507 results about "Laser data" patented technology

The invention discloses a Kinect-based robot self-positioning method. The method includes the following steps that: the RGB image and depth image of an environment are acquired through the Kinect, and the relative motion of a robot is estimated through the information of visual fusion and a physical speedometer, and pose tracking can be realized according to the pose of the robot at a last time point; depth information is converted into three-dimensional point cloud, and a ground surface is extracted from the point cloud, and the height and pitch angle of the Kinect relative to the ground surface are automatically calibrated according to the ground surface, so that the three-dimensional point cloud can be projected to the ground surface, and therefore, two-dimensional point cloud similar to laser data can be obtained, and the two-dimensional point cloud is matched with pre-constructed environment raster map, and thus, accumulated errors in a robot tracking process can be corrected, and the pose of the robot can be estimated accurately. According to the Kinect-based robot self-positioning method of the invention, the Kinect is adopted to replace laser to perform positioning, and therefore, cost is low; image and depth information is fused, so that the method can have high precision; and the method is compatible with a laser map, and the mounting height and pose of the Kinect are not required to be calibrated in advance, and therefore, the method is convenient to use, and requirements for autonomous positioning and navigation of the robot can be satisfied.

The invention belongs to the field of intelligent mobile robots and discloses a mobile robot cascading type map creating method based on mixed characteristics. The mobile robot cascading type map creating method based on the mixed characteristics overcomes the defect of the creation of a signal map and solves the problem that a large amount of service information can not be supplied by single map creation. The method comprises the steps of acquiring laser data points, extracting geometrical characteristics and conducting characteristic matching, extracting SURF characteristic points and conducting matching, establishing a cascading type map and segregating a room. According to the mobile robot cascading type map creating method based on the mixed characteristics, a laser optical sensor is used for acquiring environmental data and extracting the geometrical characteristics, meanwhile, a visual sensor is used for extracting SURF characteristics, an overall topological graph is created, an undirected weighted graph is structured to achieve segmentation of the room, the defects that in a traditional topological map, geometric environment information contained in topological nodes is less and precise location cannot be achieved are effectively overcome, and abundant room information can be provided. The mobile robot cascading type map creating method based on the mixed characteristics is suitable for the field of service robots and other fields related to mobile robot map creation.

A method of detecting objects from terrestrial based mobile mapping data is disclosed, wherein the terrestrial based mobile mapping data has been captured by way of a terrestrial based mobile mapping vehicle driving on a road having a driving direction, the mobile mapping data including laser scanner data, source images obtained by at least one camera and position and orientation data of the vehicle, wherein the laser scanner data includes laser points, each laser point having associated position and orientation data, and each source image comprises associated position and orientation data. In at least one embodiment, the method includes: retrieving a position and orientation of the vehicle; filtering the laser scanner data in dependence of the position and orientation of the vehicle to obtain laser points corresponding to regions of interest; retrieving a source image associated with the position and orientation of the vehicle; mapping the laser points corresponding to regions of interest to image coordinates of the source image to generate a recognition mask; combining the recognition mask and the source image to obtain candidate 3D images representative of possible objects within the regions of interest; and, detecting a group of objects from the candidate 3D images. By combining image recognition and laser scanner recognition the detection rate can be increased to a very high percentage, thereby substantially reducing human effort. Furthermore, the generating of regions of interest in the laser data, enables a significant reduction of the processing power and / or the processing time needed to detect the objects in the images.

A three-dimensional rebuilding method based on laser and camera data fusion is characterized in that the rebuilding method comprises the following steps: (1) a C++ language is adopted to compile a laser data automatic collecting platform based on a radar principle; (2) a rotation matrix R and a translation vector T are arranged between a camera coordinate system and a laser coordinate system; (3) a motion object is extracted and subdivided by utilizing an optical flow field region merging algorithm, thus further subdividing the point cloud corresponding to the motion object; and (4) guarantee of point cloud and image texture on the precise positioning is provided for the three-dimensional image texture mapping, thus realizing the three-dimensional rebuilding system based on data fusion. The three-dimensional rebuilding method has the advantages of quickly and automatically collecting and processing laser data, quickly completing the external labeling of the laser and CCD, effectively extracting and subdividing effective point clouds of the object in complex environment and exactly completing the three-dimensional rebuilding of the laser and CCD data of the object.

