76 results about "Georeference" patented technology

Precision agriculture methods and systems where drone images of an agricultural field are captured by a UAV and analyzed to generate information regarding the agricultural field. Items of interest are identified in the images, the pixel-space locations of the items of interest are determined, and the world-space locations of the items of interest are then determined using the pixel-space locations. The transformation from pixel-space location to world-space location occurs without transforming the images or processing transformed images.

The invention provides an ocean live big data fusion method based on deep learning, and relates to the technical field of ocean big data fusion, and the method comprises the steps: obtaining meteorological driving variables, ocean historical reanalysis data, satellite observation data and ocean field observation data, and performing unified format conversion processing on the basis of the acquired meteorological driving variables, the ocean historical reanalysis data, the satellite observation data and the ocean field observation data, and configuring a unified ocean environment feature tensor set. A unified marine environment feature tensor structure is configured, meteorological driving variables, marine historical reanalysis data, satellite remote sensing data and on-site buoy observation data are subjected to space resampling, time interpolation and missing complementation and are unified into a space-time grid under a geographic reference coordinate system, a four-dimensional tensor set is configured, and the four-dimensional tensor set is obtained. The problem of fusion obstacles caused by non-uniform data formats and inconsistent temporal-spatial resolutions in the prior art is effectively solved.

The present application relates to a geographic mosaicking method and apparatus for video images, and a computer device and a storage medium. The method comprises: acquiring real-time live streaming images of a real-world scene that are collected by a plurality of unmanned aerial vehicles, and GNSS information of the plurality of unmanned aerial vehicles; using a visual SLAM algorithm to perform input frame tracking on the real-time live streaming images, and performing pose estimation on successfully tracked input frames by combining visual trajectories and the GNSS information, so as to generate georeferenced camera poses; using the camera poses and a surface reconstruction algorithm to perform densification processing on the input frames, so as to generate a depth map of the real-world scene, and mapping the depth map into dense three-dimensional point clouds, so as to construct a three-dimensional surface model of the real-world scene; and using the camera pose and the three-dimensional surface model to perform orthorectification on the input frames, and integrating the orthorectified input frames into a global mosaicked map, so as to generate a global image of the real-world scene. By means of the embodiments of the present application, a real-time picture of a real-world scene can be quickly acquired, thereby providing robust support for a rapid emergency response in a real-world scene.

A system and method combines photometric crop surveillance with a ground-mounted directional, variable-flow sprayer that compensates for wind to enable selective, per-patch application of water, fertilizer, or crop-protection products. Photometric imagery is processed to produce georeferenced treatment targets and recommended application quantities. Wind-field estimations and local wind-sensing are used to compute aim offsets, droplet size, and flow / dwell and shielding parameters that compensate for advection and turbulence. The system commands a sprayer with aimable nozzles and proportional flow control with per-target, wind-compensated parameters to selectively treat sub-areas at different doses, while minimizing drift. Follow-up photometric verification and logged wind telemetry enable closed-loop learning of drift / advection models.

The invention discloses a map updating method and device, a server, a system and a medium, and is suitable for updating and maintaining a high-precision map, and the method comprises the steps: collecting the track information of a vehicle and a synchronous road environment image collected through a vehicle-mounted visual sensor; recognizing and extracting perception elements including lane lines and ground marks from the image; converting the identified perception elements from an image pixel coordinate system to a geographic coordinate system, and generating perception elements of geographic reference; correlation matching is carried out on the perception elements of the geographic reference and corresponding map elements in a map database, and the quality of each time of matching observation is evaluated to generate a corresponding matching probability value and a quality weight; based on the matching probability value and the quality weight, calculating the support degree of single observation on map element state hypothesis; fusing the observation support degrees from a plurality of vehicles and a plurality of moments, and calculating a posterior probability of map elements needing to be updated; and deciding whether to update the map elements according to the posterior probability.

The proposed technique introduces embodiments of a computer-implemented method for interpreting image delineations as vector objects and topological extraction from segmentation by visual computational methods applied to sections (slices) of seismic volumes, in order to aid geological interpretation and sampling of parameters originating from the fracture network and its topology. Embodiments of a developed method integrates a software / application that allows the loading and generation of statistical data related to the fracture network while maintaining georeferencing and scale of the two-dimensional input data. In addition, a fracture segmentation method is shown that uses pyramid image smoothing (decomposition into hierarchical levels of resolution) in order to reduce the amount of details and aid the identification of main faults or fractures. The segmentation after this smoothing is based on adaptive thresholding segmentation.

