Abstract | ||
---|---|---|
Object pose estimation is a fundamental problem for a robot when manipulating an object. In this paper, we propose a method for estimating the pose of an object using a 2D image and a 3D point cloud. The Speeded Up Robust Feature (SURF) descriptors between the model image and input image were used to match the keypoints. The pose of an object was estimated using the 3D points corresponding to these matches. To produce more accurate results, the outliers were removed from these matches using Random Sample Consensus (RANSAC) and the result was refined using the Iterative Closest Point (ICP) algorithm. The experimental result demonstrated the high efficiency of our method. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/CoASE.2012.6386413 | CASE |
Keywords | Field | DocType |
2d-3d sensor fusion,object pose estimation,image fusion,3d point cloud,speeded up robust feature descriptors,surf,iterative closest point algorithm,icp,pose estimation,2d image,feature extraction,ransac,random sample consensus,iterative methods,6dof pose estimation,solid modeling,data models,object recognition,estimation,computational modeling | Computer vision,Pattern recognition,Image fusion,RANSAC,Computer science,3D pose estimation,Pose,Feature extraction,Artificial intelligence,Point cloud,Iterative closest point,Cognitive neuroscience of visual object recognition | Conference |
ISSN | ISBN | Citations |
2161-8070 | 978-1-4673-0429-0 | 0 |
PageRank | References | Authors |
0.34 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong-Deuk Shin | 1 | 1 | 1.39 |
Jae-Han Park | 2 | 31 | 8.60 |
Moonhong Baeg | 3 | 40 | 7.51 |