Aspects of the present disclosure relate to using an object detected at long range to increase the accuracy of a location and heading estimate based on near range information. For example, an autonomous vehicle may use data points collected from a sensor such as a laser to generate an environmental map of environmental features. The environmental map is then compared to pre-stored map data to determine the vehicle's geographic location and heading. A second sensor, such as a laser or camera, having a longer range than the first sensor may detect an object outside of the range and field of view of the first sensor. For example, the object may have retroreflective properties which make it identifiable in a camera image or from laser data points. The location of the object is then compared to the pre-stored map data and used to refine the vehicle's estimated location and heading.

The invention provides a multi-scene drone locating and three-dimensional map mapping method based on a three-dimensional laser radar. In an indoor environment, when no GPS signal exists, a SLAM algorithm based on a three-dimensional laser sensor is built; in an outdoor environment, position information provided by RTK is mainly relied on to build the three-dimensional map, and after RTK loses theGPS signal, SLAM assists in locating. An indoor and outdoor three-dimensional map is quickly built, a convenient and efficient method is provided for obtaining the three-dimensional environment map,and the efficiency of building the three-dimensional environment map in the indoor environment and the outdoor environment is improved to a great extent; on the theoretical basis of mapping optimization of the SLAM algorithm, a drone platform SLAM algorithm is built based on the three-dimensional laser sensor, the three-dimensional environment map is built in the environment without the GPS signal, the problems of indoor locating and indoor and outdoor locating merging of a drone are solved, requirements of multi-scene drone locating are met, on the basis of obtaining high-precision attitude information, laser data is merged, and the three-dimensional map is built.

The invention discloses an intelligent vehicle laser sensor and an online camera calibration method. Laser data and image data are accurately calibrated via the steps of camera calibration, offline calibration of a three-dimensional laser sensor and an image sensor, time alignment of laser data and image data, and online alignment of the laser sensor and the image sensor. The calibration system can be applied to multiple different road conditions and scene, to achieve online high precision calibration of laser and an image. After the laser and the image are calibrated, the information of the two sensors can be used for comprehensively analyzing a barrier and making an accurate decision, so that the method has is significant in sensing technology of an intelligent vehicle. Therefore, the technology can be widely applied to the fields of driverless vehicle visual navigation and intelligent vehicle visual assistance driving.

The invention relates to a road edge detection method based on laser radar scanning, which is used for acquiring road edges of a road in a road environment. The method comprises: a three-dimensional coordinate system is established by taking a road surface as the X-Y plane, a projection point of a laser radar on the X-Y plane as the origin, and the direction perpendicular to the road surface as the Z-axis direction; environmental multi-frame laser data is obtained by laser radar scanning for forming point cloud data; the point cloud data comprises a plurality of scan points containing three-dimensional coordinate information; for each frame of laser data, scan points on a scan line are subjected to gradient filtering to obtain road edge candidate points; and the candidate road edge points that meet the conditions are subjected to quadratic curve fitting to obtain a road edge detection result. The road edge detection method is not affected by the weather and light and has a wide range of applications.

The invention provides a three-dimensional building fine geometric reconstruction method integrating airborne and vehicle-mounted three-dimensional laser point clouds and streetscape images. The method comprises the following steps: (1) a quick modeling method based on airborne laser data; (2) combining the semantic segmentation framework of the vehicle-mounted point cloud and the image; and (3) amodel automatic enhancement algorithm fusing multi-source data. According to the method, airborne laser point cloud, vehicle-mounted laser point cloud and streetscape images are taken as research objects, model reconstruction, model enhancement and updating are taken as targets, joint processing of point cloud and image data of different platforms is realized, and the fusion potential of variousdata is fully mined. The final research result will perfect the fusion and fine modeling framework of vehicle-mounted-airborne data, promote the development of the point cloud data semantic segmentation technology, and serve the emerging application fields of unmanned driving and the like.

