The method comprises the following steps: preprocessing acquired multi-modal data, and constructing multi-scale input; a dual-scale local attention module is designed, and context information of different scales is fused in a self-adaptive weighted mode through gating soft pooling; a dynamic down-sampling feature enhancement module is designed, the down-sampling rate is dynamically adjusted according to the complexity of the feature map, and deep multi-scale interaction is carried out based on a Mama backbone; constructing a directional interactive attention module, extracting features in horizontal, vertical and diagonal directions through directional gating convolution, and capturing an anisotropic structure of a linear ground feature; through the design of a double-path classifier, fusing shallow space details and deep semantic information; and the model is trained, optimized and reasoned to obtain data classification, and the method improves the classification precision and the calculation efficiency.

The invention discloses an ecological environment detection method and system based on multispectral remote sensing fusion, and relates to remote sensing image processing. The method comprises the following steps: collecting multispectral remote sensing image data of a target area; performing multiband joint atmospheric correction processing on the multispectral remote sensing image according to the scattering coefficient, the atmospheric light value and the transmissivity of each band; performing foreground and background analysis on the corrected multispectral remote sensing image; fusing the vegetation area and the non-vegetation area of each wave band image by adopting different weight strategies to generate a multispectral fusion image; and extracting spectral features of the multispectral fusion image, constructing a standard vegetation spectral feature library, and identifying regions deviating from a standard vegetation spectrum through an anomaly detection algorithm according to the extracted spectral features to obtain various vegetation coverage rates. In view of low vegetation identification precision caused by direct foreground and background division of a multispectral remote sensing image under an atmospheric interference condition, vegetation division is performed after a clear image is obtained, so that the detection precision is improved.

The invention discloses a remote sensing video segmentation method and segmentation system based on text guidance, belongs to the crossing field of remote sensing image processing and computer vision, and relates to a remote sensing video segmentation method and segmentation system. The invention aims to solve the problems that the existing remote sensing video segmentation technology is poor in flexibility, cannot interact with natural languages, is insufficient in generalization ability for new categories or complex targets, and cannot meet the requirement of quickly and accurately extracting semantic information in a dynamic remote sensing scene. The method comprises the following steps: 1, acquiring a video frame sequence, and acquiring a key frame based on the video frame sequence; 2, obtaining an initial segmentation mask; 3, obtaining an optimized mask; 4, calculating a minimum bounding rectangle of the optimized mask, obtaining a bounding box of the minimum bounding rectangle, and obtaining an expanded bounding box; and 5, inputting the expanded bounding box and the video frame sequence obtained in the step 1 into an improved SAM2 video segmentation model, and outputting a frame-by-frame segmentation result of the region of interest by the improved SAM2 video segmentation model.

The invention relates to the technical field of radar remote sensing image processing, in particular to a multi-scale synthetic aperture radar flood detection method and device, and the method comprises the steps: collecting a plurality of flood disaster SAR images of a flood region, and carrying out the preprocessing of the images, so as to obtain a standard flood disaster SAR image; dividing standard flood disaster SAR images, and constructing training, verification and test data sets; based on a multi-scale feature extraction network and a multi-head self-attention mechanism, constructing a multi-scale SAR flood detection network model, training the multi-scale SAR flood detection network model by using the training data set and the verification data set, and inputting the test data set into the trained multi-scale SAR flood detection network model, therefore, the influence of speckle noise is effectively suppressed, the capability of distinguishing flood from confusion-prone ground features in a complex scene is improved, and the accuracy and robustness of SAR image flood detection are improved.

The invention relates to the technical field of image processing, and discloses an infrared image enhancement method and system based on local phase correlation, and the method comprises the steps: obtaining a plurality of continuous frames of infrared images, carrying out the intelligent partitioning of a reference frame, and calculating the variance feature, the method comprises the following steps: selecting regions of interest with rich information, independently executing phase correlation operation in each region to extract a local translation vector, obtaining global displacement estimation through weighted fusion, adopting an abnormal value detection algorithm to improve robustness, and finally realizing sub-pixel-level image alignment and intelligent weighted fusion. The method is suitable for real-time enhancement processing of satellite-borne infrared remote sensing images, the resource constraint requirement of an embedded platform is met while the processing quality is guaranteed, and an efficient and reliable technical scheme is provided for space remote sensing image processing.

The invention discloses a remote sensing image semantic segmentation method and system based on a dynamic attention mechanism, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: carrying out the labeling and enhancement processing of a multi-scene remote sensing image, and generating a standardized data set; processing the data set through an encoder, and extracting a multi-scale high-dimensional feature map; decoding the multi-scale high-dimensional feature map, and fusing a decoding result with scale features to generate an optimized feature map; based on the optimized feature map, adopting a joint loss function to synchronously optimize segmentation, detection and classification tasks; performing dynamic up-sampling and boundary refinement on the optimized feature map, and outputting a structured analysis result; according to the method, the boundary information of the ground objects in the remote sensing image is accurately extracted through a dynamic processing flow and introduction of a double-flow decoder network and a multi-task joint optimization strategy, accurate segmentation and classification of the ground objects in a complex scene are achieved, and the overall effect of analysis and processing of the remote sensing image is improved.

The invention discloses a remote sensing image segmentation method based on global feature enhancement and Fourier detail adjustment, and belongs to the technical field of remote sensing image processing. The method comprises the following steps: constructing an image segmentation model comprising a wavelet-Mama global feature enhancement module, a fast Fourier detail adjustment unit and a decoding and segmentation prediction module; performing remote sensing image segmentation training on the built image segmentation model; and performing image segmentation on the target remote sensing image by using the trained image segmentation model. According to the invention, through the wavelet-Mama global feature enhancement module and the fast Fourier detail adjustment unit, the expression ability of surface feature structures, textures and edge information in remote sensing images can be effectively improved, and high-precision segmentation of small targets and fuzzy boundaries in complex scenes is realized. The method is especially suitable for accurate recognition of buildings, roads, water bodies and other targets under high-resolution remote sensing images, and has high practical value and popularization prospects.

The invention discloses an agricultural land utilization monitoring management system and method based on remote sensing, and belongs to the technical field of remote sensing image processing. Multi-temporal remote sensing images are acquired, and a land surface energy fluctuation spectrogram is constructed; extracting disturbance characteristics through small-scale grid slices to form a multi-dimensional disturbance characteristic tensor; identifying an abnormal evolution region by using a sparse volume accumulation algorithm, and outputting a preliminary screening identification graph; inputting the region with the continuous evolution characteristic into a time sequence attention mechanism inversion network, estimating a crop growth state trajectory, matching an agricultural planting mode library, and generating a candidate land utilization behavior probability distribution diagram; in combination with regional consistency optimization, a historical planting period and meteorological disturbance data, calculating a purpose change confidence score, and outputting early warning information and a monitoring report; the agricultural land dynamic change identification precision and management capability can be effectively improved.

The invention discloses a self-supervised hyperspectral image classification method suitable for a low-annotation sample scene, and relates to the technical field of hyperspectral remote sensing image processing, comprising a self-supervised category sensing network oriented to the low-annotation scene; in the pre-training stage, a grouping spectrum enhancement module, a spectrum self-attention module and mask reconstruction are adopted, and the model is guided to focus on category-sensitive space-spectrum features under the label-free condition by minimizing the difference between a reconstructed image and an original shielded area; in the fine tuning stage, pre-trained network parameters are used as initialization parameters, and feature expression is further refined through classification loss. Therefore, by adopting the self-supervised hyperspectral image classification method suitable for the low-label sample scene, the lossless transmission of difficult sample features is realized, the distinguishing feature expression of mixed pixels is enhanced, and the classification balance of few sample categories is improved.