Described herein are systems and techniques for underwater leak detection and monitoring. Georeferenced location information of a seafloor lander can be determined based on location information of marker buoys deployed to the seafloor surface. Acoustic sensor data can be obtained from an acoustic sensor rotatably coupled to the seafloor lander, wherein the acoustic sensor is rotated through a configured angular range one or more times. An onboard processing engine of the seafloor lander can perform in-situ detection of gaseous leaks from the seafloor surface by analyzing the acoustic sensor data. A corresponding location of the gaseous leak can be determined based on the georeferenced location information of the seafloor lander and relative position information between the acoustic sensor and the one or more gaseous leaks. The seafloor lander can transmit leak detection information indicative of the one or more gaseous leaks and the corresponding location to a surface receiver.

A system is provided for localizing an autonomous work vehicle within mapped agricultural environments when GPS may be unavailable. Range sensors capture LiDAR images that are segmented by a trained model into features such as trunks and canopy. Trunk points are clustered to compute centroids, which are used to estimate left and right tree lines and a lane centerline relative to the vehicle. This sensor-derived centerline is compared with georeferenced lane and row geometry stored in a digital map. A particle filter maintains multiple pose hypotheses, propagates them using vehicle odometry, and weights them according to alignment between the lane centerline relative to the vehicle and the mapped lane geometry for the particle. Resampling and averaging of high-weight hypotheses produces an adjusted pose that corrects for lateral and heading errors. The adjusted pose serves as input to a navigation controller that issues steering and speed commands, enabling accurate autonomous operation.

The invention discloses an unmanned aerial vehicle road disease detection and analysis system and method based on a YOLO algorithm, and the method comprises the following steps: synchronously collecting a road image and geographic coordinates through an unmanned aerial vehicle, and constructing an image data set with geographic reference; constructing an initial YOLO target detection model based on the data set; introducing an additional detection layer for detecting a pixel area into the model, and embedding a channel attention mechanism into the feature extraction network to obtain an improved YOLO target detection model; reasoning a data set by using the model, and outputting a disease category, a bounding box coordinate and a confidence coefficient; pixel coordinates are converted into geographic coordinates through a coordinate conversion algorithm, and disease records with accurate geographic coordinates are generated; and optimizing and updating the model based on the record as an incremental training sample. According to the method, the disease detection precision and the small target identification capability are effectively improved, and the long-term adaptability and generalization performance of the model are enhanced through a closed-loop incremental learning mechanism.

An autonomous feed delivery system for evenly dispensing a specified amount of feed into a specified distance such as a feed bunk. This results in a concisely controlled rate of discharge per linear distance which is critical to achieving an even and accurate delivery of the specified amount of feed into the feed bunk. Features can include using a georeferenced map of feed bunks to identify correct feed rations to the correct bunks based on a prescription for each bunk, and preventing feed dispensing outside of bunk locations, load sense hydraulic control to provide hydraulic power to dispensing independent of vehicle engine rpm, and interruption of bulk feed supply to the dispensing sub-system if indications of overload are sensed.

The invention discloses a man-machine collaborative remote sensing image intelligent labeling method and device based on a visual large model. The method comprises the steps of obtaining remote sensing image data to be labeled, and performing image enhancement processing to obtain enhanced remote sensing image data; inputting the enhanced remote sensing image data into a visual large model for mask segmentation processing, and outputting a plurality of target segmentation masks and corresponding confidence coefficients; marking layer graphs with different colors on the to-be-marked remote sensing image data to form marked remote sensing image data, and displaying the marked remote sensing image data to a user; and the user performs confirmation operation, and stores the labeled remote sensing image data as a GeoTIFF file format image with geographic reference information. In the embodiment of the invention, the image labeling precision of complex ground objects, multiple regions and the like is obviously improved.

The invention provides a panoramic image acquisition, splicing and backtracking method and system for airport inspection, and relates to the technical field of intelligent operation and maintenance of airport infrastructure, and the system comprises a high-precision panoramic image acquisition module, a self-adaptive panoramic image splicing module, a three-dimensional geographic reference fusion module, and an intelligent analysis and decision module. By introducing a Beidou + high-precision RTK integrated navigation positioning technology and multi-lens panoramic acquisition equipment, acquisition of information such as pavement panoramic images, space coordinates, timestamps and the like is realized. Through an improved feature point matching algorithm, adaptive projection transformation matrix calculation and a multi-scale frequency domain fusion strategy, an image registration offset problem under a complex illumination condition is solved and a splicing seam is eliminated. Multi-dimensional data fusion of a panoramic image and a pavement plate GIS model is realized through spatial topological mapping, and a pavement inspection panoramic image intelligent analysis and decision-making system management platform is developed.

