Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online*

Lu Wei; Xiang Zhi-yu; Liu Ji-lin

doi:10.1631/FITEE.1400139

Your Location：

Home >

Browse articles >

Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online*

Computer & Automation | Updated：2022-06-06

- Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online*
  Enhanced Publication
- 基于在线建立与匹配压缩全景路标的增强型视觉里程计
- Frontiers of Information Technology & Electronic Engineering Vol. 16, Issue 2, Pages: 152-165(2015)
- Affiliations：
  
  1.Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China
  2.Zhejiang Provincial Key Laboratory of Information Network Technology, Hangzhou 310027, China
- Author bio：
  
  †E-mail:lwhfh01@zju.edu.cnxiangzy@zju.edu.cn
  ‡Corresponding Author
- Funds：
- DOI：10.1631/FITEE.1400139
  CLC：
- Published：2015-02，
  
  Received：20 April 2014，
  
  Revised：06 January 2015，
  
  Accepted：2014-11-24
- Accepted：
Scan QR Code
LU WEI, XIANG ZHI-YU, LIU JI-LIN. Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online*. [J]. Frontiers of information technology & electronic engineering, 2015, 16(2): 152-165.
DOI：

LU WEI, XIANG ZHI-YU, LIU JI-LIN. Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online*. [J]. Frontiers of information technology & electronic engineering, 2015, 16(2): 152-165. DOI： 10.1631/FITEE.1400139.

摘要

目的

高效精确定位是移动机器人智能导航的先决条件。传统视觉定位系统，如视觉里程计（VO）和同时定位与三维重建（SLAM）算法，存在两点不足：一是由累积定位误差引起的漂移问题，二是由光照变化和移动物体导致的错误运动估计结果。

创新

通过引入全景相机到传统双目VO系统，提出一种增强型VO，高效利用全景相机360˚视场角信息。（1）在线建立路口场景压缩全景路标库；（2）机器人以任意方向重新访问路标时，对定位结果进行全局校正；（3）当双目立体VO不能提供可靠定位信息时对航向角估计结果进行校正；（4）为高效利用信息量较多的全景图像，引入压缩感知概念并提出一种自适应压缩特征。

方法

首先，在压缩亮度特征基础上，增加压缩SURF特征提高其描述能力，通过分析特征区分度，使压缩特征可以根据具体图像特点自适应调节，最终构建自适应压缩特征（ACF

图2），该特征计算速度快（表3）、描述能力强（图6、7，表1），有效提高全景图像信息利用效率。然后，使用ACF对全景路标图像进行描述，提出一种任意方向的路标图像匹配算法，若当前全景图像与路标图像匹配成功，则对当前定位结果进行全局位姿校正（图4），抑制大范围环境中定位路径漂移问题（图10、11）。最后，介绍基于图像片匹配的航向角鲁棒估计方法，当双目视觉里程计因特征跟踪质量差而导致运动估计结果不稳定时，对局部运动估计结果进行校正，提高运动估计的精度（图9）。

结论

提出的增强型视觉里程计系统可以准实时提供可靠定位结果，极大抑制大范围挑战性环境中传统VO漂移问题和运动估计错误问题。实验结果显示，所提算法大幅度提高传统VO的准确性和鲁棒性。

Abstract

Efficient and precise localization is a prerequisite for the intelligent navigation of mobile robots. Traditional visual localization systems

such as visual odometry (VO) and simultaneous localization and mapping (SLAM)

suffer from two shortcomings: a drift problem caused by accumulated localization error

and erroneous motion estimation due to illumination variation and moving objects. In this paper

we propose an enhanced VO by introducing a panoramic camera into the traditional stereo-only VO system. Benefiting from the 360° field of view

the panoramic camera is responsible for three tasks: (1) detecting road junctions and building a landmark library online; (2) correcting the robot’s position when the landmarks are revisited with any orientation; (3) working as a panoramic compass when the stereo VO cannot provide reliable positioning results. To use the large-sized panoramic images efficiently

the concept of compressed sensing is introduced into the solution and an adaptive compressive feature is presented. Combined with our previous two-stage local binocular bundle adjustment (TLBBA) stereo VO

the new system can obtain reliable positioning results in quasi-real time. Experimental results of challenging long-range tests show that our enhanced VO is much more accurate and robust than the traditional VO

thanks to the compressive panoramic landmarks built online.

关键词

视觉里程计全景路标路标匹配压缩感知自适应压缩特征

Keywords

Visual odometryPanoramic landmarkLandmark matchingCompressed sensingAdaptive compressive feature

references

H Bay, T Tuytelaars, L van Gool. SURF: speeded up robust features. 2006. Proc. 9th European Conf. on Computer Vision. 404-417. DOI:10.1007/11744023_32http://doi.org/10.1007/11744023_32.

X Cai, Z Zhang, H Zhang, 等. Soft consistency reconstruction: a robust 1-bit compressive sensing algorithm. arXiv:1402.5475, 2014. (preprint).

EJ Candes, T Tao. Decoding by linear programming. IEEE Trans Inform Theory, 2005. 51(12):4203-4215. DOI:10.1109/TIT.2005.858979http://doi.org/10.1109/TIT.2005.858979.