The invention provides an infrared small target detection method and system based on depth-guided low-rank sparse decomposition, and relates to the technical field of remote sensing image processing, and the method comprises the steps: obtaining all original infrared images shot by remote sensing equipment, and sequentially stacking the original infrared images according to an obtaining time sequence, and obtaining an infrared original tensor; performing low-rank background and sparse target decomposition processing based on the infrared original tensor to obtain a low-rank sparse tensor decomposition model; a low-rank background tensor containing nonlinear transformation is obtained through processing of a constructed hierarchical nonlinear tensor ring background module; processing through a sparse target module fused with an attention mechanism to obtain a sparse feature tensor of the infrared small target area; and reconstructing a low-rank sparse tensor decomposition model guided by the deep neural network, and carrying out solving processing to obtain a final infrared small target detection result. According to the invention, accurate, robust and rapid detection can be carried out on a small target under a complex background.

The invention relates to the technical field of remote sensing image processing, in particular to a multi-modal target detection method and device based on attention self-modulation fusion, and the method comprises the steps: extracting visible light modal shallow layer features of a visible light modal image, and extracting infrared modal shallow layer features of an infrared modal image; carrying out fusion processing on the visible light modal shallow layer features and the infrared modal shallow layer features to obtain target fusion features, and carrying out feature extraction to obtain deep semantic features; and performing multi-scale feature aggregation on the deep semantic feature, performing feature enhancement on a feature aggregation result based on a preset feature enhancement mechanism to obtain a multi-scale fusion feature, and detecting the multi-scale fusion feature to obtain a detection result. Therefore, the problems of high calculation cost and high model complexity of multi-modal target detection in the background technology are solved, and efficient and lightweight multi-modal target detection is realized.

The invention discloses a remote sensing image space-time fusion method and device based on a selective state space model, and belongs to the technical field of remote sensing image processing and computer vision crossing. The method comprises the following steps: acquiring high-resolution and low-resolution image input, and extracting multi-scale features through a multi-layer encoder; capturing an anisotropic space structure in the remote sensing image by using a four-way two-dimensional selective scanning mechanism; designing a state space fusion module, decoupling and cooperatively processing space details and time dynamic information through a space and time sequence selective scanning fusion sub-module, and performing feature fusion by adopting adaptive gating parameters; and finally, reconstructing a high-resolution image through a symmetric decoder, and carrying out model optimization by adopting a composite loss function. On the premise of ensuring the linear calculation complexity, the spatial detail fidelity, the time continuity and the overall efficiency of the fused image are remarkably improved, and the method is suitable for large-scale remote sensing data processing.

The invention relates to the field of remote sensing image processing, and provides a remote sensing image terrain radiation correction method, device and equipment, and the method comprises the steps: obtaining a to-be-corrected remote sensing image, calculating the terrain parameter of each pixel, dividing the to-be-corrected remote sensing image into a shadow region and a non-shadow region, and determining the direction weighting function of each pixel; calculating a topographic modulation spherical harmonic primary function corresponding to each pixel; training samples are selected in the shadow area and the non-shadow area respectively, a linear model is constructed, and spherical harmonic illumination coefficients representing overall three-dimensional illumination distribution of the shadow area and the non-shadow area are solved; and based on the topographic modulation spherical harmonic primary function, combining the spherical harmonic illumination coefficient corresponding to the area to which each pixel belongs, reconstructing the average incident radiance of each pixel, and then performing inversion to obtain the real reflectivity of the earth surface. According to the method, the problem of inaccurate radiation distortion correction of the remote sensing image under the complex terrain in the prior art is solved, and accurate inversion of the real reflectivity of the earth surface is realized.