The invention provides a blind sidewalk detection management method, device and equipment based on an unmanned aerial vehicle and a storage medium thereof, and the method comprises the steps: obtaining multi-source detection data through the unmanned aerial vehicle, and the multi-source detection data comprises image data and point cloud data; based on the image data, blind sidewalk feature extraction is carried out on the point cloud data, blind sidewalk point cloud is generated, and the blind sidewalk point cloud is a three-dimensional point set with geographic reference coordinates; performing topology modeling based on the blind sidewalk point cloud to obtain a blind sidewalk network topological graph; spatial analysis is carried out based on the blind sidewalk network topological graph, to-be-maintained road section data are obtained, and the to-be-maintained road section data comprise breakpoint data and coverage blind area data; and performing maintenance decision based on the to-be-maintained road section data to obtain a maintenance work order sequence. By adopting the method, high-precision spatial positioning and intelligent analysis of urban blind sidewalk facilities can be realized, the problems of inaccurate blind sidewalk breakpoint identification and coverage evaluation distortion caused by positioning errors are effectively solved, and the blind sidewalk connectivity detection precision and management efficiency are improved.

A geographic position of an agricultural machine is captured. Agricultural data is received that corresponds to a geographic position. Georeferenced visual indicia are displayed that are indicative of the received agricultural data.

The invention discloses a POS prior assisted heterogeneous unmanned aerial vehicle fine thermal infrared color point cloud generation method, which comprises the following steps: 1) based on a conventional photogrammetry method, processing a visible light image and POS data thereof, and generating a dense point cloud with geographic reference information; 2) selecting homonymy points in the thermal infrared image and the dense point cloud, and solving exterior orientation elements of the thermal infrared camera in a point cloud coordinate system by adopting a resection algorithm; 3) completing geometric calibration between the thermal infrared camera and the GNSS / IMU system in combination with POS data of the thermal infrared image; 4) establishing a spatial mapping relation based on the calibration parameters and the POS information, mapping the thermal infrared image to the visible light point cloud, and generating a preliminary thermal infrared color point cloud; 5) constructing a virtual camera consistent with the thermal infrared camera in parameter, and projecting the point cloud to generate a two-dimensional image; 6) performing different-source image registration on the projection image and the thermal infrared image by using a deep learning network with phase consistency and dense feature matching to obtain a relative orientation parameter; and 7) performing spatial correction on the initial thermal infrared color point cloud according to the relative orientation parameter to obtain a fine thermal infrared color point cloud. The fusion of the thermal infrared image and the visible light point cloud of the heterogeneous unmanned aerial vehicle platform is realized under the limiting conditions of missing pre-calibration information, low resolution of the thermal infrared image, load separation of the visible light camera and the thermal infrared camera and the like, and the method has the advantages of high spatial precision and good adaptability.

The application discloses a kind of unmanned aerial vehicle image and multi-modal map area cutting method and system based on attitude information, first obtain the unmanned aerial vehicle image containing EXIF metadata, extract GPS information and attitude parameter, calculate image ground real projection center point longitude and latitude in combination with sensor parameter graph;Again, according to pixel size, sensor physical size etc., calculate ground resolution and geographical coverage, correct the projection angle to get four real longitude and latitude, then four corner coordinates are converted to map projection coordinate system, generate cutting window in combination with base map geographic reference information, high-precision cutting is carried out in infrared, visible light map base map respectively, corresponding result is carried out after spatial alignment and consistency verification, and relevant data is saved in JSON format structure.The method realizes accurate area matching and cutting, improves the spatial accuracy and processing efficiency of multi-source remote sensing data fusion and target identification, and is suitable for remote sensing surveying and mapping, resource investigation and emergency monitoring and other scenes.

A computer-implemented georeferencing method (100), the method (100) comprising: receiving (102) sensor data representing a portion of the surface of the earth, wherein the sensor data is obtainable or obtained by a sensor included in or attached to a vehicle, preferably an aerial vehicle; segmenting (106) the sensor data to generate a sensor data segmentation map comprising one or more segments and a set of labels, wherein each of the labels relates to a segment and is indicative of a type of the segment; determining (118) a labelled reference segmentation map obtainable by segmenting georeferenced reference data; and comparing (126) the sensor data segmentation map to the reference segmentation map to determine a georeference of the sensor data segmentation map.

