132 results about "Satellite image" patented technology

This application discloses a landslide segmentation method, apparatus, equipment, and medium based on hybrid Mamba and frequency domain calibration, relating to the field of landslide disaster detection technology. The method involves fusing optical satellite imagery with slope and lithological topographic constraints, preprocessing the data, and then inputting it into a model containing a hybrid Mamba encoder, a multi-scale adaptive gating module, and a progressive frequency domain calibration decoder for processing. Through multi-stage hybrid coding, contextual aggregation modulation, and progressive resolution recovery, accurate landslide segmentation is achieved, effectively improving global feature modeling capabilities, enhancing the identification accuracy of multi-scale and boundary-ambiguous landslides, balancing lightweight design and robustness, and better adapting to the actual monitoring needs of highway landslides.

The application discloses a kind of satellite radiation product-based remote sensing image geometric calibration method, electronic equipment and medium.The method can include: determining reference image, inputting image to be calibrated;For the same name point matching of image to be calibrated and reference image, obtain the same name point coordinates;The third polynomial distortion model about CCD probe element number is constructed;Based on the same name point coordinates, curve fitting is carried out on the distortion model, and the distortion coefficient is obtained;The resampling of image to be calibrated is carried out by distortion coefficient, and the correction of internal distortion of image is realized.The application can quickly and accurately carry out geometric calibration processing to satellite image, greatly improve the efficiency and quality of image processing.

Example methods and systems for geological interpretation in hydrocarbon exploration are disclosed. One example method includes obtaining a geological sketch of a first region, where the geological sketch includes a color-labeled image of the first region, and each color in the geological sketch represents a respective type of geological land cover in the first region. A first machine learning model is applied to convert the geological sketch into a first virtual satellite image of the first region. The first virtual satellite image is provided for geological interpretation of the first region.

The application discloses a road centerline determination method and system based on a deep neural network satellite map, and relates to the technical field of satellite image processing; the method comprises the following steps: preprocessing time-phase satellite images of a collected to-be-processed region, vehicle GPS track data and street view image sequences to obtain a dynamic region in the to-be-processed region, a track density map and a street view feature mapping table; inputting the time-phase satellite images into a pre-trained road segmentation model to obtain multiple road probability maps; based on the multiple road probability maps, performing dynamic region weighted fusion, non-dynamic region logical or operation and threshold determination to obtain an initial road mask; vectorizing the initial road mask into a centerline network and extracting cross nodes to obtain an initial road network topology; and the application has the advantages of improving the accuracy of the road network topology and guaranteeing the rationality of path planning.

This invention provides a method and system for constructing a 3D model of a construction site by combining multiple data sources. It relates to the field of data processing technology. The method includes: retrieving satellite imagery at a preset resolution to obtain a full-area stereo image pair dataset; performing radiometric correction to generate a regional surface model and a regional elevation model; performing raster-level modeling defect detection to locate distributed blind zone blocks; fitting obstacle avoidance paths to generate optimized obstacle avoidance flight trajectories; driving a UAV to perform multi-angle surround scanning to directionally collect dense point clouds in the distributed blind zones; constructing a distributed blind zone model; and performing microscopic overlay to output a 3D model of the construction site. This invention solves the technical problems of existing construction site modeling methods, which have limitations in coverage, modeling efficiency, and data real-time performance, and rely on a single data source, failing to provide a comprehensive and accurate 3D model of the construction site, thus affecting construction progress and decision-making.

An electronic device includes a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction to: input first data to a first artificial intelligence model including a plurality of convolution blocks sequentially connected with a pooling layer interposed therebetween to obtain a plurality of feature maps that are output by corresponding ones of the plurality of convolution blocks, input the first data and the plurality of feature maps to a second artificial intelligence model including a plurality of local attention blocks sequentially connected to obtain a plurality of attention maps that are output by corresponding ones of the plurality of local attention blocks, output an amplified feature map by amplifying a region corresponding to a last attention map among the plurality of attention maps in a last feature map among the plurality of feature maps, and input the amplified feature map to a classifier to output a classification result for the first data.

This application discloses a lightweight, gated landslide image screening method, apparatus, device, and medium, relating to the field of image data processing technology. The method includes: acquiring and preprocessing satellite image slices, then processing them through a pre-defined gated lightweight model containing a backbone network, a neck network, and a detection head; performing multi-scale feature extraction, high- and low-order feature fusion, and target detection and judgment; and outputting landslide-containing slices. This scheme employs enhanced spatial pyramid pooling, high- and low-order gated fusion, and an improved fast dual-branch module, effectively preserving detailed landslide features, reducing computational load and parameter count, and quickly and accurately screening satellite image slices containing landslide targets, meeting the needs of rapid screening of massive images and emergency monitoring.

