115 results about "Medium resolution" patented technology

The invention discloses a forest grass vegetation coverage refined inversion method and system based on multi-scale remote sensing, and the method comprises the steps: firstly providing end member types and end member abundance information through the field observation data of an unmanned plane, inputting the prior knowledge into a linear mixed pixel decomposition model, and carrying out the back calculation to obtain end member spectrum information of the corresponding end member types; by taking unmanned aerial vehicle over-resolution observation data as priori knowledge, the end member spectrum extraction precision is improved, and a technical support is provided for improving the inversion precision of the total coverage of forest and grass vegetation; the textural features of high-resolution satellite observation data are fully utilized, the spectral features of medium resolution and the textural features of high resolution are combined, and the optimal response relation between different remote sensing feature combinations and woody vegetation coverage measured data is constructed by utilizing a random forest model. Therefore, high-precision inversion of the woody vegetation coverage in a large-area range is realized, and data support is provided for further estimation of the herbaceous vegetation coverage.

The invention belongs to the technical field of artificial intelligence and satellite remote sensing crossing, and particularly relates to a cross-scale space-time fusion ground feature classification method based on a double-branch architecture, and the method comprises the steps: preprocessing a remote sensing image: obtaining a high-resolution optical image and a multi-stage medium-resolution time sequence image, carrying out the processing, generating time sequence data, carrying out the marking, and segmenting a data set; constructing a double-branch network, wherein the network comprises space and time feature extraction branches and fusion and decoding modules; training an optimization model by using a weight optimizer and a loss function for dynamically adjusting category weights; and post-processing the classification result, and outputting vector data. According to the method, heterogeneous information fusion is realized, the problems of same object and different spectrums and the like are solved, the feature utilization rate and minority class recognition precision are improved, end-to-end design is convenient, the generalization ability is high, and reasoning is fast.

The invention relates to the technical field of remote sensing images, and provides a staple food grain crop planting area evaluation method and device, and the method comprises the steps: carrying out the target extraction of a first medium-resolution remote sensing image of a to-be-investigated region through a first target extraction network, layering the terrain and planting structure of the to-be-investigated area according to the extracted planting distribution information and cultivated land distribution information of the first staple food grain crop; determining a first sub-meter remote sensing image corresponding to the extracted sample frame of each layer; according to the first sub-meter remote sensing image corresponding to the extracted sample frame of each layer, area extraction is carried out by using a second target extraction network to obtain a first staple food grain crop planting area in the extracted sample frame corresponding to each layer, and according to the first staple food grain crop planting area in the extracted sample frame corresponding to each layer, a second sub-meter remote sensing image corresponding to the extracted sample frame is obtained; and determining an estimated value of the total planting area of the staple food crops in the to-be-investigated area. According to the invention, the accuracy of staple food grain crop planting area evaluation is improved.

The invention relates to the technical field of remote sensing image intelligent processing, in particular to a multi-scale progressive surface temperature fusion downscaling method and device, and the method comprises the steps: preprocessing a surface temperature image in a multi-scale image library; constructing a multi-scale training data set containing the surface temperature and at least one auxiliary parameter; constructing a surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training a surface temperature downscaling network and a domain transformation network based on a progressive dual-network joint training strategy; finely adjusting the downscaling model meeting a preset low-medium resolution condition; and performing low-medium-high progressive downscaling on the low-resolution surface temperature image to be processed to generate a multi-scale progressive surface temperature meeting a target high-resolution condition. The method fully considers the problem of descending scale difference of different resolutions, achieves the maintenance of the physical characteristics of the surface thermal field, and improves the processing efficiency of large-area remote sensing data.

A video decoding apparatus and a method for adaptively setting a resolution are disclosed. According to one embodiment of the present invention, a method for adaptively setting a resolution on a per-picture basis comprises the steps of: decoding maximum resolution information from a bitstream; decoding, from the bitstream, resolution information about a current picture; and setting the resolution of the current picture on the basis of the maximum resolution information or the resolution information, wherein the resolution information has a size less than or equal to that of the maximum resolution information.