A method may include receiving first data collected as a first pipeline inspection gauge (PIG) passes through a first pipeline and training a machine learning model using the first data. The method may further include receiving second data collected via an optical fiber as a second PIG passes through a second pipeline, wherein the second data is representative of one or more fiber optic events and applying the trained machine learning model to the second data. Additionally, the method may include identifying a position of the second PIG and generating a graphical user interface (GUI) to display the position of the second PIG.

Examples for localization using tessellated grids are described. In an example, a plurality of physical entities can be identified in an indoor space and each physical entity can be georeferenced to a coordinate system. The indoor space can be divided into a grid of polygonal tiles abutting adjacent polygonal tiles, and arranged in a hierarchical structure with the tiles in one level of the hierarchical structure being substantially representable by polygonal tiles in other levels of the hierarchical structure. The grid is then spatially indexed by associating each physical entity with a polygonal tile from amongst the polygonal tiles in each hierarchical level, thereby correlating a georeference of the physical entity with the polygonal tile. Based on the spatial indexing, a grid map for the indoor space can be generated for localizing mobile devices in the indoor space.

A geographic position of an agricultural machine is captured. Agricultural data is received that corresponds to a geographic position. Georeferenced visual indicia are displayed that are indicative of the received agricultural data.

The invention relates to a ground station system (38a-c) for georeferencing aerial images, in particular for calibrating and / or surveying drone photogrammetry data, of an area (10a-c), such as, for example, a construction site, an archaeological find and / or excavation site or an infrastructure facility, with a plurality of control point units (12a-c, 14a-c, 16a-c) that can be arranged distributed over the area (10a-c), wherein each of the control point units (12a-c, 14a-c, 16a-c) has an optical marker (18a-c) on at least one surface that is uniquely identifiable from the air. It is proposed that each of the control point units (12a-c, 14a-c, 16a-c) is associated with a Global Navigation Satellite System (GNSS) module (20) for acquiring its instantaneous geographic position and a Wide Area Network (WWAN) module (28a-c) for at least wirelessly transmitting the acquired instantaneous geographic position, wherein at least one of the control point units (12a-c, 14a-c, 16a-c) is integrated into a functional object (22a-c, 24a-c, 26a-c) that is at least temporarily assigned to the area (10a-c) and performs a main function within the area (10a-c) that is different from georeferencing.

Methods and systems for improved generation and georeferencing of floor plans are presented. In one embodiment, a method is presented that includes receiving images that depict sheets of a blueprint of a structure. Subsets of the images depicting floor sheets and elevation sheets may be identified. Exterior contours may be extracted from the images depicting floor sheets and elevation contours may be extracted from the images depicting elevation sheets. A corresponding structure within a three-dimensional map may be identified based on the exterior contours and the elevation contours. A three-dimensional contour of the exterior of the structure may be extracted from the three-dimensional map.

Described are systems and techniques for visualization and manipulation of non-composite oblique aerial imagery. Information can be obtained for an annotation feature for overlay on a displayed oblique image with an oblique viewpoint of a scene within a geographic area. Three-dimensional (3D) model data can be obtained for a portion of the geographic area and including 3D information of object surfaces within the scene. A 3D representation of the annotation feature can be generated using the 3D model data and georeferenced coordinates determined for the annotation feature. An oblique projection of the 3D representation of the annotation feature into the oblique viewpoint of the scene can be generated to include portions of the annotation feature unobstructed by the object surfaces within the scene. The oblique projection of the annotation feature can be output as a two-dimensional (2D) overlay on the displayed oblique image.

The application discloses a kind of based on Gaussian distribution's remote sensing image pixel and sampling point matching method and device, it is related to remote sensing data processing and environmental monitoring technical field.The method first obtains ground sampling point longitude and latitude coordinate and the remote sensing image data of coverage area, and extracts image spatial resolution, the geographical reference information of pixel;Then according to image resolution to determine initial weighted window range, in combination with preset boundary weight threshold and maximum coverage distance, calculate Gaussian kernel standard deviation;With sampling point as center, construct two-dimensional Gaussian weight field, according to the Euclidean distance of sampling point and the center of pixel in image to calculate weight, and according to the pixel set of dynamic determination involved in calculation according to Gaussian kernel coverage range;Finally, the reflectivity of each pixel is multiplied by corresponding weight and is normalized, and obtains the estimated reflectivity at sampling point.The method can effectively fuse neighborhood pixel information when sampling point and pixel center do not coincide, improve reflectivity extraction precision.

