Full Text:   <3260>

CLC number: TP391.7

On-line Access: 

Received: 2007-07-04

Revision Accepted: 2007-11-05

Crosschecked: 0000-00-00

Cited: 2

Clicked: 6173

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE A 2008 Vol.9 No.4 P.500-509


Stereo vision based SLAM using Rao-Blackwellised particle filter

Author(s):  Er-yong WU, Gong-yan LI, Zhi-yu XIANG, Ji-lin LIU

Affiliation(s):  Department of Information Science and Electrical Engineering, Zhejiang University, Hangzhou 310027, China; more

Corresponding email(s):   wueryong343@sohu.com, xiangzy@zju.edu.cn

Key Words:  Robot, Vision based SLAM, SIFT, Feature management

Er-yong WU, Gong-yan LI, Zhi-yu XIANG, Ji-lin LIU. Stereo vision based SLAM using Rao-Blackwellised particle filter[J]. Journal of Zhejiang University Science A, 2008, 9(4): 500-509.

@article{title="Stereo vision based SLAM using Rao-Blackwellised particle filter",
author="Er-yong WU, Gong-yan LI, Zhi-yu XIANG, Ji-lin LIU",
journal="Journal of Zhejiang University Science A",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T Stereo vision based SLAM using Rao-Blackwellised particle filter
%A Er-yong WU
%A Gong-yan LI
%A Zhi-yu XIANG
%A Ji-lin LIU
%J Journal of Zhejiang University SCIENCE A
%V 9
%N 4
%P 500-509
%@ 1673-565X
%D 2008
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A071361

T1 - Stereo vision based SLAM using Rao-Blackwellised particle filter
A1 - Er-yong WU
A1 - Gong-yan LI
A1 - Zhi-yu XIANG
A1 - Ji-lin LIU
J0 - Journal of Zhejiang University Science A
VL - 9
IS - 4
SP - 500
EP - 509
%@ 1673-565X
Y1 - 2008
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A071361

We present an algorithm which can realize 3D stereo vision simultaneous localization and mapping (SLAM) for mobile robot in unknown outdoor environments, which means the 6-DOF motion and a sparse but persistent map of natural landmarks be constructed online only with a stereo camera. In mobile robotics research, we extend FastSLAM 2.0 like stereo vision SLAM with “pure vision” domain to outdoor environments. Unlike popular stochastic motion model used in conventional monocular vision SLAM, we utilize the ideas of structure from motion (SFM) for initial motion estimation, which is more suitable for the robot moving in large-scale outdoor, and textured environments. SIFT features are used as natural landmarks, and its 3D positions are constructed directly through triangulation. Considering the computational complexity and memory consumption, Bkd-tree and Best-Bin-First (BBF) search strategy are utilized for SIFT feature descriptor matching. Results show high accuracy of our algorithm, even in the circumstance of large translation and large rotation movements.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article


[1] Arulampalam, M.S., Maskell, S., Gordon, N., 2002. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. on Signal Processing, 50(2):174-188.

[2] Beis, J.S., Lowe, D.G., 1997. Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.1000-1006.

[3] Davison, A.J., 2003. Real-Time Simultaneous Localisation and Mapping with a Single Camera. Proc. Ninth IEEE Int. Conf. on Computer Vision, p.1403-1410.

[4] Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O., 2007. MonoSLAM: real-time single camera SLAM. IEEE Trans. on Pattern Anal. Machine Intell., 29(6):1052-1067.

[5] Eade, E., Drummond, T., 2006. Scalable Monocular SLAM. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.469-476.

[6] Elinas, P., Sim, R., Little, J.J., 2006. ( SLAM: Stereo Vision Slam Using the Rao-Blackwellised Particle Filter and a Novel Mixture Proposal Distribution. Proc. IEEE Int. Conf. on Robotics and Automation, p.1564-1570.

[7] Hartley, R., Zisserman, A., 2003. Mutiple View Geometry in Computer Vision. Cambridge University Press.

[8] Horn, B., 1987. Closed-form solution of absolute orientation using unit quaternion. J. Opt. Soc. Am., 4:629-642.

[9] Jensfelt, P., Kragic, D., Folkesson, J., Bjorkman, M., 2006. A Framework for Vision Based Bearing Only 3D SLAM. Proc. IEEE Int. Conf. on Robotics and Automation, p.1944-1950.

[10] Julier, S., Uhlmann, J., 1996. A General Method for Approximating Nonlinear Transformations of Probability Distributions. Technical Report, Department of Engineering Science, University of Oxford. Http://www.robots.ox.ac.uk/siju/work/publications/lettersize/Unscented.zip

[11] Laurent, I., 2006. The iLab Neuromorphic Vision C++ Toolkit. University of Southern California. Http://ilab.usc.edu/toolkit/home.shtml

[12] Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Computer Vision, 60(2):91-110.

[13] Montemerlo, M., Thrun, S., Koller, D., Wegbreit, B., 2003. FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges. Proc. Int. Joint Conf. on Artificial Intelligence, p.1151-1156.

[14] Murphy, K., 1999. Bayesian Map Learning in Dynamic Environments. In: Advances in Neural Information Processing Systems. MIT Press, Denver, USA, p.1015-1021.

[15] Nister, D., Naroditsky, O., Bergen, J., 2004. Visual Odometry. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.652-659.

[16] Procopiuc, O., Agarwal, P., Arge, L., Vitter, J.S., 2002. Bkd-tree: A Dynamic Scalable Kd-tree. In: Advances in Spatial and Temporal Databases (SSTD). Springer Press, Berlin/Heidelberg, 2750:46-65.

[17] Robinson, J.T., 1981. The K-D-B-Tree: A Search Structure for Large Multidimensional Dynamic Indexes. Proc. Int. Conf. on Management of Data, p.10-18.

[18] Sim, R., Elinas, P., Griffin, M., Little, J.J., 2005. Vision-based SLAM Using the Rao-Blackwellised Particle Filter. Proc. IJCAI Workshop on Reasoning with Uncertainty in Robotics, p.9-16.

[19] Vergauwen, M., Pollefeys, M., Goll, L.V., 2003. A stereo-vision system for support of planetary surface exploration. Machine Vision and Applications, 14(1):5-14.

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE