39 results about "Geographic coordinate system" patented technology

The application discloses a 4D video generation method fusing monocular vision and terrain elevation data, comprising the following steps: acquiring video frame images and corresponding camera pose data collected by a monocular camera; acquiring terrain elevation data of a target area, and constructing a three-dimensional elevation network model; based on the camera pose data, establishing a ray projection model for pixels in the video frame images, calculating the intersection of the rays and the three-dimensional grid model, and obtaining the reference distance from the monocular camera to the ground surface corresponding to the pixels; generating an initial relative depth map of the video frame images by using a depth estimation model; selecting high-confidence ground pixels from the video frame images as reference points, taking the reference distance corresponding to the reference points as the true value, and performing absolute scale correction on the initial relative depth map to obtain an absolute depth map; performing back projection calculation on the absolute depth map, the camera pose data and pixel color information to generate a three-dimensional point cloud, mapping the three-dimensional point cloud to a real geographic coordinate system, and generating 4D video data in time sequence.

This invention relates to the field of data processing technology and discloses a method, apparatus, and equipment for monitoring surface deformation based on parameter search interval optimization. The method, based on the location information of multiple buildings in a geographic coordinate system and multiple SAR images, determines at least one building-related region and at least one non-building region within a target area. It then determines a first residual elevation search interval for the building-related region based on the roof elevation value of at least one target building within the building-related region; determines a second residual elevation search interval for the non-building region; and performs temporal InSAR phase calculation based on the first residual elevation search interval, the second residual elevation search interval, a preset deformation rate search interval, and multiple SAR images to obtain the surface deformation rate field and residual elevation field of the target area. This significantly improves data processing efficiency while ensuring the accuracy of the temporal InSAR phase calculation and obtaining accurate surface deformation rate and elevation fields.

The application discloses a kind of based on unmanned aerial vehicle image geographical coverage area calculation method and terminal, to large quantities unmanned aerial vehicle image real-time processing, i.e. to sequence image is handled, the image that unmanned aerial vehicle is photographed is obtained binary mask graph by semantic segmentation, contour detection is carried out to binary mask graph, and contour coordinate is obtained;Through coordinate conversion chain, on the basis of considering the shooting angle such as unmanned aerial vehicle holder shooting parameter, coordinate conversion is carried out, two-dimensional contour coordinate is mapped to real world geographical coordinate system point by point, and contour point set with geographical coordinate is formed;Afterwards, the contour point set generated for each image that unmanned aerial vehicle is photographed constructs corresponding polygon object, merges all polygon objects to obtain contour polygon set, the polygon area corresponding to contour polygon set is superimposed with preset geographical boundary Analysis, finally output accurate geographical coverage area.In this way, the accuracy and efficiency of geographical coverage area calculation are improved.

This invention belongs to the field of UAV autonomous positioning and navigation technology, and relates to a UAV map construction method for environments where satellite imagery is unavailable. Specifically, it provides a method for constructing a UAV work area map based on aerial imagery, addressing issues such as image distortion and edge misalignment in existing area map construction methods. This invention orthogonally divides the UAV's aerial photography work area into a grid according to the same geographic coordinate system. The UAV performs a coverage flight mission within the work area according to a planned flight path, maintaining an interval of 50% of the field of view width between adjacent flight paths. During aerial photography, the UAV simultaneously acquires image and geographic positioning information (GPS information and yaw angle information of the center point) as image location points. Based on UAV sensor data and the UAV's flight trajectory and pose, keyframes of geographic location information are extracted from the aerial video, and then used to fill the corresponding grid content to obtain a global map of the work area.

Embodiments of the present application provide a VIO map correction method, electronic equipment and storage medium, the method comprises: obtaining a to-be-corrected map of a visual-inertial odometry (VIO) in a camera coordinate system; determining an attitude angle of a measurement device relative to a geographic coordinate system, the measurement device comprising an acceleration sensor and a magnetic force sensor; obtaining magnetic field data of the measurement device; obtaining an azimuth angle of the measurement device relative to the geographic coordinate system by combining the magnetic field data with the attitude angle; and converting the to-be-corrected map from the camera coordinate system to the geographic coordinate system based on the attitude angle, the azimuth angle, and a camera external parameter corresponding to the camera coordinate system, to obtain a corrected map. The corrected map of the present embodiment is more intuitive than the map in the camera coordinate system, thereby improving the user experience.

The application provides a high-precision generalized dynamic image motion compensation method, device, equipment and storage medium, six homogeneous coordinate transformation matrices between a geographic coordinate system and an image plane coordinate system are sequentially multiplied to form a total transformation matrix, and a multi-stage series kinematics mapping of a ground point to an image plane point is completely expressed in a single mathematical framework. A homogeneous position vector of the image plane point obtained by the total transformation matrix is directly derived with respect to time, so that each motion source and its cross-coupling effect are naturally included in an image motion velocity vector expression in an analytical form, and a truncation error caused by component separation and superposition is avoided. Accurate image motion velocity vector values are obtained by substituting real-time parameters into the expression, and then a deflection angle correction amount and a TDI charge transfer matching rate are solved to perform compensation.

This invention relates to a remote sensing image positioning method and system based on depth feature vector retrieval and matching, belonging to the field of remote sensing image positioning technology. The method includes: firstly, using a depth feature extraction model finely tuned from remote sensing image samples, extracting the first global feature vector of global orthophoto tiles, and constructing a global feature vector database through inverted index clustering; secondly, after preprocessing the remote sensing image to be located, extracting its second global feature vector, and obtaining the top K candidate tile images through nearest neighbor retrieval in the database; thirdly, performing coarse and fine local feature matching on the two, eliminating mismatched points using the RANSAC algorithm, and obtaining the reference tile image and corresponding point information; finally, calculating the affine transformation matrix based on the corresponding points to complete the mapping from pixel coordinates to the geographic coordinate system, outputting accurate geographic location information. This invention effectively improves the accuracy and efficiency of remote sensing image positioning and is suitable for various civilian application scenarios.

This application discloses a multi-mode fusion method and system for calculating canopy height in fields and orchards, belonging to the field of agricultural remote sensing and precision agriculture monitoring technology. It utilizes an unmanned aerial vehicle (UAV) platform equipped with a lidar sensor, a multispectral sensor, and a pose acquisition module to simultaneously collect lidar point cloud data, multispectral image data, and timestamped pose data. Based on the pose data, spatial registration and stitching are performed on the point cloud data to generate a 3D point cloud model of the crop; geometric correction and stitching are performed on the multispectral image data to generate a multispectral orthophoto. The two are unified to the same geographic coordinate system to establish a spatial mapping relationship; spectral indices are calculated based on the multispectral orthophoto to identify land cover categories and regions; corresponding subsets of the point cloud are extracted based on the spatial mapping relationship to generate a digital surface model and a digital ground model; and canopy height is calculated by the difference. This application integrates multi-source data to achieve automated and high-precision calculation of canopy height for crops such as corn and fruit trees, and has strong applicability.

This invention belongs to the field of agricultural consulting technology, specifically a big data-based precision agricultural production consulting management system. It includes a plot spatiotemporal grid construction unit, used to divide the target area into multiple rectangular spatiotemporal grids with unique plot IDs based on a preset geographic coordinate system and a minimum management unit area threshold. It outputs specific agricultural operation suggestions, including operation type, recommended time window, material type, and application rate, and pushes these suggestions in text and image format through farmer terminals. By adopting a dynamic adaptation mechanism for plot spatiotemporal grids and a crop growth cycle tag linkage update mechanism, it achieves adaptive reconstruction and synchronous information updates of the spatiotemporal grid under scenarios of plot boundary changes and crop rotation, while retaining historical data relationships. This system enables continuous and precise control of single plots across cycles and a high degree of matching between the grid and the actual production scenario.

This invention relates to the field of graphics processing technology and discloses a web-based static demonstration system for a mineral exploration platform. The system includes: a data processing module that constructs an overlay display interface of a 3D geological model and a 2D data layer; a target area analysis module that renders the range of high-potential target areas on the 3D geological model or 2D data layer; a task planning module that marks associated equipment locations and exploration paths on the 3D geological model; an equipment management module that displays static equipment ledger information and, in conjunction with an equipment monitoring panel, displays preset equipment operating parameter change trend curves; and an access control module that loads preset role permission data and configures the rendered interface menu and operation buttons according to the permissions of three roles: administrator, technician, and visitor. These modules are integrated into a single web-based page in a component-based manner, sharing a unified geographic coordinate system and display container, and responding to user operations. This reduces development costs and improves user experience and information expression capabilities.