The invention relates to a rice identification method based on optical and SAR image fusion, and belongs to the technical field of remote sensing image processing. The method comprises the following steps: synchronously acquiring SAR and optical time sequence data, respectively preprocessing the SAR and optical time sequence data, and extracting characteristic parameters; the method comprises the following steps: constructing a double-flow Vision Transform model, wherein the double-flow Vision Transform model comprises a double-branch feature extraction module, a space-time Transform aggregation module, a gating feature fusion module and a decoder; the double-branch feature extraction module extracts SAR and optical features according to the SAR and optical feature parameters; inputting the extracted SAR features and optical features into a space-time Transform aggregation module, and carrying out time sequence dependence modeling through a self-attention mechanism; the gating feature fusion module performs weighted fusion on the optical and SAR features; and the decoder generates a rice distribution probability graph according to a weighted fusion result. According to the method, the rice identification precision under the multi-temporal and multi-environment conditions can be improved.

The invention relates to the technical field of remote sensing image processing, and provides a remote sensing multi-modal target detection method and device for gated cross attention fusion, and the method comprises the steps: obtaining a multi-modal remote sensing image pair; and inputting the multi-modal remote sensing image pair into the target detection network model, and outputting a target detection result. According to the remote sensing multi-mode target detection method based on gating cross attention fusion, firstly, the edge information of each mode is explicitly enhanced, then, the information interaction and reconstruction between the two modes are realized by using a bidirectional cross attention mechanism, a key region can be adaptively highlighted, redundant or noise characteristics can be inhibited, and the detection accuracy is improved. The reconstructed visible light feature map and invisible light feature map not only maintain respective modal advantages but also have complementarity, dynamic weighted fusion is performed on different modal features through a gating weighted fusion mechanism, target discrimination features in the multi-modal fusion feature map are highlighted, accurate and stable target detection is realized, and the target detection accuracy is improved. And the advantages of the multi-modal image can be fully played in a complex scene.

The invention belongs to the technical field of remote sensing image processing. The invention provides a multi-source remote sensing image class incremental learning method based on prompt fine tuning. According to the embodiment of the invention, a mode-specific prompt pool is constructed, an instance-based prompt query mechanism is designed, and proper prompts are dynamically selected for different input characteristics; a learnable modal sharing global prompt is added to each attention layer of the frozen Vision Transform network, and modal public information specific to a task is extracted; carrying out cross-modal prompt conversion and fusion; freezing a part of the modal mapping network to reserve a modal conversion relation of the old task; establishing a prompt-guided knowledge aggregator module, freezing a knowledge aggregation token in an old task network, and jointly guiding the knowledge aggregation token, a knowledge aggregation token of a new task and a modal specific prompt to guide the aggregator module to learn image features; and training the established incremental learning network model.

The invention discloses a causal reasoning-based satellite-ground collaborative remote sensing image interpretation method and device, relates to the technical field of remote sensing image processing, and mainly aims to solve the problem that the inference requirement of environmental causes in a remote sensing image cannot be met in the prior art. Comprising the following steps: a ground end obtains initial interpretation features obtained by performing initial interpretation on multi-modal remote sensing data by a satellite-borne end, and interprets the initial interpretation features based on a first interpretation model of which model training is completed to obtain core interpretation features; determining causal variables based on the core interpretation features, and constructing a causal variable graph based on the causal variables; determining a cause label and an interpretation result of the label area according to the causal variable graph, and obtaining a verification result corresponding to the cause label and the interpretation result; and based on the knowledge distillation and the verification result, determining learning core features of the first interpretation model for updating training, so that a second interpretation model in the satellite-borne end coordinates the learning core features fed back based on the ground end.

The invention discloses a remote sensing image three-dimensional reconstruction method based on semantic information, and relates to the technical field of remote sensing image three-dimensional modeling, and the method comprises the steps: carrying out the processing of a remote sensing image covering a target region, obtaining point cloud data, and carrying out the semantic segmentation based on a semantic segmentation model, and determining a semantic category label; dividing voxel units based on a three-dimensional sparse point cloud distribution condition, and constructing to obtain an initial anchor point; the distribution density of the initial anchor points is adjusted in combination with the semantic category labels, and the adjusted initial anchor points are obtained; iteratively training the three-dimensional Gaussian splash model for multiple times to update the anchor points to obtain scene anchor points; and obtaining a three-dimensional reconstruction model of the target area based on scene anchor point rendering. According to the method, semantic information is introduced and a 3DGS three-dimensional modeling technology is fused, so that the densification quality of anchor points and the geometric boundary definition of the model are effectively improved, the modeling efficiency can be improved, and the structural rationality and semantic interpretation of a three-dimensional reconstruction result can be enhanced.

