DMCA
Efficient Multi-View Object Recognition and Full Pose Estimation
| Citations: | 10 - 2 self |
BibTeX
@MISC{Collet_efficientmulti-view,
author = {Alvaro Collet and Siddhartha S. Srinivasa},
title = {Efficient Multi-View Object Recognition and Full Pose Estimation},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract — We present an approach for efficiently recognizing all objects in a scene and estimating their full pose from multiple views. Our approach builds upon a state of the art single-view algorithm which recognizes and registers learned metric 3D models using local descriptors. We extend to multiple views using a novel multi-step optimization that processes each view individually and feeds consistent hypotheses back to the algorithm for global refinement. We demonstrate that our method produces results comparable to the theoretical optimum, a full multi-view generalized camera approach, while avoiding its combinatorial time complexity. We provide experimental results demonstrating pose accuracy, speed, and robustness to model error using a three-camera rig, as well as a physical implementation of the pose output being used by an autonomous robot executing grasps in highly cluttered scenes. I.
Keyphrases
full pose estimation efficient multi-view object recognition local descriptor global refinement autonomous robot three-camera rig consistent hypothesis combinatorial time complexity art single-view algorithm full multi-view pose accuracy pose output theoretical optimum cluttered scene full pose camera approach experimental result multiple view novel multi-step optimization physical implementation