This invention proposes a method for updating lane-level dynamic information in high-precision maps based on crowdsourced data. The method includes: collecting trajectory information and road image data from multiple sources, with a high-precision map embedded within; constructing a single-stage line-anchor detection model using a convolutional neural network; performing lane line perception detection on the road image data based on the single-stage line-anchor detection model; outputting lane line perception information; using an image alignment compensation algorithm to register and fuse road image data from consecutive frames during vehicle movement, and inputting this data into a target detection model for recognition, outputting traffic cone perception information; and projecting the lane line perception information and traffic cone perception information onto the high-precision map's geographic coordinate system using camera parameters. This method effectively suppresses missed and false detections in single-vehicle perception by combining low-cost crowdsourced data with a multi-vehicle evidence fusion mechanism, improving the accuracy and real-time performance of lane-level dynamic information updates, and meeting the high-precision requirements of autonomous driving for high-precision maps.

The present application relates to the technical field of three-dimensional data processing, and discloses a three-dimensional terrain modeling method based on surveying and mapping data, comprising the following steps: step one, obtaining multi-source heterogeneous surveying and mapping point cloud data of a region to be modeled, unifying the multi-source heterogeneous surveying and mapping point cloud data to a preset geographic coordinate system, and performing elevation normalization processing on underwater data by using synchronous tidal level data; step two, identifying homonymous feature elements of the processed multi-source heterogeneous surveying and mapping point cloud data in an overlapping area, calculating the vertical offset parameters between each load by using a least square adjustment algorithm, and performing elevation compensation on the multi-source heterogeneous surveying and mapping point cloud data by using the vertical offset parameters. The three-dimensional terrain modeling method adopts the overlapping area homonymous feature element matching and vertical offset parameter calculation technology, eliminates the systematic elevation difference of multi-source surveying and mapping data, achieves the unification of water and land benchmarks, realizes seamless smooth splicing of the terrain of the boundary area, and solves the problem of false steep cliffs and geometric misplacement at the water-land junction caused by traditional modeling.

This application provides a coordinate estimation method and system for matching UAV photos with 3D ground real-world scenes, belonging to the field of geographic coordinate estimation technology. The method includes: acquiring aerial images of the task area using an UAV's onboard camera; identifying and masking dynamic interference areas in the aerial images using semantic segmentation and motion detection to obtain static background images and extracting features to obtain two-dimensional image features; extracting features from a preset static urban real-world 3D model to obtain 3D model features; matching the 2D image features with the 3D model features to establish a correspondence between 2D image points and 3D model points; based on the correspondence, using the PnP algorithm to calculate the initial exterior orientation elements of the UAV in the absolute geographic coordinate system, and optimizing it using bundle adjustment to obtain the optimized UAV visual pose; fusing it with the observation data from the inertial measurement unit to obtain the final 3D position and attitude of the UAV in the absolute geographic coordinate system.

The application discloses a dam micro-deformation monitoring method, relates to the technical field of water conservancy engineering structure health monitoring, and comprises the following steps: installing a self-stabilizing platform connected with a fixed end and a universal joint on a dam; an inertial unit is used to perceive dam dynamics and drive an actuator to reversely compensate, so that a platform probe is stabilized relative to a space reference; a non-contact array is used to measure the vector of the displacement of the fixed end along with the dam; data locking is triggered when the displacement or energy characteristics exceed the limit; relative displacement and platform residual compensation are fused, vibration interference is removed through coordinate transformation, real micro-deformation in a dam geographic coordinate system is solved, and early warning is generated. The application effectively isolates high-frequency vibration interference in a physical layer through active self-stabilizing technology, and establishes a stable local measurement reference; a triggered acquisition mechanism greatly improves data value density; the method has high measurement precision, strong anti-interference capability, and can effectively identify small plastic damage of a dam.