The invention discloses a modular unmanned vehicle positioning method and system based on visual inertia laser data fusion. The method comprises the following steps that (1), an acquisition module acquires current information of an unmanned vehicle through a monocular camera, a laser radar and an IMU; (2), according to the current information of the driverless vehicle collected in the step (1), apose estimation module performs pose estimation of the vehicle through a monocular odometer and an IMU pre-integration model to obtain pose information of the unmanned vehicle; and (3), a pose optimization module establishes a multi-sensor fusion optimization model according to the pose estimation information in the step (2), a weight coefficient dynamic adjustment module adjusts the optimizationproportion of each sensor to enhance the environmental adaptability, the optimal pose of the vehicle is obtained after optimization, and the optical pose is converted into a world coordinate system to obtain the real-time pose of the vehicle. The method can meet the requirements for accuracy and robustness of positioning of the unmanned vehicle in a complex environment, and is suitable for positioning of the unmanned vehicle in the complex environment.

The application discloses an unmanned vehicle lane dynamic obstacle detection method. The method comprises the steps of analyzing and processing the 64-wire laser data to detect and track the dynamic obstacles surrounding an unmanned vehicle; for a sector area in front of the unmanned vehicle having a higher accuracy, fusing a confidence distance theory with the 64-line laser data processing information and the motion state information outputted by the four-wire laser sensors to improve the detection accuracy of the obstacle motion states greatly; and then carrying out the time delay correction on the positions of the motion obstacles according to the fusion result; and finally, distinctively marking the positions occupied by the dynamic obstacles and the positions occupied by the static obstacles on an obstacle occupation grid map. According to the method, not only the obstacle motion information in an outdoor environment can be detected accurately, but also the dynamic obstacle position deviation brought by the sensor data processing time delay can be eliminated.

The invention relates to a mobile robot path planning method based on improved A star strategy. The method comprises the following steps: (a) processing laser data and mileage data acquired by a mobile robot by using a slam algorithm; (b) constructing a binaryzation raster map into a Voronoi map by utilizing a dynamic weinuo graph library; (c) constructing a corresponding Voronoi cost map according to the node coordinate on the Voronoi map; (d) transferring the starting position and the final position of the mobile robot to a map coordinate, and checking whether the starting and final coordinated indexes are legal or not; and (e) initializing g cost values of all nodes; and (f) smoothing the whole discrete path by using a smoother. The memory and calculation resources are greatly saved, the algorithmic convergence rate is accelerated; the Voronoi map is fused, so that the path is far away from barriers, and finally a best path is acquired by using the smoother.

The invention discloses a raster map building method based on local map splicing.The method comprises the following steps that 1, a robot scans and records environment information; 2, scanning data points are filtered to remove useless points; 3, local raster maps are calculated based on the filtered data through a ray tracking method; 4, sift feature points and corresponding feature descriptors of the local raster maps under two adjacent poses are calculated; 5, according to relevancy of the feature descriptors, the feature points are ranked, and feature points with small feather feature descriptors are filtered away; 6, the two local maps are subjected to iterative closest point algorithm ICP, and a transformation matrix of the two local maps is calculated; 7, the steps 1-6 are repeated, a transformation matrix of the whole path is recorded and completed, and finally data is merged to obtain a global raster map.The map is built through one-time laser data, so that the estimation error of the map is mainly the observation error of a laser sensor, and no estimation error exits.

The invention discloses a method for creating a 3D map based on a 3D laser, and belongs to the technical field of data processing. The method comprises the steps of performing rich information processing on point cloud data obtained by a 3D laser sensor to obtain an ordered laser point cloud data frame; performing feature extraction on the point cloud data frame to obtain feature points of the point cloud data frame; optimizing a transformation matrix according to an LM algorithm, and enabling the transformation matrix capable of enabling the sum of squares of distance errors of the matching of all feature points to be the minimum to serve the pose of radar; transforming each frame of the point cloud data into a point cloud map under a global coordinate system according to the pose of theradar, and transforming the point cloud map into a map expressed by voxels. According to the invention, rich information processing is performed on the original laser data, thereby providing a data basis for the creation of the 3D map. The method avoids a problem that it is inconvenient to perform filtering and denoising by adopting a point cloud map through adopting an expression mode of the voxel map, and the definition of the 3D map is improved.