The photovoltaic region segmentation method, apparatus, storage medium, and computer equipment provided in this application include: determining a preset region segmentation model; inputting satellite images into the first feature extraction layer of the region segmentation model for preliminary feature extraction; inputting the feature map output from the first feature extraction layer into the second feature extraction layer of the region segmentation model for deep feature extraction by a multi-scale feature extraction module and a dual attention module to obtain a region feature map; and finally inputting the region feature map into the point rendering layer of the region segmentation model to obtain a photovoltaic region segmentation image. Multi-layer feature extraction can obtain richer data representations of the photovoltaic region, thereby improving the generalization ability of the photovoltaic region segmentation model. Furthermore, combining the multi-scale feature extraction module and the dual attention module for further feature extraction can adaptively fuse local features and global contextual information, improving the accuracy of photovoltaic region segmentation.

This invention proposes a high-dynamic real-time yaw rate adjustment and image shift compensation optical scanning imaging method and device, belonging to the field of optical remote sensing technology. It solves the technical problem of ensuring the quality of satellite on-orbit imaging. The method includes: using a combined imaging mode of vertical orbit scanning with a tilting mirror and pitch return to perform high-dynamic vertical orbit wide-area scanning imaging, determining the satellite imaging motion law, and establishing a high-precision multi-coordinate system object-image geometric mapping and image shift calculation model to calculate the variation law of image shift compensation parameters; measuring satellite orbit information, attitude information, and camera optical axis pointing information through a high-precision sensor, predicting the camera optical axis motion law using filtering, and substituting it into the image shift calculation model to obtain the line frequency; and achieving graded yaw rate adjustment through fixed yaw rate adjustment, curve fitting, and adjustment of the installation angle. This invention is applied to optical remote sensing satellites with high-dynamic vertical orbit wide-area scanning imaging, achieving on-orbit image shift compensation imaging that balances wide-area coverage and high resolution.

The application provides a large-scale satellite image automatic registration and enhancement method based on adaptive multi-source fusion, comprising: performing orthorectification and multi-resolution unified projection on a multi-source original data set obtained to obtain a coarse registration image set; calculating a local tensor structure of the coarse registration image set, performing repeated texture recognition, generating a final structure representation and a structure reliability; performing regional registration to obtain a full-image dense deformation field, then performing image transformation to be aligned and registration uncertainty estimation to obtain a high-precision registration image and structure registration uncertainty estimation; combining a pseudo-change probability of the high-precision registration image and the structure registration uncertainty estimation to obtain a change reliability weight; under the constraint of the change reliability weight, performing consistency enhancement on the high-precision registration image to output a quantitative and reliable enhanced image. The application realizes high-precision, low-false alarm and quantifiable and reliable automatic registration and enhancement of multi-source large-scale satellite images.

The application discloses a kind of based on sentinel-2 satellite image's duckweed type eutrophication water monitoring method, it is related to water monitoring technical field, including the following steps: after the atmospheric correction processing of sentinel-2 L1 C level satellite image of non-duckweed growing season and duckweed growing season, all wavebands are resampled to the same resolution, after mean filtering to the blue band, green band, red band, near infrared band, narrow near infrared band of multi-band surface reflectance image after resampling of non-duckweed growing season and duckweed growing season, then band synthesis is carried out, obtain non-duckweed growing season band synthesis image and duckweed growing season band synthesis image;The proportion of duckweed growing range in water range is calculated using non-duckweed growing season band synthesis image and duckweed growing season band synthesis image.The present application can realize the fast, large-scale, low-cost duckweed type eutrophication water monitoring.

The application discloses a cloud layer blocking-based landslide disaster satellite image data generation method and device, equipment and medium, relates to the technical field of satellite landslide disasters, and comprises the following steps: obtaining multi-source remote sensing, meteorological, topographic and cloud-shielded multi-temporal optical satellite image data of a target area, calculating multi-dimensional landslide physical characteristic vectors in combination with the topography; fusing multi-source data fine classification cloud layers, determining a priority processing area according to the cloud layer, meteorological and topographic data; inputting the area image and the physical characteristic vector into a landslide feature enhancement generation network containing a double-attention module, performing feature extraction, enhancement, fusion and up-sampling recovery, generating a cloud-free landslide satellite image and completing credibility evaluation, effectively suppressing the interference of cloud layer blocking, and improving the accuracy of the satellite landslide image data generated under the condition of cloud layer blocking.

