66 results about "Medium resolution" patented technology

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 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.

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 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.

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 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 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 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 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.

The application provides a semantic segmentation method for landslide detection by using medium-resolution multi-source remote sensing data, mainly including five steps: data selection and download, data preprocessing, model construction, model training and result evaluation. The application faces medium-resolution multi-source remote sensing data, proposes a new double-encoder semantic segmentation network with a self-attention mechanism, realizes feature expression and hierarchical fusion of multi-modal data, and further improves the landslide detection precision, thereby providing a technical reference for landslide detection in a large spatial scale.

A computer-implemented method for generating synthetic mammographic images using a modified diffusion model has as novelty three training phases in which modified diffusion is performed, namely: in a second stage 200 of local context generations, over an image representing a third channel, in a step 208 of adding noise to the image patch, and in a step 209 of training the neural network to remove the noise, and also modified diffusion is performed in a third phase 300 of generating full-resolution patches, in a step 308 of denoising the image patch, and in a step 310 of training a neural network to remove noise. Also, the method includes working with patches in the image in the second phase 200 in steps 204-210 and in a third phase 300 in steps 304-311. The method includes training in phase 100 on an image representing a single channel, a global context, with steps 101-106, then training over the images representing the first, second, and third channel: in phase 200 with steps 201-210 and in phase 300 with steps 301-311 and finally phase 400 of generating a full-resolution mammogram image. Phase 400 includes: subphase 401 where noise is programmatically generated and in step 403 the neural network removes it and provides an output image at a resolution of 256x256; subphase 405 with step 406 where the input image from the first phase is loaded and steps 407 are then performed-411; step 412 of integrating patches with local context in a way that ensures smooth transitions during integration, which is an innovative step; then subphase 413 where, in step 414, the medium-resolution image obtained by integrating the patches from the second phase 200 is loaded, after which steps 415-420 are performed. then step 421 of integrating the patches in the image follows, and finally, the full-resolution output image is obtained in step 422. The patch integration in step 412 is innovative and ensures smooth transitions in the image.

The invention discloses a defect detection method and system for a gantry machine tool workbench casting, and relates to the technical field of casting detection. The method comprises the following steps: performing low-resolution mode scanning on a target casting part according to a wide-beam probe, executing analysis based on an automatic encoder, and constructing a first uncertain thermodynamic diagram; performing detection path sequence planning and medium-resolution mode scanning on the first uncertain thermodynamic diagram based on Bayesian optimization, and updating and determining a second uncertain thermodynamic diagram; aiming at the second uncertain thermodynamic diagram, executing high-resolution mode detection and defect verification on a part higher than an uncertain threshold value, and determining a defect detection result; and after the uncertainty thermodynamic diagram is obtained in the one-by-one detection stage, defect pre-detection and uncertainty compensation are carried out. The technical problem that in the prior art, the detection efficiency and the detection precision are low in the gantry machine tool workbench casting part detection process is solved, and the technical effect of improving the casting part defect detection efficiency and the detection precision is achieved.

The invention provides a distributed SAR satellite follow-up bunching InSAR mode realization method and system. The method comprises the steps of obtaining a formation configuration and a working wave position; predicting the overhead time of the target area and the ground station; sAR working parameters are obtained; generating a task instruction and uploading the task instruction to a satellite; controlling the satellite to perform bunching mode imaging and record data when the satellite passes through the top target area; downloading the data when the ground station passes the top; and finally carrying out ground imaging and interference processing to generate a surveying and mapping product. The technical problems that a traditional InSAR system is insufficient in resolution and low in precision in small-area region surveying and mapping are solved.

The embodiment of the application provides a kind of river and lake shore zone remote sensing monitoring method and product, the river and lake shore zone remote sensing monitoring method includes: obtaining historical medium resolution remote sensing image data and historical high resolution remote sensing image data;From the historical medium resolution remote sensing image data, the end-member spectrum of typical ground object is extracted;The end-member spectrum is corrected according to the high resolution remote sensing image data and the interference of shadow or cloud layer is eliminated, and the target end-member spectrum matrix is obtained;According to the target end-member spectrum matrix, pixel unmixing is carried out on the medium resolution remote sensing image data to be decomposed, and the pixel unmixing result is obtained;According to the pixel unmixing result and water flooding frequency, water level amplitude area is determined;The shore zone monitoring range is determined according to the water level amplitude area;The image data corresponding to the shore zone monitoring range is input into wavelet transform U-Net deep convolutional neural network model, and the shore zone land use classification result is obtained;According to the shore zone land use classification result, the ecological shore zone ratio result of each river section is quantified.

The present application relates to the technical field of remote sensing image intelligent processing, and particularly relates to a multi-scale progressive land surface temperature fusion downscaling method and device, wherein the method comprises: preprocessing land surface temperature images in a multi-scale image library; constructing a multi-scale training data set containing land surface temperature and at least one auxiliary parameter; constructing a land surface temperature downscaling network based on multi-parameter fusion, and constructing a domain transformation network based on heterogeneous high-frequency information guidance; training the land surface temperature downscaling network and the domain transformation network based on a progressive double-network joint training strategy; fine-tuning a downscaling model meeting a preset low-to-medium resolution condition; and performing low-to-medium-to-high progressive downscaling on a low-resolution land surface temperature image to be processed, so as to generate a multi-scale progressive land surface temperature meeting a target high-resolution condition. The present application fully considers the downscaling difference problem under different resolutions, realizes the physical property retention of a land surface thermal field, and improves the processing efficiency of large-area remote sensing data.