The application provides a method for positioning and abnormality analysis of power equipment, comprising the following steps: obtaining original pixel coordinates of the power equipment; performing distortion correction and depth compensation on the original pixel coordinates; mapping the corrected coordinates to a power grid node construction geographic coordinate system; inputting the geographic coordinates into a geographic information system for searching; calculating the Euclidean distance between the geographic coordinates and three-dimensional bounding box coordinates; judging whether the Euclidean distance is less than a threshold value, if yes, determining that the positioning result of the power equipment is accurate; obtaining the file data of the power equipment according to the identification of the power equipment; determining the abnormality reason of the power equipment according to the file data of the power equipment; and outputting the geographic coordinates and the abnormality reason of the power equipment. The method can significantly improve the positioning accuracy, and the average error of positioning is reduced to 0.38 meters, which is much better than the industry level of more than 2 meters; a single analysis can output 3-5 combined fault reasons, thereby providing more accurate and comprehensive decision basis for operation and maintenance.

This invention discloses a method for testing the attitude of marine buoys based on a solar-geomagnetic dual-vector gyroscope. The method includes: acquiring sky images via a camera, identifying solar spots and extracting the center pixel coordinates using the gray-scale centroid method; calculating the measured solar vector in the carrier coordinate system from camera intrinsic parameters and the installation matrix; calculating the solar reference vector using latitude, longitude, and time; acquiring the measured geomagnetic vector in the carrier coordinate system using a magnetometer; calculating the geomagnetic reference vector in the geographic coordinate system; constructing the Davenport matrix using the Wahba problem and solving for the eigenvectors to obtain the optimal attitude quaternion observations; establishing a model with quaternions and gyroscope zero bias as state variables; fusing the observations with the gyroscope angular rate measurements using an extended Kalman filter; and estimating the buoy's three-dimensional attitude in real time and compensating for gyroscope drift. This invention offers high accuracy and robustness, making it particularly suitable for buoy platforms operating in long-term marine environments.

This application provides a method, apparatus, equipment, and medium for measuring individual tree stand parameters, belonging to the field of forest resource survey and forestry remote sensing technology. The method includes: acquiring visible light images, laser point cloud data, and individual tree IDs for each tree within a target area; converting the visible light images and laser point cloud data to a global geographic coordinate system; performing canopy segmentation, tree species classification, and occlusion estimation on each visible light image; performing individual tree point cloud segmentation on each laser point cloud data; matching the canopy segmentation mask with the point cloud clusters based on the individual tree ID to obtain successfully matched 3D contour point sets and 3D projected contour point sets; thereby extracting the target parameters for each tree; obtaining the diameter at breast height (DBH) parameter based on the target parameters; and determining the individual tree volume using a univariate volume model, thereby determining the stand volume. This application improves the accuracy of individual tree parameter extraction and the precision of stand volume measurement.

The application relates to the technical field of image change detection, in particular to a low-altitude unmanned aerial vehicle video frame extraction and orthographic image change detection method based on deep learning, which is characterized in that unmanned aerial vehicle video is acquired to perform frame-by-frame semantic segmentation and grid feature extraction, adjacent frame grid distribution is compared to screen change-related frames, spatial mapping of the change-related frames and orthographic images is constructed through edge matching, images are spliced according to positions and edge transition processing is performed to generate a continuous sequence, finally, new and old image ground categories are compared based on a geographic coordinate system, and video frame extraction and image change detection results are output. According to the application, grid time sequence description based on ground semantics is introduced, change recognition is converted into category evolution analysis with semantic meaning, key space-time regions with attribute transfer are focused, continuous image organization under a unified geographic reference is combined, content space continuity is ensured, result time sequence direction and spatial certainty are strengthened, and expression stability and explanation clarity of patrol change information are improved.

This invention discloses a method and system for generating 3D terrain registration profiles and interactive situational awareness data using airborne cloud radar, relating to the field of airborne cloud radar application technology. The method acquires real-time aircraft position and attitude, cloud radar per-detection-unit data, 3D terrain data, and external airspace data; maps multi-source data to a unified time reference and establishes a cache queue; constructs a four-level transformation model from the cloud radar coordinate system through the aircraft coordinate system, local navigation coordinate system to the geographic coordinate system or 3D terrain coordinate system; interpolates attitude parameters for each effective detection unit according to the sampling time, completing point-by-point or group attitude compensation and spatial registration; constructs 3D cloud bodies, terrain, aircraft, flight paths, and airspace objects and overlays them to form a 3D main view; generates cutting planes and section views, achieving bidirectional linkage positioning between the main view and section views; supports multi-view switching, target attribute viewing, and highlight display interaction. This invention solves the problems of cloud body drift and spatial interpretation difficulties, improving the efficiency of flight situational awareness.