The invention provides a multi-mode remote sensing tea garden automatic identification method and system integrating phenolic indexes and phenological characteristics. According to the method, the growth amplitude GA reflecting tea phenological characteristics is calculated through medium-resolution time sequence radar data, and the normalized vegetation index NDVI, the phenolic compound index PCI and the phenol high-value dominant index PHD are calculated from optical remote sensing images so as to represent the growth condition of the tea tree and the change rule of the phenol content. A double-branch lightweight deep learning model is constructed, a first branch processes a high-resolution remote sensing image, and a second branch processes multi-modal tea garden remote sensing features; and then multi-modal geoscience knowledge of the tea garden is fully extracted and fused through a double-branch fusion module, refined and automatic extraction of large-area tea garden distribution is realized, and key technical support is provided for tea garden resource monitoring, management and the like.

The invention provides a high spatial resolution vegetation productivity method and system based on flux observation footprint, and relates to the technical field of ecological system carbon cycle process and model simulation, the method comprises the steps of calculating the flux footprint of each station, and determining the observation range of a vortex motion related system, and micrometeorological parameters comprise the height of an observation tower and the rough length; extracting land satellite high-resolution normalized vegetation index data matched with a 16-day period in the range of each station; utilizing the vegetation index data to drive and optimize a parameter framework based on a vortex motion correlation light energy utilization rate model; in combination with site carbon flux data, a Markov chain Monte Carlo method is adopted to invert model key parameters for optimization, and finally a model optimization parameterization result is obtained. The method has the beneficial effects that the accurate verification of the observation and remote sensing high-resolution GPP on the pixel scale based on the flux footprint is realized, and the problem that the current medium-resolution GPP cannot consider the parameter optimization and verification scheme of the flux footprint is solved.

The invention discloses a remote sensing-based space-time backtracking analysis method for river and lake water area invasion and occupation, which comprises the following steps of: firstly, respectively acquiring medium-resolution dense time sequence remote sensing image data and high-resolution remote sensing data of a river and lake invasion and occupation area, and processing to obtain a medium-resolution satellite remote sensing data set and a high-resolution satellite remote sensing data set which are consistent in time sequence; then, according to the high-resolution satellite remote sensing data set, forming river and lake water body characteristic wave bands by constructing various types of water body indexes and vegetation indexes, selecting river and lake water body and non-water body samples, and performing intelligent extraction on the river and lake water body by adopting an improved extreme gradient lifting algorithm to obtain a river and lake water body change range; and finally, according to the river-lake water area change range and the medium-resolution satellite remote sensing data set, constructing a river-lake water area invasion space-time backtracking evidence obtaining index system, carrying out river-lake water area invasion long-time-sequence backtracking evidence obtaining index quantitative extraction and key time point determination, and providing support for cross-region and long-time-sequence river-lake water area invasion space-time tracing evidence obtaining.

The embodiment of the invention provides a riverside and lakeside zone remote sensing monitoring method and product. The riverside and lakeside zone remote sensing monitoring method comprises the following steps: acquiring historical medium-resolution remote sensing image data and historical high-resolution remote sensing image data; extracting an end member spectrum of a typical ground feature from the historical medium-resolution remote sensing image data; correcting the end member spectrum according to the high-resolution remote sensing image data and eliminating shadow or cloud interference to obtain a target end member spectrum matrix; performing pixel unmixing on the to-be-decomposed medium-resolution remote sensing image data according to the target end member spectrum matrix to obtain a pixel unmixing result; determining a water level amplitude variation area according to the pixel unmixing result and the flooding frequency; determining a coastal zone monitoring range according to the water level amplitude variation area; inputting image data corresponding to the monitoring range of the coastal zone into a wavelet transform U-Net deep convolutional neural network model to obtain a land utilization classification result of the coastal zone; and quantifying the ecological bank zone ratio result of each river reach according to the land utilization classification result of the coastal zone.