The application belongs to the technical field of artificial intelligence and satellite remote sensing, and particularly relates to a cross-scale spatio-temporal fusion ground feature classification method based on a double-branch architecture, which comprises the following steps: preprocessing a remote sensing image; obtaining high-resolution optical images and multi-period medium-resolution time-series images, generating time-series data and labeling through processing, and cutting a data set; constructing a double-branch network, wherein the network comprises a spatial and temporal feature extraction branch and a fusion and decoding module; training and optimizing a model by using a weight optimizer and a loss function with dynamically adjusted class weights; post-processing a classification result, and outputting vector data. The method realizes the fusion of heterogeneous information, solves problems such as the same object with different spectra, improves the feature utilization rate and the recognition accuracy of a minority class, is convenient to design in an end-to-end mode, has strong generalization ability, and is fast in reasoning.

The invention belongs to the field of infrared measurement, and particularly relates to a precision optical adjustment and boresight device and a use method, targets and point targets with multiple medium resolutions are generated through an infrared multi-target simulator, and under the driving of a motor, a guide rail can be driven to precisely move in a 2 pi space and keep a precise spatial position, so that the precision optical adjustment and boresight device is obtained. Clear images can be formed in all directions of the detector, the sliding table can accurately feed back the position relation of each infrared point target in the space, the boundary position of the target in imaging of the detector can be found by continuously moving the point target, and the spatial orientation and the pitch axis of the distributed infrared equipment are calibrated. Meanwhile, the infrared multi-target simulation can simulate images with various resolutions, the sliding table 6 moves in the space 2pi range, imaging can be carried out at all positions of the detector, the imaging quality of target plates with various resolutions can be observed, and the resolution performance, distortion and imaging uniformity of the distributed infrared equipment detection system can be accurately calibrated.

A sensor circuit, method and apparatus are provided. A clock source may be configured to generate a clock signal. A plurality of samplers may be configured to receive a plurality of radio frequency signals and to produce, based on the clock signal, a plurality of low-frequency samples. A data analyzer may be configured to process low-resolution representations of the plurality of low-frequency samples collected over a plurality of sampling instances and process them at low or medium resolution to generate one or more data analysis metrics associated with the plurality of RF signals. The sensor circuit including samplers taking low-frequency samples, and a data analyzer processing low-resolution or medium-resolution representations of a number of samples collected over time for statistical analysis, provides power efficiency compared to known approaches that use power-hungry samplers at a high frequency.

The application discloses a resolution plate, a resolution test system and a method for measuring resolution capability, wherein the resolution plate comprises a plate body, at least one slit group is arranged on the plate body, the slit group comprises two parallel slits which are arranged on the plate body along a path, the slit has a width in a direction perpendicular to the path, the slit has a uniform width along the path, the two slits have a consistent shape and width, the two slits are arranged at intervals, and the interval of the two slits is equal to the width of the slit. By arranging at least one slit group with two slits on the plate body made of tungsten material, high-energy X rays can form at least one image with two strips on the imaging plate through the slit group, and the corresponding curve can be obtained through simple measurement and multiple tests, so that the resolution capability of the ray point source under the corresponding magnification ratio and the slit width can be intuitively and accurately reflected.

The invention relates to the technical field of remote sensing image analysis and target detection, in particular to a multi-temporal multi-resolution SAR image aircraft detection method based on gate position prior. The method comprises the following steps: firstly, constructing composite variability on a low-resolution multi-temporal sequence, and extracting gate position priori by quantile threshold and morphological processing; carrying out overlapping merging, point domain association and neighborhood scale interpolation on the detection result and a medium-resolution detection result to form candidates; prior cross-resolution registration to a high-resolution domain is realized through learning type homography mapping; and in the candidate cutting pieces, key point heat map guided frequency domain adaptive filtering is combined with domain confrontation to complete fine detection and confidence reweighting, and an aircraft bounding box and geographic coordinates are output. According to the method, the search space is compressed, and the cross-sensor robustness and the detection precision are improved. The system is modularized, does not need ground control point marking, adapts to different wavebands and spatial resolutions, and facilitates engineering deployment and rapid updating.

The application relates to a satellite image-based cross-domain ground object classification fine-tuning sample automatic selection method, which comprises the following steps: obtaining an initial interpretation model, to-be-interpreted images and medium-resolution ground surface cover classification results; obtaining an interpretation result and an interpretation category probability distribution; constructing a high-value sample selection framework; selecting candidate images from the to-be-interpreted images as a to-be-labeled sample set according to a sample screening strategy, artificially labeling the candidate samples to obtain a fine-tuning sample set; fine-tuning the initial interpretation model according to the fine-tuning sample set and model evaluation, and obtaining an optimal interpretation model; and obtaining a final fine-tuning sample set after a screening criterion is met. On the basis of reasonably utilizing an existing model, the application constructs diversified, representative and differentiated fine-tuning samples through ground surface cover prior knowledge, fully utilizes the prior knowledge, reduces the input of manpower and material resources, and can better complete a current satellite remote sensing image ground object classification task.