A cross-view image retrieval method for unmanned aerial vehicle navigation, comprising the following steps: step one, first enhancing the image, step two, based on the ConvNeXt network for cross-view image retrieval for unmanned aerial vehicle navigation, multi-scale feature extraction is performed on the enhanced image; step three, multi-dimensional feature fusion is performed based on an attention mechanism; step four, after multi-dimensional feature fusion, the loss value is calculated, and a detection model is obtained based on the determined weight to perform image retrieval; through the multi-scale feature convolution and multi-dimensional feature fusion technology, the technical problems of insufficient matching precision and poor retrieval robustness caused by the differences in view, scale and structure between satellite images and unmanned aerial vehicle images are solved; the application also includes a system, a device and a medium for implementing the above method.

[Problem] To provide a vegetation determination system that estimates vegetation proportions of a plurality of plant classifications on the basis of a satellite image. [Solution] In the present invention, an information processing system generates a second trained model by using a training data set which includes a satellite image as input data and includes, as teacher data, an output result of a first trained model generated using a UAV image. The information processing system comprises: a vegetation proportion map generation unit that generates the first trained model by performing training processing for determining a vegetation classification, by using a high-resolution vegetation classification training data set in which the UAV image and the teacher data indicating the vegetation classification are associated with each other, and generates a vegetation proportion map on the basis of a vegetation classification image outputted from the first trained model; a low-resolution vegetation proportion training data generation unit that generates a low-resolution vegetation proportion training data set in which the vegetation proportion map is associated, as the teacher data, with the satellite image; and a second training processing unit that performs machine learning processing for determining vegetation proportions from the satellite image, by using the low-resolution vegetation proportion training data set.

This invention discloses a drone navigation method based on Transformer and hypergraph enhancement algorithms. The method utilizes a gimbal camera to capture drone images and acquires satellite images to construct a drone image-satellite image pairing dataset. The drone image-satellite image pairing dataset is then standardized to obtain a standardized pairing dataset. This standardized pairing dataset is input into a visual positioning neural network based on Transformer and hypergraph enhancement algorithms for training, resulting in a visual positioning neural network model. The visual positioning neural network model is converted into Engine format and deployed to an onboard computer, forming a drone visual navigation module for rapid positioning. This invention's drone visual navigation module combines the advantages of lightweight and miniaturized structure with the performance advantages of fast inference speed and high positioning accuracy. It is adaptable to most drone models and has broad engineering application value.

This invention discloses a satellite data acquisition system and method based on ground-based space environment simulation. The system includes a satellite physical model unit, a simulated space environment construction unit, an attitude and position adjustment unit, a camera acquisition unit, and a data acquisition and control unit. Each unit works collaboratively under the unified coordination of the data acquisition and control unit to construct a controllable simulated space imaging environment and complete the acquisition of satellite image data. This invention achieves automated and repeatable acquisition of satellite image data by constructing a controllable simulated space imaging environment under ground conditions and utilizing a robotic arm to adjust the camera attitude. This provides stable and reliable dataset support for satellite vision missions, addressing the problems of existing satellite vision datasets that mainly rely on simulation generation or on-orbit measured data, low integration of ground acquisition systems, insufficient controllability of the imaging environment, and low automation of camera attitude adjustment and data acquisition processes.

A vehicle mileage estimation method based on remote sensing imagery and deep learning includes: constructing a self-labeled dataset by dividing high-resolution satellite images into grid cells; estimating vehicle density using a YOLO-based deep learning model, which achieves multi-scale feature fusion through a three-layer pyramid network for accurate vehicle detection; abstracting the urban road network as a graph structure and employing a cross-temporal graph neural network (CrossGraphNet) to build a model of the relationship between vehicle density and speed for accurate speed prediction; and training a semi-supervised graph neural network vehicle mileage estimation model using traffic count data from ground monitoring stations as ground truth. This model combines vehicle density and speed data with road topology relationships and uses a message passing algorithm to accurately estimate vehicle mileage. This invention overcomes the limitations of traditional methods, effectively improves the efficiency and accuracy of traffic monitoring, and provides strong data support for traffic management and planning.

