A synchronous localization and mapping method for vision-inertia-laser fusion mainly relates to the technical fields of multi-sensor fusion, SLAM and the like. In order to solve a problem that single sensor SLAM has low precision and is easy to lose in localization and mapping, the invention provides a robust high precision vision, inertia, laser radar fusion SLAM system. A tightly-coupled visual inertia odometer is further optimized through laser radar scanning and matching so as to obtain a more accurate localization result. And when a camera or a laser radar degenerates, and a visual inertia module or a scanning and matching module can not work normally, a system automatically integrates remaining workable modules to maintain stable pose estimation. In order to remove cumulative errors, loopback detection based on an appearance and neighboring matching based on point cloud are added, and then six-degree-of-freedom pose optimization is performed to maintain global consistency. In the invention, robust high-precision localization and mapping effects can be obtained.

Synchronous localization and mapping method for vision-inertia-laser fusion

The invention provides a cloud control aerial image photogrammetry method for LiDAR point cloud data. The method comprises the steps that firstly, GPS/POS auxiliary aerial triangulation is conducted on an image, initial camera distortion and image orientation parameters are calculated, and meanwhile sparse feature point cloud and image three-dimensional feature lines are generated; secondly, rigidregistration is performed on the LiDAR point cloud and the image sparse feature point cloud through ICP and ICL algorithms, rigid transformation parameters of the sparse feature point cloud relativeto the LiDAR point cloud are calculated, and exterior orientation elements of the image are updated by using the rigid transformation parameters; and finally, regional network adjustment is carried out under the constraint of LiDAR point cloud control information, and image orientation parameters are optimized. Rigid registration and LiDAR constrained regional network adjustment are repeatedly iterated until the variation of the error in image orientation meets a preset threshold value. According to the method, large-proportion high-precision geometric orientation of the aerial image under thecondition of no field control point is realized by taking the LiDAR point cloud as a geometric reference without dependence on the field control point, and the efficiency of image photogrammetry processing in the information era is greatly improved.

LiDAR data'cloud control 'aerial image photogrammetry method

The invention discloses an RGBD camera large-scale three-dimensional scene construction method and system, and the method comprises the following steps: obtaining a depth image and a color image of anRGBD camera, generating a three-dimensional point cloud, and registering the point cloud to a laser radar reference system; acquiring robot attitude data and scanning point data of the laser radar, and processing the data by using a local optimization algorithm of a Cartographerd algorithm to generate a subgraph and robot odometer information; and binding the generated sub-graphs with the corresponding point clouds according to the robot odometer information, and splicing the sub-graphs to generate a three-dimensional map.

RGBD camera large-scale three-dimensional scene construction method and system

The invention relates to a structure adjustable multiple laser radar coupling system and a control method thereof, and belongs to the field of 3D laser radar detection. The system comprises 3D laser radars, a radar data synchronizer, a DC motor, a motor driving unit, a transmission mechanism, a hydraulic rod, a radar elevating platform and a control unit; and an angle gradual change type guide rail and system parts are mounted on a system bracing frame. The structure adjustable multiple laser radar coupling system can determine the condition according to map, GPS and IMU information, a physical arrangement array of the multiple laser radars is changed according to different condition demands to realize different point cloud data fusion strategies of the laser radars, the point cloud density of the region of interest in specific condition is improved, and blind areas of perception is reduced. The system and method are characterized by high integrated level, high sensitivity and low cost, the disadvantages that a single multi-line laser radar is high in cost and large in perception blind area are overcome, the laser radars can be used more widely, and the using efficiency of the laser radars is improved.

Structure adjustable multiple laser radar coupling system and control method thereof

The invention discloses a laser radar and camera fusion device and a calibration method. The laser radar and camera fusion device comprises a vertical lifting platform and a calibration plate bracket,a working table is arranged on a working guide rail on the vertical lifting table; a camera and a laser radar are fixedly mounted on the working table; a calibration plate is fixedly mounted on the calibration plate bracket; the laser radar scans the calibration plate to obtain a horizontal straight line, finds left and right end points of the straight line on the boundary of the calibration plate, then moves for multiple times at the same interval to obtain multiple groups of end points on the left and right side lines, and performs fitting to approximately obtain a linear equation of the left and right boundaries so as to obtain the end points of the calibration plate; pixel points at the positions where the upper end points of the camera pictures are located correspond to the end points, so that a pose relation expression of the camera and the radar can be obtained; by applying the laser radar and camera fusion calibration method, the characteristics under a radar point cloud sparse scene can be obtained, the joint expressions of internal and external parameters can be solved, and the internal parameters of the camera do not need to be measured in advance.