This invention proposes a novel high-latitude navigation method based on the ECEF system, belonging to the field of high-precision navigation technology. This invention addresses the problems of low positioning accuracy and large error fluctuations in traditional grid coordinate system and transverse coordinate system navigation algorithms in high-latitude environments, as well as the navigation interference caused by meridian convergence and high-latitude dynamic effects. The steps of this invention include: establishing a transformation matrix between the geographic coordinate system and the geocentric-fixed coordinate system; establishing discrete navigation solution equations for attitude direction cosine matrix, velocity, and position in the geocentric-fixed coordinate system; establishing error equations for attitude error, velocity error, and position error in the geocentric-fixed coordinate system; performing an S-domain transformation based on the error equations and converting to the time domain to obtain an analytical expression for inertial navigation error in the geocentric-fixed coordinate system; and obtaining optimized high-latitude navigation results based on the oscillation and divergence characteristics of attitude and velocity errors presented by the analytical expression for inertial navigation error.

The application discloses a turntable attitude compensation method for aircraft semi-physical simulation experiment and relates to the technical field of aviation, which comprises the following steps: acquiring the theoretical geographical position longitude and latitude set in the aircraft semi-physical simulation; respectively calculating the projection vectors of the earth rotation angular velocity under the geographical coordinate systems of two places and determining the vector difference between the two; acquiring the second direction cosine matrix of the turntable body coordinate system relative to the turntable geographical coordinate system; calculating the dynamic compensation angular velocity under the turntable body coordinate system for offsetting the geographical position error; and generating and executing the compensated turntable control instruction. The application establishes the projection error model of the earth rotation angular velocity of two places, directly corrects the turntable driving instruction, ensures the high confidence of long-time simulation, breaks the dependence of the simulation system on the fixed physical position of the turntable through pure algorithm compensation, and greatly improves the flexibility, universality and engineering practical value of the semi-physical simulation system.

The application relates to a shipborne optical telescope image despin angular velocity calculation method, which comprises the following steps: 1. based on the ship body pitch angle, the ship body azimuth angle, the ship body roll angle, the camera mounting platform pitch rotation angle and the camera mounting azimuth rotation angle output by a shipborne inertial navigation device, an attitude matrix of a camera coordinate system relative to a geographic coordinate system is established; 2. the attitude matrix of the camera coordinate system relative to the geographic coordinate system established in step 1 is calculated to obtain an attitude matrix of a lens coordinate system at a current time of the camera relative to a lens coordinate system at a previous sampling time, and the obtained attitude matrix of the lens coordinate system relative to the lens coordinate system at the previous sampling time is used to calculate the rotation angular velocity of the image; and 3. the rotation angular velocity of the image obtained in step 2 is subjected to noise reduction processing to remove the angle measurement noise of the inertial navigation device and the angle measurement noise of the rotating mechanism. The application ensures that the reference coordinate systems of each frame of image in the continuously shot images are consistent.

The application discloses a kind of based on map framework three-dimensional visual geographic scene switching method and device, the method includes obtaining the tactical scenario information input by user and target confrontation scene name, and according to the data information in tactical scenario information, determine the first offset coordinate set of confrontation unit;Find out corresponding scene center coordinates in the preset database, and according to the first offset coordinate set and scene center coordinates, the first target coordinate set is converted;Based on the first offset coordinate set and the motion data of confrontation unit in tactical scenario information, the second target coordinate set is converted;According to the first and second target coordinate set, the first trajectory of confrontation unit in target confrontation scene is drawn out.This application solves the deviation problem of Cesium from independent coordinate system to GPS geographic coordinate system conversion, realizes the reuse of single tactical scenario in multiple scenes, so that the tactical scenario formulated by user is fully utilized, to improve the reliability of the plan.