The invention relates to the technical field of remote sensing image processing, and discloses a remote sensing image semantic segmentation method fusing frequency domain modeling and lightweight linear attention, comprising the following steps: extracting basic spatial texture and edge features of a remote sensing image through an initial convolutional layer to obtain an initial feature map; performing layer-by-layer down-sampling on the initial feature map to obtain multi-scale features; inputting the multi-scale features into a multi-scale frequency domain enhanced lightweight linear attention unit, and outputting the enhanced multi-scale features through the synergistic effect of frequency domain significance guidance and spatial multi-scale modeling; sequentially performing up-sampling on the enhanced multi-scale features from the highest-layer features, and adding and fusing the multi-scale features with the enhanced features of the corresponding layers to obtain a fused high-resolution feature mapping feature map; and performing classification prediction mapping on the fused high-resolution feature mapping feature map to obtain a semantic segmentation map. By introducing a frequency domain enhancement mechanism and a lightweight linear attention structure, the segmentation accuracy of the model on complex ground features is remarkably improved.

The invention provides a building LOD2 model diffusion generation method and system based on multi-modal feature constraints, and belongs to the field of remote sensing image processing. According to the method, a three-dimensional polygon noise generation module MM2P-Init and a multi-modal feature constraint module MM2D-Control are mainly utilized to construct a diffusion model MMP-DiffNet, a noise reduction generation process from three-dimensional polygon noise to a building roof structure is realized, the influence of extraction precision of low-dimensional features such as points and lines on a building LOD2 model topology reconstruction process is reduced, and the construction efficiency is improved. And the precision of building LOD2 model construction by the satellite image is improved.

The invention relates to the field of remote sensing image processing and geological disaster monitoring, in particular to a goaf three-dimensional subsidence basin reconstruction system based on multi-source remote sensing image fusion, which comprises a heterogeneous data preprocessing module, a differential geometry-based data fusion module, a three-dimensional subsidence basin reconstruction module, a subsidence dynamic monitoring module and a virtual reality interaction module, the system innovatively introduces a differential geometry theory to solve the problem of heterogeneous fusion of a high-resolution optical satellite image, an SAR satellite image and airborne remote sensing Lidar point cloud data, maps multi-source data to a unified feature space through manifold learning, calculates an adaptive fusion weight through curvature analysis, constructs a multi-scale feature correlation matrix based on a geodesic line distance, and achieves the fusion of the high-resolution optical satellite image, the SAR satellite image and the airborne remote sensing Lidar point cloud data. A high-precision fusion image is generated, three-dimensional reconstruction is carried out in combination with subsidence basin geological parameters and a physical constraint method, it is ensured that a reconstruction result conforms to an actual subsidence physical rule, dynamic monitoring and virtual reality interaction of the subsidence process are achieved, and parameter adjustment and model optimization are supported.

The invention discloses a remote sensing image low-frequency noise correction method and system, relates to the field of remote sensing image processing, realizes accurate removal of stripe noise under the condition of reducing satellite image detail loss, and relieves the problems of unstable correction effect, easiness in losing image details, difficulty in accurately depicting prior characteristics and the like of the existing remote sensing image low-frequency noise correction technology. The remote sensing image low-frequency noise correction process takes a column mean value or a row mean value as a basic processing unit; fine noise intensity calibration is carried out; low-frequency noise of the image is corrected in a mean value compensation mode, and detail loss of the corrected image is avoided. The method is suitable for multispectral and panchromatic remote sensing images of a remote sensing satellite, and is not influenced by ground feature types.