A high-resolution impervious surface extraction method based on weakly supervised deep learning, firstly determines the remote sensing ground object target according to the extraction task and produces a small number of accurate high-resolution remote sensing image sample labels and a large number of coarse-grained medium-resolution remote sensing image sample labels. Then, a small sample set impervious surface model is trained using a small number of accurate sample labels. Then, a large number of high-resolution unlabeled images are predicted using the small sample set impervious surface model to obtain a large number of high-resolution remote sensing image impervious surface pseudo labels, from which a large number of more accurate high-resolution remote sensing image sample labels combined with a small number of accurate sample labels are selected as new training sets, and a new impervious surface model is generated through multiple cycles of training until the model accuracy is no longer improved, and the final sample labels are predicted by the final model, and then a large sample set impervious surface model is generated by combining a large number of medium-resolution remote sensing impervious surface weak label data for training, and finally, the large sample set impervious surface model is used to predict the high-resolution remote sensing image to be produced to obtain the final impervious surface extraction result.

This application relates to an anomaly detection method, apparatus, device, and storage medium based on distillation learning. The method includes: acquiring anomaly detection data of a target; inputting the anomaly detection data into a Teacher-Student framework to obtain multiple pairs of feature maps, and normalizing the multiple pairs of feature maps based on a preset feature processing strategy; inputting the pair of feature maps with the lowest resolution from the multiple pairs of feature maps into a pre-trained Reconstructor network to obtain multiple pairs of reconstructed feature maps; subtracting each pair of reconstructed feature maps to obtain an anomaly map; and obtaining the anomaly detection result of the anomaly detection image data based on the anomaly map and the reconstructed feature anomaly map. This solves the problems of low accuracy and poor robustness in existing pixel-level anomaly detection methods based on distillation learning when dealing with anomaly data.

The invention discloses a multi-scale feature fusion and multi-attention combination weak supervision anomaly detection method, and the key points of the technical scheme are that the method comprises the following steps: 1, constructing a mixed sample: obtaining a weak supervision training data set which comprises labeled normal samples and unlabeled mixed samples, the mixed sample comprises a normal sample and an abnormal sample; step 2, constructing and layering a feature extraction network: constructing a multi-scale feature extraction network, and extracting high-resolution features, medium-resolution features and low-resolution features of the samples in a layered manner; 3, constructing a fusion module: constructing a multi-attention fusion module, and respectively applying space attention, channel attention and scale attention to the multi-scale features; according to the method, the multi-scale anomaly detection rate is improved, and the weight of each scale is dynamically adjusted in combination with scale attention by extracting different resolution characteristics in a layered manner.

The invention discloses a wetland vegetation automatic classification method based on time sequence remote sensing data segmentation. Comprising the following steps: step 1, performing Savitzky-Golay filtering preprocessing on NDVI data of a time sequence, and reconstructing NDVI data of a dense time sequence; step 2, based on a vegetation habitat similarity principle, using an X-means algorithm to segment NDVI dense time sequence data; and step 3, based on sample plot survey data and literature data, determining a mapping relation between the classification of the segmented plaques and the classification of the actual vegetation clusters, and realizing classification and precision evaluation of the vegetation clusters. According to the method, automatic classification on the vegetation cluster level can be achieved, the precision of vegetation classification based on medium-resolution optical data is improved, the defect that priori knowledge is insufficient in wetland vegetation remote sensing classification is overcome, and a new technical means is provided for large-scale vegetation mapping.

The invention discloses an electronic component defect detection method. The method comprises the following steps: acquiring infrared images corresponding to three resolutions of an electronic component; extracting a low-resolution feature, a medium-resolution feature and a high-resolution feature of the infrared image; respectively extracting and fusing fine-grained associated information and coarse-grained associated information of the low-resolution features, the medium-resolution features and the high-resolution features; generating an adversarial sample graph through an adversarial network DCGAN; constructing a defect detection model based on deep learning, and fusing detection results to obtain an electronic component defect detection result; evaluating the defect detection result of the electronic component, and optimizing the defect detection model based on the evaluation result; according to the method, based on the defect detection model of deep learning, fine-grained and coarse-grained information of infrared images of different resolutions of electronic components is identified and detected, and the adversarial sample graph is generated by using the adversarial network DCGAN, so that the defect detection precision, accuracy and robustness are improved.