The invention provides an object detection and identification method, device, electronic equipment and a storage medium; the object detection and identification method based on multi-sensor fusion comprises the following steps: obtaining visual observation data of one or more objects according to image data of an image acquisition device; clustering laser data of a laser radar sensor, and obtaining position information of one or more objects to serve as the laser observation data; obtaining millimeter wave observation data of one or more objects according to millimeter wave data of a millimeter wave radar sensor; fusing and filtering the visual observation data, the laser observation data and the millimeter wave observation data of the same object according to time sequence so as to obtainthe fused observation data, and detecting and identifying the object according to the fusion data. The method and device can improve the object detection and identification reliability, stability andrecognition rate.

The invention provides a trackless positioning navigation method and device. According to the method, the moving distance of a robot in a moving direction between adjacent time points (t-1) and t and the turning rate of the robot on a horizontal plane are measured, a position predication value of the robot is calculated through a preset dead reckoning equation and the measured moving distance and turning rate, local feature information in laser data obtained by measurement of a laser sensor is extracted and fused into a unified global feature map by the SLAM (Simultaneous Localization And Mapping) technology, and the processes of estimating the position of the robot and generating a topological graph are achieved, so that the positioning navigation stability and reliability are improved on the basis of reducing the cost and the operation and maintenance expenses, and the moving needs of the robot in a natural environment are met.

The invention provides a robot relocation method and device. The method comprises the steps of acquiring laser data transmitted by a robot currently and a local map corresponding to the position of the robot, matching the laser data with the local map, and judging whether the position of the robot currently located is correct according to a matching result; determining the area, corresponding to at least one prestored laser datum of which similarity to a histogram of the laser data is larger than or equal to a preset value, in the local map as a relocation candidate area if not; calculating the matching scores of different positions of the candidate area and the laser data, and determining the position with the largest matching score as the position of the relocated robot. According to the method, the robot is relocated when it is determined that the position of the robot currently located is incorrect, remapping is not needed, and increase of mapping cost and stop of a task which is being executed by the robot caused by remapping are avoided.

The invention aims at providing a positioning and map establishing method and system. A global optimum route from a starting point to a destination is determined in a grid map, determined according tomilemeter data and laser data, of a current environment to complete a navigation task of a mobile device; word bag data of a current image is extracted based on a re-positioning request, and key frames corresponding to historical word bag data having the similarity with the word bag data of the current image in a preset range is retrieved through a lexicographic tree; feature matching is performed based on the key frames to determine the posture and position of the current image in a world coordinate system, and the posture and position of the mobile device under world coordinates are determined according to the posture and position of the current image in the world coordinate system and the installing posture and position of an image sensor in the mobile device to complete re-positioning. Accordingly, the mobile device can perform map establishing, positioning and navigation tasks in an unknown environment, makes global re-positioning easy to achieve and can be used for navigation and obstacle avoidance tasks of mobile devices.

The invention discloses a scanning laser based large-scale three-dimensional terrain modeling method. The scanning laser based large-scale three-dimensional terrain modeling method comprises the following steps of: firstly perceiving a surrounding environment through the scanning laser arranged on a mobile robot platform, and transforming original laser data into three-dimensional point clouds through coordinate transformation; secondly preprocessing the three-dimensional point clouds by adopting a median filter method, and constructing an octree structure to complete data storage; then carrying out fusion processing on data by adopting a Gaussian mixed model based randomization method to build a terrain environment model in real time; and finally detecting and processing an obstructed area positioned in the terrain environment model to further enhance model accuracy. In the invention, the problem of real-time modeling of a large-scale complex terrain is effectively solved by adopting the low-cost two-dimensional scanning laser; and good balance between the model accuracy and real-time property is realized in such a way that randomization processing is carried out on various uncertainties of the terrain environment model, and therefore, wide requirements of different fields, such as a GIS (Geographic Information System) system or unmanned autonomous navigation and the like, can be met.

