Share Email Print
cover

Proceedings Paper

3D model-based detection and tracking for space autonomous and uncooperative rendezvous
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In order to fully navigate using a vision sensor, a 3D edge model based detection and tracking technique was developed. Firstly, we proposed a target detection strategy over a sequence of several images from the 3D model to initialize the tracking. The overall purpose of such approach is to robustly match each image with the model views of the target. Thus we designed a line segment detection and matching method based on the multi-scale space technology. Experiments on real images showed that our method is highly robust under various image changes. Secondly, we proposed a method based on 3D particle filter (PF) coupled with M-estimation to track and estimate the pose of the target efficiently. In the proposed approach, a similarity observation model was designed according to a new distance function of line segments. Then, based on the tracking results of PF, the pose was optimized using M-estimation. Experiments indicated that the proposed method can effectively track and accurately estimate the pose of freely moving target in unconstrained environment.

Paper Details

Date Published: 15 October 2015
PDF: 6 pages
Proc. SPIE 9676, AOPC 2015: Optical Design and Manufacturing Technologies, 967618 (15 October 2015); doi: 10.1117/12.2224964
Show Author Affiliations
Yang Shang, National Univ. of Defense Technology (China)
Hunan Key Lab. of Videometrics and Vision Navigation (China)
Yueqiang Zhang, National Univ. of Defense Technology (China)
Hunan Key Lab. of Videometrics and Vision Navigation (China)
Haibo Liu, National Univ. of Defense Technology (China)
Hunan Key Lab. of Videometrics and Vision Navigation (China)


Published in SPIE Proceedings Vol. 9676:
AOPC 2015: Optical Design and Manufacturing Technologies
Lin Li; Kevin P. Thompson; Ligong Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top