Laser radar and camera fusion device and calibration method

An asynchronous on-line calibration method for multi-sensor fusion is disclosed. The mutual conversion relationship between the coordinate systems of the three sensors are calibrated, and the measurement information of the plurality of sensors is unified into the same coordinate system, The traditional calibration method is limited to the calibration between two sensors, and requires strict time synchronization, so the calibration process is more complex. The invention calculates the motion of the laser radar, the camera and the inertial measurement unit (IMU) respectively, obtains the motionof different sensors in the same time interval by using linear interpolation, and finally obtains the external rotation between two sensors by aligning the rotation sequence of the three sensors. Theinvention can obtain more accurate external orientation between the lidar, the camera and the inertial measurement unit (IMU), and provides initial value for subsequent calibration.

An asynchronous on-line calibration method for multi-sensor fusion

The invention relates to a multi-line lidar and camera joint calibration method based on fine radar scanning edge points, which mainly relates to the technical fields of robot vision, multi-sensor fusion and the like. Because of the influence of the resolution of lidar, the scanned edge points are often not accurate enough, so the calibration results are not accurate enough. According to the characteristic that the range of the lidar point is abrupt at the edge, the invention searches and compares for many times, and takes the point closer to the edge as the standard point. By detecting the circle in the camera image and radar edge points, the translation between the camera and the lidar is calculated according to the pinhole camera model. The calibration parameter C is searched in the neighborhood space of the obtained translation vector to find the calibration result that minimizes the projection error. The invention can extract the points swept by the lidar on the edge of the objectwith high precision, avoids the problem of insufficient precision caused by low resolution of the lidar, and improves the calibration precision.

A multi-line lidar and camera joint calibration method based on fine radar scanning edge points

An SLAM (simultaneous localization and mapping) method combining GPS (global positioning system) and radar odometer comprises the steps of 1) acquiring differential GPS data and point cloud data fromlaser radar; 2) processing the GPS data to obtain displacement (X, Y, Z) and attitude RPY (rolling, pitching and yawing) angles; 3) matching the GPS data and point cloud data of LiDAR by means of timestamp aligning; 4) checking reliability of the GPS data according to the attitude data from GPS processing of step 2) and the point cloud data of LiDAR; 5) using a LOAM (Lidar odometry and mapping) method to acquire (X, Y, Z) and RPY angles; 6) in a place with reliable GPS data, using the GPS-acquired attitude as a final attitude; in a section with unreliable GPS data, using GPS attitudes of startpoint and endpoint of the section to optimize the attitude of the LOAM method to acquire a final attitude; 7) using the attitude output in step 6) to transform point cloud data of laser radar to a world coordinate system to obtain a final global map. The method herein is suitable for construction of large-range city three-dimensional maps.

SLAM (simultaneous localization and mapping) method combining GPS (global positioning system) and radar odometer

Lidar has been used in many areas of computer vision and robotics, like 3D reconstruction, autonomous navigation and positioning. Extracting accurate edges for 3d point clouds plays a key role in some applications. However, few people are concerned about this issue. In this paper, we present a novel pipeline for refining the position of the edge using the rotation of the lidar itself and its depth discontinuity at the edges. Our method consists of two parts. First, edge points are extracted according to the depth difference in the reference frame of point cloud. Then, we apply our refining strategy to obtain the more accurate edge points. The novelty is that our approach compensates for hardware deficiencies through algorithms, improving the accuracy of lidar edge points. The experiment provides comparisons of the edge points extracted by the direct method and our method.

Refinement of Edge Extraction Based on Lidar Point Cloud

A loopback detection method based on point cloud segment matching constraint and trajectory drift optimization is proposed, which adopts real-time lidar odometer and LOAM system, but the LOAM system will have large drift after long-time mapping, so a method based on point cloud segment matching constraint and trajectory drift optimization is proposed. By segmenting, describing and matching the point cloud acquired by lidar, the loop relationship is found, and the loop is adjusted by using explicit loop closure ELCH algorithm after the loop is found, and an optimization algorithm is proposed toeliminate the local inconsistencies in the adjustment process of point cloud map. After optimization, the invention proposes a posture prediction and compensation algorithm to predict and compensatethe posture after the loop. So as to maximize the effect of reducing drift error.

A loop detection method based on point cloud segment matching constraint and trajectory drift optimization

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Feng Yuting

Author Tools

Chat about Author