The invention discloses a method for automatically acquiring a vehicle training sample based on multi-modal sensor data. The method comprises the following steps of: detecting a vehicle based on laser data and positioning data, namely acquiring a two-dimensional coordinate relative to a data acquisition vehicle according to a distance and an angle of the laser data and a laser sensor calibration parameter so as to describe horizontal contour information of an object; and extracting a time sequence of parameters such as the position and direction of a candidate vehicle relative to the data acquisition vehicle by analyzing a shape and detecting and tracking a mobile object; and extracting a vision image sample, namely projecting the candidate vehicle into an image according to the position and direction of the candidate vehicle at each moment on the basis of a geological relation between the laser sensor and image acquisition equipment to produce a region of interest, correcting the region of interest by using a detector, calculating a relative view angle of each candidate vehicle relative to a camera according to the parameters such as position and direction, removing image frame samples with similar view angles, and automatically extracting sample pictures of the candidate vehicle under different view angles.

The present invention discloses an AGV positioning system and method for fusing a 2D environmental map and a sparse artificial landmark. The system comprises a vehicle-mounted device, an artificial landmark, and a 2D environmental map. The 2D environmental map is established by the vehicle-mounted device according to a current environment. The artificial landmark comprises position information andnumber information. Each artificial landmark is uniquely numbered in the environmental map. The vehicle-mounted device comprises a laser radar, a milemeter, a gyroscope, and a positioning unit. The positioning unit comprises a laser data processing module, a sensor data storage module, a point cloud matching graph construction module, an environment positioning module, an artificial landmark positioning module, and a positioning result fusing module. The point cloud matching graph construction module is used for graph construction. After the 2D environmental map is obtained, the environment positioning module and the artificial landmark positioning module are used for obtaining a positioning result. Finally, the positioning result fusing module is used for fusing positioning results and providing final positioning information, so that high-precision positioning of an AGV car in environment is implemented.

The invention belongs to the technical field of autonomous environment sensing of robots and relates to an automatic calibration method between three-dimensional laser and monocular vision. The method is characterized in that the automatic combined calibration between the three-dimensional laser and the monocular vision can be completed through a designed calibration device. The process of extracting laser data feature corners can be divided into two stages of detection and correction. The mapping association of original three-dimensional laser data with a distance measurement data matrix after binarization and the statistical analysis are carried out during the detection stage; and the matching through a standard template constituted by black and white corners in a calibration plate is carried out during the correction stage, thereby improving the corner extraction precision and further adopting the iterative optimization method for solution. The automatic calibration method has the beneficial effects of effectively reducing the noise and the affects of an incident angle on laser distance measurement data, and the calibration process realizes the automation and the integration of the extraction and the matching of laser-vision data feature corners, thereby laying a foundation for multi-sensor information fusion.

The invention solves the problems such as feature extraction, asynchronization and synchronization, feature relevance and data difference value to fuse visual data and laser radar data so as to generate three-dimensional color depth image data, namely a three-dimensional color laser data point cloud, thereby providing precise distance information and rich environment information, effectively overcoming the defects of the traditional laser radar and the visual sensor in the aspects of robustness, information amount, precision and cost. The invention integrates a two-dimensional laser radar, a monocular vision sensor, an inertial navigation data measuring unit, a driving motor and the like into an information fusion-based three-dimensional color laser radar integral unit with universal applicability and high precision, and utilizes inertial navigation data and visual data to perform secondary alignment on laser radar data, the structure is simple, equipment does not need to be subjected to precise calibration, the performance is reliable and stable, the practicability is strong, and the method and the device can be widely used in various indoor and outdoor environments under the motion condition, and have certain universal applicability.

From a survey vehicle, two types of data are obtained: images from a camera and reflections from a laser. The laser data is filtered in order to detect assets. The detected assets are then processed to locate and measure the assets. Once this information has been obtained, it is combined with the images captured by the camera in order to recognize the assets.