The invention discloses an unmanned aerial vehicle image and multi-modal map area cutting method and system based on attitude information, and the method comprises the steps: firstly obtaining an unmanned aerial vehicle image containing EXIF metadata, extracting GPS information and attitude parameters, and calculating the latitude and longitude of a real projection center point of the image ground in combination with sensor parameters; calculating ground resolution and geographical coverage according to pixel size, sensor physical size and the like, correcting projection angles to obtain real longitudes and latitudes of four corners, transferring coordinates of the four corners to a map projection coordinate system, generating a cutting window by combining geographical reference information of the base map, and performing high-precision cutting in the base map of the infrared and visible light map respectively to obtain a three-dimensional image; after a corresponding result is obtained, space alignment and consistency verification are carried out, and related data are stored in a JSON format in a structured mode. The method realizes accurate region matching and cutting, improves spatial precision and processing efficiency of multi-source remote sensing data fusion and target identification, and is suitable for various scenes such as remote sensing surveying and mapping, resource investigation, emergency monitoring and the like.

This invention belongs to the field of image reconstruction technology using 3D Gaussian sputtering. It discloses a reconstruction method, system, and storage medium that directly converts color point clouds into 3D Gaussian sputtering. By using the color point cloud as the sole input, an initial color image and corresponding depth map are generated using the intrinsic and extrinsic parameters of a virtual camera. The virtual camera's intrinsic and extrinsic parameters are set to seamlessly incorporate absolute spatial coordinate information into subsequent image enhancement and 3D Gaussian sputtering training processes, ensuring that the final reconstructed 3D Gaussian sputtering model has a clear geographic reference. The initial color image and corresponding depth map are then processed using a diffusion model for style enhancement and hole completion, outputting an enhanced image. Finally, the enhanced image and depth map are used together for 3D Gaussian sputtering training. Through joint optimization of photometric, depth, and multi-view consistency, the final scene representation is obtained, achieving direct generation from point clouds to 3D Gaussian sputtering and improving the realism, texture, and multi-view consistency of the reconstructed image.

An imaging system for an aircraft is provided. A plurality of image sensors are attached, fixed, or secured to the aircraft. Each image sensor is configured to generate sensor-generated pixels based on an environment surrounding the aircraft. Each of the sensor-generated pixels is associated with respective pixel data including position data, intensity data, acquisition time data, sensor type data, pointing angle data, latitude data, and longitude data. A controller generates a buffer image including synthetic layer pixels, maps the sensor-generated pixels onto the synthetic layer pixels in the buffer image, fills a plurality of regions of the buffer image with the sensor-generated pixels, and presents the buffer image on a head-mounted display (HMD) to a user of the aircraft. Figure 1

The invention relates to a method for controlling a drone (100) provided with a surface treatment device and with position sensors, the method comprising: - flying the drone (100) according to the flight plan (400) at a distance from a surface to be treated; - the flight plan (400) of the drone (100) being defined in a georeferenced 3D point cloud (300) representing the surface to be treated; - the flight plan (400) comprising a flight path in which a set of successive positions that the drone (100) must adopt are defined, the flight path being such that the drone (100) passes at a treatment distance from the surface to be treated, the coordinates of the points of the surface being known; - defining the position of the drone (100) during flight and selectively activating the surface treatment device depending on the position of the drone (100).

A method for controlling the trajectory of a motor vehicle (MV) comprising a vehicle localization system including a single-antenna satellite geolocation unit (ANTE) and an inertial geolocation unit cooperating with a georeferenced high-definition map; said method, implemented by said localization system, consisting of exploiting the rear axle drift angle (RAR) of said vehicle to estimate, in real time, the yaw angle, or heading, of the vehicle throughout the determined trajectory of the vehicle, particularly during turns, using a dynamic model representing the vehicle, of the bicycle model type (BM), in an x, y reference frame, taking into account the position of the satellite geolocation unit's antenna (ANTE) in the vehicle's x, y reference frame and the antenna drift angle (ANTE). (Figure 1)

A data gathering module receives georeferenced data from a UAV over a target area. A processing module receives the captured georeferenced sensor data and analyzes the data to create detailed landscape condition maps using techniques such as machine learning and vegetation indices (NDVI, NDRE). In some embodiments the module automatically identifies and segments different landscape features such as turf, plants, weeds and hardscapes. The data processing module pinpoints specific problem areas or polygonal zones that require remediation for issues such as water stress, nutrient deficiency, weed infestation or pest damage and generates a specific remediation recommendation. An action module generates a set of targeted commands to accomplish the remediation recommendation, and a verification module compares the pre- and post-mediated areas to generate a verification report.