The application provides a high-precision map lane-level dynamic information updating method based on crowd-sourced data, comprising: collecting trajectory information and road image data of crowd-sourced vehicles, and internally embedding a high-precision map; a line anchor single-stage detection model is constructed by using a convolutional neural network, the lane lines of the road image data are perceived and detected based on the line anchor single-stage detection model, and lane line perception information is output; an image alignment compensation algorithm is used to register and multi-modal fuse the road image data of continuous frames in the vehicle driving process, and the road image data is input into a target detection model for identification, and traffic cone perception information is output; the lane line perception information and the traffic cone perception information are projected to a high-precision map geographic coordinate system through camera parameters; the method effectively suppresses the missed detection and false detection of single-vehicle perception by combining low-cost crowd-sourced data with a multi-vehicle evidence fusion mechanism, improves the accuracy and real-time performance of lane-level dynamic information updating, and meets the high-precision requirements of automatic driving on high-precision maps.

This invention relates to the field of drainage network monitoring technology, and discloses a method, device, electronic equipment, and medium for full-scene surveying of drainage networks. This invention acquires and integrates the geographical location data of manholes, multi-frame 3D point cloud data above and / or underwater, and their corresponding pose data. Based on coordinate transformation, it constructs a 3D point cloud model with geographic coordinates, achieving accurate spatial positioning of network nodes in a unified geographic coordinate system. By identifying pipe outlet nodes from this model and extracting their geographical location, orientation, and pipe diameter, and then automatically establishing the connection relationships between pipe outlet nodes according to spatial matching rules, an accurate network topology is generated. By integrating multi-frame point cloud and pose information for 3D reconstruction and relationship derivation, the data adaptability and analysis reliability under different manhole structures and environmental conditions are enhanced, thereby improving the overall accuracy, automation, and environmental adaptability of full-scene surveying of drainage networks.

The application discloses a kind of marine mine detection methods based on multi-source data fusion, belong to marine target detection and anti-mine technical field.For the technical problems that the space-time inconsistency of multi-source data in the existing marine mine detection is not realized effective fusion, resulting in insufficient detection accuracy and reliability, the solution points are as follows: collecting multiple types of original detection data and marking the collection time, establishing a unified time axis with global navigation satellite system timing, taking the carrier pose data as the spatial reference, correcting the acoustic data and converting the magnetic field data to the same geographic coordinate system, inputting the extracted features after fusion into the target recognition model for analysis and judgment, and outputting suspected mine information and thematic chart results.The application is mainly used for marine mine detection, and can improve the accuracy and reliability of mine detection in complex marine environment, and meet the operational requirements of anti-mine operations.

This invention relates to the field of image processing, specifically to an automatic measurement and extraction method for surface cracks in mines based on image recognition. The method employs a multi-time-segment, multi-angle mine image acquisition strategy, performing feature matching and benchmark registration on multiple mine images to align all images to the same geographic coordinate system. Candidate cracks are selected based on edge overlap in the crack representation of the mine images. The final crack edges are obtained based on the grayscale features and edge pixel overlap of the corresponding regions of the candidate cracks in each mine image. Finally, the final crack edges are merged based on the direction angle and distance between them to obtain the actual cracks. This invention can identify areas in complex mine surfaces that may contain cracks, reducing interference from sunlight and shadows, improving crack identification accuracy, and reducing the false positive rate, thus facilitating subsequent measurement and damage assessment and the development of corresponding safety measures.

This invention discloses a method and related apparatus for identifying and calculating the installation of column foundations in photovoltaic power plants, belonging to the field of photovoltaic power generation technology. The method acquires image data of a photovoltaic power plant; overlaps and segments the image data to detect column foundations in the image; calculates the geographical coordinates of the column foundations in the image; and matches the column foundations in the image with those in the design drawings based on the geographical coordinates, thus statistically analyzing the installation status of the column foundations. This invention reduces reliance on professional surveyors, making the construction and operation of photovoltaic power plants more convenient and economical. Accurate identification of column foundation installation is crucial for the safety and stability of photovoltaic power plants. This method, by accurately calculating the position of the column foundations in the geographical coordinate system, can promptly detect and resolve installation deviations and other problems. This helps ensure the structural safety of the photovoltaic power plant and improve its power generation efficiency and operational stability.