Embodiments of the present disclosure relate to a fire point monitoring data processing method and device based on optical remote sensing image data, wherein the method comprises: preprocessing an original satellite image to obtain a to-be-processed satellite image; extracting a plurality of features of each pixel in the to-be-processed satellite image to construct a multi-dimensional feature vector, and performing initial screening based on the multi-dimensional feature vector to obtain a potential fire point pixel; identifying the potential fire point pixel to output a probability value of the potential fire point pixel being a fire point, and determining that the potential fire point pixel is a suspected fire point pixel when the probability value is greater than a first preset threshold; obtaining the abundance of the suspected fire point pixel, and confirming that the suspected fire point pixel is a real fire point pixel when the abundance is higher than a second preset threshold, and outputting the geographical coordinates, the burning intensity and the confidence parameter corresponding to the real fire point pixel. The above technical solution has stronger recognition ability for small and weak fire points and fire points in a singular background, and greatly reduces the false positive rate of fire points.

The application discloses a performance equalization compression method of satellite images. The method equalizes the excellent compression performance of images and the poor compression performance of images from the perspective of a multi-image system by arranging the images, overcomes the influence of the barrel effect on the practicability of image compression, overcomes the defect that the compression quality of a plurality of images compressed by a JPEG2000 standard compression algorithm is too different, and improves the performance of the standard compression algorithm without increasing complexity. The method has the characteristics of easy software and hardware upgrading and realization, has practical value in a satellite image compression transmission system, and can also play a role in any other multi-source standard compression transmission occasion.

The application discloses an online satellite map-based photovoltaic field area business management and control system, and belongs to the technical field of photovoltaic power station operation and management and control, and comprises the following: a high-precision positioning layer, which comprises a plurality of Beidou positioning terminals, the Beidou positioning terminals are arranged on operation personnel and inspection vehicles, and are used for collecting and uploading position data in real time; a dynamic satellite map layer, which is provided with customized field area satellite image base maps by high-resolution optical remote sensing satellites; and a business data layer, which is constructed on a light-weight GIS platform and comprises a static equipment library and a dynamic operation library. According to the application, the Beidou high-precision positioning, high-resolution satellite remote sensing and light-weight GIS platform are deeply fused, a digital and visual management and control data base covering the whole field area is formed, and the integration application of multi-source data is realized, so that the problem of single information caused by lagging update of traditional drawing account and information dispersion is effectively solved, and unified, real-time and accurate data support is provided for photovoltaic field area business management and control.

The purpose of the present invention is to provide an image generation device that enables a user to easily acquire a satellite image. An image generation device according to the present disclosure comprises: an acquisition unit that acquires terminal information indicating an attitude of a terminal that images a prescribed region on a map; an estimation unit that estimates an attitude of a satellite that images the prescribed region on the basis of the attitude of the terminal; a generation unit that generates image data representing a case where three-dimensional data of the prescribed region is imaged from the satellite; and a communication unit that transmits the image data to the terminal.

This invention discloses a fog identification method that automatically generates prompts based on ground observation data and satellite images. The method includes: data acquisition, acquiring satellite remote sensing images and ground meteorological observation station data; prompt generation, generating initial prompts based on ground observation data through logical judgment, and filtering and optimizing the prompts using satellite image features; feature extraction, extracting high-frequency features from satellite images through frequency domain transformation, and fusing them with deep semantic features to obtain enhanced features; and fog area identification, inputting the optimized guidance prompts and enhanced features into a segmentation model and outputting fog area identification results. This invention solves the problems of relying on manual annotation and the difficulty of multi-source data fusion in fog identification by automatically generating guidance prompts from ground observation data and combining them with frequency domain enhanced features, achieving high-precision automatic monitoring of sea fog without human intervention.

This invention relates to the field of satellite simulation technology, and discloses a method, device, and electronic equipment for simulating ultra-high resolution multi-view satellite images. The method includes: constructing a rigorous imaging geometric model between ground points in a preset three-dimensional scene and image points of a satellite sensor based on atmospheric refraction correction and solid tide correction; generating global illumination realistic shadows under the rigorous imaging geometric model based on solar radiation, and simulating the pixel output of the satellite sensor according to the global illumination realistic shadows to obtain a multi-view satellite image model; simulating different view images of the satellite sensor based on the multi-view satellite image model to obtain multi-view satellite images, and determining the rational function model of the rigorous imaging geometric model. This invention can overcome the limitations of traditional DSM / DOM data sources, taking into account the requirements of multi-view, ultra-high resolution, ultra-high precision, and fine detail, and achieving engineering simulation output of multi-view satellite images at the 0.2m level.

The application discloses a method for calculating tree height and determining planting point by using a map, comprising the following steps: selecting two satellite images of the same place taken at different times in a map, and determining tangent values of their deformation azimuths; obtaining coordinates of the same point on the crown of the same tree in the two satellite images; obtaining a cosine value of the shooting angle of one of the satellite images; determining real coordinates of the point before deformation; establishing an equation group according to the relationship between deformation and tree height, and solving tree height and base point coordinates of the tree, which represent planting point coordinates. The method can obtain tree height and planting point without field measurement, is simple to operate, short in time consumption, and can be applied to sampling detection of different urban trees.