The invention provides a remote sensing image cloud removal method and system fusing gradient fidelity and time-spectrum consistency, and relates to the technical field of remote sensing image processing and tensor modeling, and the method comprises the steps: firstly obtaining a multi-temporal remote sensing image and cloud mask data, and generating a fault mask through active fault recognition; then calculating a guide gradient tensor and carrying out low-rank approximate processing to obtain a spatial characteristic factor and a time-spectrum characteristic factor; constructing a multi-objective optimization model of a gradient domain fidelity term, a pixel domain fidelity term and a time-spectrum consistency constraint term based on the multi-objective optimization model; and a near-end alternating minimization algorithm of an embedded alternating direction multiplier method is adopted to efficiently solve, a reconstruction result is corrected in combination with a cloud mask and an active fault mask, and a high-quality cloud-removed image sequence is output. According to the method, the edge structure, texture details and space-time consistency of the image can be effectively kept in a complex cloud coverage scene, and the usability and analysis value of remote sensing data are remarkably improved.

The invention discloses a remote sensing image segmentation method and system based on multi-scale context enhancement, and relates to the technical field of remote sensing image processing, and the method comprises the steps: obtaining a to-be-processed remote sensing image, inputting the to-be-processed remote sensing image into a global-local fusion network, and obtaining a multi-scale feature; inputting the multi-scale feature into a cascade fusion network to obtain a first processing feature, a second processing feature, a third processing feature and an integration feature; inputting the integrated features into a multi-scale context fusion network to obtain multi-scale semantic features; fusing the first processing feature, the second processing feature and the third processing feature with the multi-scale semantic feature to correspondingly obtain a first fusion feature, a second fusion feature and a third fusion feature, and fusing the first fusion feature, the second fusion feature and the third fusion feature to obtain a cascade feature; and inputting to a result output network based on the cascade features to obtain a segmentation prediction result of the remote sensing image. And the segmentation precision of the complex ground feature boundary and the small target in the remote sensing image is effectively improved.

The invention relates to the technical field of remote sensing image processing, and particularly discloses a remote sensing image target detection method based on a multi-scale cross-stage network model, and the method comprises the following steps: obtaining a to-be-detected remote sensing image; the method comprises the following steps of: inputting a backbone network after passing through an input layer, extracting multi-scale and multi-level semantic features step by step, and obtaining feature maps of different sizes through multi-scale down-sampling; inputting the feature maps of different sizes into a feature integration network, and performing cross-stage fusion and lightweight optimization to obtain a plurality of fused feature maps; and inputting the plurality of fusion feature maps into a prediction head, and carrying out classification detection to obtain detection results of multiple scales. According to the method, the brand new multi-scale cross-stage network model is constructed, multi-scale feature extraction, fusion and target recognition capabilities are enhanced, accurate detection of multi-scale targets, especially small targets and complex-form targets, in the remote sensing image can be realized, detection precision and reasoning efficiency are both considered, and the method is suitable for remote sensing application scenes such as ocean monitoring and urban planning.

The invention discloses an unmanned aerial vehicle hyperspectral image object-level target detection method based on spatial-spectral decoupling and double-flow interactive fusion, belongs to the technical field of remote sensing image processing and computer vision, and particularly relates to an object-level target detection method of a hyperspectral image. The objective of the invention is to solve the problems of low detection precision and robustness and the like caused by pixel-by-pixel detection, insufficient spatial spectrum information fusion and insufficient complex scene adaptability in an existing unmanned aerial vehicle hyperspectral target detection method. The method comprises the following steps: step 1, acquiring a hyperspectral image of an unmanned aerial vehicle; step 2, inputting the hyperspectral image into a hyperspectral decoupler, and outputting spatial features and spectral features by the hyperspectral decoupler; 3, inputting the spatial features and the spectral features output by the hyperspectral decoupler into a spatial-spectral feature extraction and fusion module, and outputting the features by the spatial-spectral feature extraction and fusion module; and 4, inputting the features into a detection head, and outputting a detection result by the detection head.