The invention relates to a mineral separation density measurement method based on X-ray imaging. The method comprises the following steps: carrying out initial calibration on an X-ray emission source and a digital detector; performing system calibration on the imaging system by using the calibration plate; collecting an X-ray image without a sample and an original X-ray image of a pure solid particle sample with a known thickness; the bed body is filled with a to-be-detected particle sample with the preset mass, and a particle layer is made to be uniform and loose; collecting an X-ray image of the to-be-detected particle sample, and performing geometric correction, gray normalization and phase distribution segmentation processing on the X-ray image based on a calibration result to obtain a bubble phase region and an emulsion phase region; calculating the fluidized bed layer density based on the bubble phase volume fraction, the emulsion phase volume fraction, the bubble phase density and the emulsion phase density of the to-be-detected particle sample; and calculating the fluidized bed mineral separation density according to the fluidized bed layer density. The invention aims to solve the problems of low resolution, poor anti-interference capability and large model error in the existing mineral separation density detection of the gas-solid fluidized bed.

The present application discloses a road extraction method and device based on dual-phase medium-resolution data, which solves the problems of high cost and small coverage of road extraction in the prior art. The road extraction method based on dual-phase medium-resolution data includes: determining a dual-phase road data set; the dual-phase road data set contains RGB band data of two phases; training a dual-phase branch road extraction model through the dual-phase road data set for identifying roads in the image; determining the RGB band data of two phases in the target area; inputting the RGB band data of two phases into the dual-phase branch road extraction model to determine the inferred results of the road data in the target area. The present application realizes large-scale field road network extraction through medium-resolution data. The road network is completely extracted through dual-phase data. It overcomes the problem that the existing method uses high-resolution data to extract road networks, which is difficult to apply to large-scale road network extraction.

The invention relates to multi-plane recombination of three-dimensional medical images. In particular, the present invention provides a method for recombining a sequence of images, comprising: determining a landmark plane intersecting a volume; acquiring an image sequence; recombining the image sequence along the landmark plane to generate a first recombined image sequence; perturbing the landmark plane to produce a perturbed landmark plane; recombining the first recombined image sequence along the disturbed landmark plane to generate a second recombined image sequence; mapping the second recombined image sequence, the image sequence and the landmark plane to a resolution-enhanced image sequence by using a trained image enhancement network; and displaying, via a display device, the sequence of resolution enhanced images. The present disclosure provides a method that can reduce image artifacts in retrospectively recombined image sequences, particularly in the case of retrospectively recombining medium-resolution image sequences or low-resolution image sequences, without relying on acquiring high-resolution 3D images.

The invention discloses an emission line star identification method and system based on LAMOST spectral data, and the method comprises the steps: constructing LAMOST Dr9 medium-resolution spectral data, and carrying out the data preprocessing, and obtaining a spectral data feature matrix; based on the deep residual network, introducing a shortcut residual path, and constructing an H alpha-ResNet model; carrying out dichotomy training on the H alpha-ResNet model, constructing a trained dichotomy H alpha-ResNet model, and carrying out dichotomy identification to obtain launch line star sample data; and performing six-classification training on the H alpha-ResNet model after preprocessing based on the launch line star sample data, constructing the trained six-classification H alpha-ResNet model, and performing six-classification identification to obtain a launch line star identification result. According to the invention, the multi-emission line stars can be classified, and the classification and identification accuracy of the spectral data can be improved. The method and the system for identifying the transmitting line stars based on the LAMOST spectral data can be widely applied to the technical field of astronomical data processing.