This invention discloses a satellite image compression method under extremely low bandwidth conditions. The steps are as follows: collect a static image dataset; establish a variable bitrate image encoding / decoding network; train the encoding / decoding network; embed a generative adversarial network (GAN) at the decoder and retrain it; embed a super-resolution network after the encoder / decoder and retrain it; the user selects a region of interest (ROI), and the selected region is compressed; the decoder restores the bitstream to an image and displays it; the unselected regions are compressed; when bandwidth is sufficient, the unselected regions are transmitted, and the decoder stitches the images together; super-resolution processing is performed. This image transmission method, under extremely low bandwidth constraints, provides a superior subjective reconstruction effect compared to traditional image coding methods such as JPEG and deep learning-based image coding methods in a large number of test images.

The application discloses a kind of based on multi-source remote sensing wild tea tree dynamic monitoring and distribution prediction method, comprising: based on local self-similarity algorithm to optical satellite image and synthetic aperture radar image are registered in space, and the optical feature and synthetic aperture radar feature after registration are spliced into unified remote sensing feature;Based on spatial attention mechanism, spectral attention mechanism and cross-modal attention mechanism, each feature is weighted and fused to generate multi-source fusion feature;Extract initial feature set and carry out correlation and collinearity screening, obtain key feature set and construct time series feature data;Multi-layer Deep-LSTM network of integrated adversarial domain self-adaptive module is constructed, and the optimal prediction model is obtained after training is completed;Based on the optimal prediction model, the distribution density variation trend of wild tea tree in future period is obtained by predicting current time series feature data.The application can improve the accuracy and efficiency of wild tea tree dynamic monitoring and distribution prediction.

The present application relates to the field of aerospace technology, especially to a kind of earth observation satellite attitude controller parameter self-tuning method, the scheme includes: obtaining the desired direction and actual direction of satellite, and determining the control torque of flywheel, the satellite is earth observation satellite;Based on the control torque, obtain initial PID parameter, initial PID parameter is PID controller simulation parameter;Based on the PID controller simulation method of flywheel physical constraint, construct the fitness function of PID controller simulation parameter based on different satellite imaging mode;Satellite attitude control is simulated by PID controller simulation parameter, based on fitness function and initial PID parameter, the optimal fitness corresponding to target PID parameter under each satellite imaging mode is determined by iterative updating through particle swarm algorithm, the optimal solution of PID parameter is target PID parameter by using particle swarm algorithm combined with fitness function for iterative updating, the accuracy and efficiency of parameter setting are improved.

This invention provides a method and apparatus for highway slope monitoring based on multi-platform InSAR collaboration, belonging to the field of highway slope monitoring technology. The method includes: extracting surface deformation information under the rising and falling orbits from the time-series SAR satellite images of the target area corresponding to the highway to be monitored, performing phase calculation to obtain two-dimensional deformation information along the radar line of sight; calculating the two-dimensional deformation information within a determined visibility differentiation map to obtain the deformation characteristics of the target area in the vertical and slope directions, respectively, to identify road sections with potential slope hazards; obtaining an interferometric phase map based on UAV SAR images acquired from the road sections with potential slope hazards, inverting the deformation characteristics in the road sections with potential slope hazards, and using the inverted deformation time-series information to predict slope risk, thereby obtaining the slope monitoring results of the highway to be monitored. This invention addresses the limitations of single-platform InSAR in highway monitoring and the insufficient dimensionality of monitored highway deformation information.

This invention discloses a method, apparatus, and computer equipment for extracting buildings in complex building areas. The method includes acquiring remote sensing images of the buildings to be extracted; inputting the remote sensing images into an AFL U-Net model and converting them into vector-form roof data; wherein the model training process includes: collecting and processing high-resolution remote sensing images and Sentinel-2 satellite images, resampling them to a uniform resolution, and calculating the urban building index; using an extended spatial particle swarm optimization algorithm to perform optimized sampling and select representative samples; using the representative samples, training the U-Net model through an improved Focal_Loss loss function parameter self-prediction mechanism to optimize the learning efficiency for difficult-to-classify samples, thus forming the AFL U-Net model. By implementing the method of this invention, the loss function parameters can be adaptively predicted, optimizing the model's focus on difficult-to-classify samples and improving the overall accuracy of building extraction.