Title :
Point cloud registration with 2D and 3D fusion information on mobile robot integrated vision system
Author :
Xu Zhang ; Lin Li ; Dawei Tu
Author_Institution :
Fac. of Mech. Eng. & Autom., Shanghai Univ., Shanghai, China
Abstract :
Multi-view point clouds registration method based on the 2D and 3D fusion information is proposed. First the joint calibration of the CCD camera and 3D laser radar system is conducted to fuse the image information and range information. Then, matching feature points in the images are obtained with the SIFT algorithm. Based on the joint calibration results and the images feature matching points, the point clouds feature matching points are determined. After that, the initial value of the different view point cloud space transform is calculated with the RANSAC, and ICP algorithm is adopted to optimize the results. Finally, the proposed method was implemented on a mobile robot and verified effective in the experiment.
Keywords :
cameras; feature extraction; image fusion; image matching; image registration; iterative methods; mobile robots; robot vision; 2D fusion information; 3D fusion information; 3D laser radar system; CCD camera; ICP algorithm; RANSAC; SIFT algorithm; charge-coupled device camera; feature points matching; image information; iterative closest point algorithm; mobile robot integrated vision system; multiview point clouds registration method; point cloud space transform; range information; scale-invariant feature transform; Calibration; Cameras; Laser fusion; Laser radar; Radar imaging; Three-dimensional displays;
Conference_Titel :
Robotics and Biomimetics (ROBIO), 2013 IEEE International Conference on
Conference_Location :
Shenzhen
DOI :
10.1109/ROBIO.2013.6739625