The invention provides a silicon wafer image defect detection method. The method comprises the following steps: acquiring a silicon wafer image; inputting the silicon wafer image into a defect detection network, wherein the defect detection network comprises a backbone network, a neck network and a head network; the backbone network processes the silicon wafer image to output high-resolution, medium-resolution and low-resolution features with sequentially reduced resolution and sequentially enhanced semantic information; the neck network performs enhancement processing on the high-resolution features to generate high-resolution enhanced features; the head network detects the high-resolution enhancement feature, the medium-resolution feature and the low-resolution feature and outputs defect information corresponding to the high-resolution enhancement feature, the medium-resolution feature and the low-resolution feature, and the defect information at least comprises defect classification of the silicon wafer image and the confidence coefficient of the defect classification; and determining a defect detection result of the silicon wafer image based on the defect information corresponding to the high-resolution enhancement, the medium-resolution feature and the low-resolution feature respectively. According to the method, defects under various resolutions can be identified, and the detection reliability is improved.

The present application relates to the technical field of remote sensing information extraction and snow monitoring, and particularly relates to a sub-pixel snow mapping method based on medium-resolution remote sensing data, comprising the following steps: obtaining medium-resolution remote sensing images, a digital elevation model, and ground meteorological station snow observation data, and preprocessing the remote sensing images to obtain surface reflectivity; identifying cloud-covered pixels, filling in the cloud-free dataset by temporal and spatial interpolation and ground object spectral similarity matching; selecting snow, vegetation, and water as spectral endmembers and extracting features; constructing a linear mixing model, and using the least square method to retrieve the snow proportion in the pixel to obtain preliminary data; and generating a high temporal and spatial accuracy snow distribution map through meteorological station data verification, digital elevation model terrain correction, and model parameter optimization, which solves the problems of mixed pixels, cloud coverage, terrain errors, and the lack of accuracy verification.

A video decoding apparatus and a method for adaptively setting a resolution are disclosed. According to one embodiment of the present invention, a method for adaptively setting a resolution on a per-picture basis comprises the steps of: decoding maximum resolution information from a bitstream; decoding, from the bitstream, resolution information about a current picture; and setting the resolution of the current picture on the basis of the maximum resolution information or the resolution information, wherein the resolution information has a size less than or equal to that of the maximum resolution information.

The present disclosure discloses an extraction method of raft culture area based on multi-temporal optical remote sensing images, including: constructing a raft culture marker sample library including culture types such as fish, shellfish, and algae; optimizing the deep learning model of the UNet network by using ASPP (Atrous Spatial Pyramid Pooling) and the shape constraint module; using the deep learning model to extract a corresponding multi-temporal raft culture area by using the multi-temporal optical remote sensing images with medium resolution in the target area; combining prior knowledge, fusing the extraction results of the raft culture area to obtain a final extraction results of the raft culture area.

The invention discloses a remote sensing residential area extraction method and system based on multi-source data fusion semantic segmentation, and particularly relates to the field of remote sensing image processing and land utilization mapping. A multi-source fusion automatic labeling strategy is adopted, and a rural residential area pixel-level training label is automatically generated by using an impervious surface product, an open source map interest point and a night light learning area-brightness threshold value; the method comprises the following steps: constructing an SELPFormer lightweight Transform segmentation model, introducing Lite-PPM, SCSE and ELA feature enhancement modules and a lightweight decoder on the basis of SegFormer, and outputting a rural residential spot pixel level extraction result for regional scale rural residential spot mapping.

The utility model discloses a power transmission tower deformation monitoring device, which comprises a bracket, a corner reflector, a connecting piece and a mounting piece, and is characterized in that the bracket is detachably and fixedly arranged on a tower; the corner reflector comprises a bottom plate and two reflecting plates, the bottom plate is horizontally arranged and detachably and fixedly arranged on the support, and one sides of the two reflecting plates are detachably and fixedly connected to form a reflecting groove of a right-angle structure; and the connecting piece is used for detachably and fixedly arranging the end parts of the two reflecting plates on the bottom plate. The beneficial effects of the utility model are that: can solve in the prior art transmission tower deformation and inclination monitoring application, the low-medium resolution radar satellite signal reflection energy is weak, and the problem that the effective monitoring can not be realized, on the other hand, can provide the geometric calibration of the radar satellite image of centimeter level precision, and the accuracy of the transmission tower deformation and inclination monitoring is improved. And finally, mutual fusion of mm-level precision observation results of Beidou deformation monitoring and InSAR deformation monitoring can be realized.