The invention discloses a line feature map creation method of a mobile robot based on a laser range finder and belongs to the technical field of mobile robot map creation. The line feature map creation method of the mobile robot based on the laser range finder includes the following steps: firstly, starting the laser range finder to scan an external environment, then preprocessing scanned laser data through an average filtering method to filter noise points; utilizing exponential distribution to approximate posterior distribution of laser data points, conducting region segmentation on the laser measurement data points through a dynamic threshold method, dividing the laser measurement data points into N region pieces after the region segmentation, and conducting segment fitting on the data points in the regions through a golden section method; and extracting feature corners through a method of combining Hough transformation and an area threshold value, achieving transition from an image space to a parameter space, building local environment maps, and achieving the fusion of the local environment maps by utilizing a sector matching method. The line feature map creation method of the mobile robot based on the laser range finder has the advantages of being easy in calculation and high in accuracy and improving rapidity of algorithm execution.

The invention brings forward a dancing robot indoor pedestrian tracing method based on a laser radar. The method comprises the following steps of: 1, laser data preprocessing; 2, density-based laser data clustering; 3, pedestrian identification based on laser acquisition points; 4, graphical display; 5, pedestrian tracking based on particle filtering; and 6, pedestrian movement track drafting. According to the invention, pedestrians with different forms at different distances are identified by use of a single laser radar, the pedestrians at different movement modes such as static, walking and the like can be tracked, the tracking scope is wide, the real-time performance is good, and the identification and tracking accuracy is high.

The invention discloses a precise plane coordinate correction method in laser radar scanning measurement. The method comprises the following steps of: a, designing and spraying a control sign: arranging control signs along the path in a staggered form on the two sides of a highway; b, selecting a control point for the feature signs formed by two crossed straight lines along the existing road; c, laser radar scanning: determining the laser radar scanning measurement mode; d, measuring a control point, wherein the control point plane measurement adopts GPS (global position system) static positioning measurement, and a net structure is formed; e, controlling sign extraction: accurately extracting the position of the laser radar point cloud data plane of the control sign by use of the information of the laser radar point cloud data; and f, precisely correcting the laser radar point cloud plane coordinate: performing precise plane coordinate processing on the laser data according to the GPS measurement result at the control point and the laser radar point cloud extraction result of the control sign. The method has high precision, low cost and high efficiency, and is easy to implement, simple and convenient to operate and suitable for precise plane coordinate correction in the laser radar scanning measurement for road reconstruction and expansion.

Aspects of the present disclosure relate to using an object detected at long range to increase the accuracy of a location and heading estimate based on near range information. For example, an autonomous vehicle may use data points collected from a sensor such as a laser to generate an environmental map of environmental features. The environmental map is then compared to pre-stored map data to determine the vehicle's geographic location and heading. A second sensor, such as a laser or camera, having a longer range than the first sensor may detect an object outside of the range and field of view of the first sensor. For example, the object may have retroreflective properties which make it identifiable in a camera image or from laser data points. The location of the object is then compared to the pre-stored map data and used to refine the vehicle's estimated location and heading.

From a survey vehicle, two types of data are obtained: images from a camera and reflections from a laser. The laser data is filtered in order to detect assets. The detected assets are then processed to locate and measure the assets. Once this information has been obtained, it is combined with the images captured by the camera in order to recognize the assets.

The invention discloses a robot map building method suitable for a large-scale transformer substation environment. A particle filter algorithm is used for building a map, discrete particles are used for approximating posterior probability distribution of a robot posture, each particle independently maintains a map of the transformer substation, for the problem of large calculation amount and insufficient power of the robot, an SLAM algorithm is optimized, a rosbag software package based on ROS is combined to be changed, only speedometer and laser data packets are recorded in the field of the transformer substation, if the power of the robot is used up in the process, the robot can be restarted after being charged, data of the transformer substation can be stored as a plurality of data packets, the speedometer among the data packets is unnecessarily continuous, and after the data packets are completely recorded, the map is built in a way of playing back the data packets by virtue of rosbag. By adopting the method, a high-precision raster map of a large-scale transformer substation environment can be built, and the probability of map building failure caused by the positioning mistake can be reduced.