The invention discloses a short-time wind speed prediction method and short-time wind speed prediction equipment based on satellite image information, belongs to the technical field of meteorological prediction, and realizes high-precision and dynamic prediction of short-time wind speed by combining a satellite remote sensing image and an image feature tracking technology and setting a distance threshold adaptive to an image resolution. According to the method, the motion trend of an extreme point in a wind speed field is extracted and tracked through the SIFT algorithm, the evolution rule of the extreme point is established through regression analysis, and the complete wind speed field is reconstructed in combination with optimal interpolation, so that the limitations of insufficient resolution and obvious hysteresis of traditional numerical weather forecast in short-time local wind speed forecast are effectively overcome, and the wind speed forecast accuracy is improved. The method significantly improves the timeliness and spatial details of forecasting, and is especially suitable for offshore wind plants and other application scenes sensitive to short-time wind speed changes.

The present invention relates to a method for classifying land features based on the fusion of satellite remote sensing multispectral and panchromatic images. The method specifically comprises the following steps: S1. Acquire multispectral and panchromatic images of a target area, extract EMAP spatial features from the multispectral image, and concatenate them with the multispectral image to obtain shallow spatial spectral features; S2. Use the shallow spatial spectral features as input to a deep network and the panchromatic image as the reconstructed output, and obtain multi-resolution hidden layer features through network training; S3. Extract low-resolution hidden layer features, medium-resolution hidden layer features, and high-resolution hidden layer features, respectively, and perform feature fusion and classification training through a convolutional neural network to obtain land feature classification results within the target area. Compared with the prior art, the present invention combines shallow features at the global scale of the image with deep features at the local scale, fully exploiting the multi-resolution hidden layer feature expression between MS and PAN images, and has the advantages of high classification accuracy and high robustness.

The application discloses a lightweight multi-branch semantic segmentation method and system for complex road scenes, belongs to the field of computer vision, and comprises the following steps: taking an input image as a starting point, extracting multi-scale feature representations through a lightweight backbone network; constructing global semantic requirements on low-resolution features by an anchor semantic kernel ASK branch; performing pixel-level semantic prediction on medium-resolution features by an execution semantic kernel FSK branch; detecting boundaries and abnormal areas on high-resolution features by a boundary and outlier detection FOD branch; gating and fusing ASK and FSK features through a Qi-GFM gating fusion module; performing semantic negotiation in combination with FOD output through a Qi-Negotiation semantic negotiation module; and outputting an optimized semantic segmentation result. The application can effectively improve the prediction stability and robustness of a model in complex boundary areas and semantic uncertain areas.

This invention discloses an intelligent detection method for ecological violations in water source protection areas based on multi-source heterogeneous remote sensing spatiotemporal collaborative perception. The method includes: acquiring time-series data of medium-resolution multispectral satellite imagery and high-resolution imagery data; calculating spectral indices and establishing ecological base fingerprints based on the medium-resolution time-series data, and extracting suspected change hotspots through time-series anomaly detection; employing a cross-scale guided Transformer to perform cross-attention fusion using high-resolution texture features as queries and medium-resolution spectral features as keys and values; using a semantic segmentation network with distance field constraints to perform pixel-level fine segmentation of the violations; and vectorizing the segmentation results and overlaying them with the protection area zoning for analysis, outputting compliance assessment results. This invention employs a cascade mechanism of macroscopic scanning-targeted acquisition-fine analysis, significantly reducing monitoring costs, achieving effective identification of camouflaged targets, supporting high-frequency, routine integrated land-water monitoring, and meeting the operational needs of hierarchical management of water source protection areas.