DL Donoho. Compressed sensing. IEEE Trans Inform Theory, 2006. 52(4):1289-1306. DOI:10.1109/TIT.2006.871582http://doi.org/10.1109/TIT.2006.871582.

H Durrant-Whyte, T Bailey. Simultaneous localization and mapping: part I. IEEE Robot Autom Mag, 2006. 13(2):99-110. DOI:10.1109/MRA.2006.1638022http://doi.org/10.1109/MRA.2006.1638022.

MA Fischler, RC Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM, 1981. 24(6):381-395. DOI:10.1145/358669.358692http://doi.org/10.1145/358669.358692.

F Fraundorfer, D Scaramuzza. Visual odometry: part II. Matching, robustness, optimization, and applications. IEEE Robot Autom Mag, 2012. 19(2):78-90. DOI:10.1109/MRA.2012.2182810http://doi.org/10.1109/MRA.2012.2182810.

D Galvez-López, JD Tardos. Bags of binary words for fast place recognition in image sequences. IEEE Trans Robot, 2012. 28(5):1188-1197. DOI:10.1109/TRO.2012.2197158http://doi.org/10.1109/TRO.2012.2197158.

A Geiger, P Lenz, R Urtasun. Are we ready for autonomous driving? The KITTI vision benchmark suite. 2012. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 3354-3361. DOI:10.1109/CVPR.2012.6248074http://doi.org/10.1109/CVPR.2012.6248074.

BKP Horn. Closed-form solution of absolute orientation using unit quaternions. JOSA A, 1987. 4(4):629-642. DOI:10.1364/JOSAA.4.000629http://doi.org/10.1364/JOSAA.4.000629.

K Konolige, M Agrawal, J Solà. Large-scale visual odometry for rough terrain. 2011. Proc. 13th Int. Symp. on Robotics Research. 201-212. DOI:10.1007/978-3-642-14743-2_18http://doi.org/10.1007/978-3-642-14743-2_18.

Y Liu, H Zhang. Visual loop closure detection with a compact image descriptor. 2012. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems. 1051-1056. DOI:10.1109/IROS.2012.6386145http://doi.org/10.1109/IROS.2012.6386145.

W Lu, Z Xiang, J Liu. High-performance visual odometry with two-stage local binocular BA and GPU. 2013. Proc. IEEE Intelligent Vehicles Symp.. 1107-1112. DOI:10.1109/IVS.2013.6629614http://doi.org/10.1109/IVS.2013.6629614.

R Munguia, A Grau. Monocular SLAM for visual odometry. 2007. Proc. IEEE Int. Symp. on Intelligent Signal Processing. 1-6. DOI:10.1109/WISP.2007.4447564http://doi.org/10.1109/WISP.2007.4447564.

D Nistér, O Naroditsky, J Bergen. Visual odometry. 2004. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition. 652-659. DOI:10.1109/CVPR.2004.1315094http://doi.org/10.1109/CVPR.2004.1315094.

D Scaramuzza, F Fraundorfer. Visual odometry (tutorial). IEEE Robot Autom Mag, 2011. 18(4):80-92. DOI:10.1109/MRA.2011.943233http://doi.org/10.1109/MRA.2011.943233.

S Se, D Lowe, J Little. Global localization using distinctive visual features. 2002. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems. 226-231. DOI:10.1109/IRDS.2002.1041393http://doi.org/10.1109/IRDS.2002.1041393.

G Singh, J Košechá. Visual loop closing using gist descriptors in Manhattan world. 2010. ICRA Omnidirectional Vision Workshop. .

J Sivic, A Zisserman. Video Google: a text retrieval approach to object matching in videos. 2003. Proc. 9th IEEE Int. Conf. on Computer Vision. 1470-1477. DOI:10.1109/ICCV.2003.1238663http://doi.org/10.1109/ICCV.2003.1238663.

H Stewénius, C Engels, D Nistér. Recent developments on direct relative orientation. ISPRS J Photogr Remote Sens, 2006. 60(4):284-294. DOI:10.1016/j.isprsjprs.2006.03.005http://doi.org/10.1016/j.isprsjprs.2006.03.005.

N Sünderhauf, P Protzel. BRIEF-Gist—closing the loop by simple means. 2011. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems. 1234-1241. DOI:10.1109/IROS.2011.6094921http://doi.org/10.1109/IROS.2011.6094921.

Y Wang. Navigational Road Modeling Based on Omnidirectional Multi-camera System, 2013. :Hangzhou, ChinaZhejiang University, PhD Thesis(in Chinese).

J Wright, AY Yang, A Ganesh, 等. Robust face recognition via sparse representation. IEEE Trans Patt Anal Mach Intell, 2009. 31(2):210-227. DOI:10.1109/TPAMI.2008.79http://doi.org/10.1109/TPAMI.2008.79.

C Wu. SiftGPU: a GPU Implementation of Scale Invariant Feature Transform (SIFT). 2007. Available from http://cs.unc.edu/~ccwu/siftgpu/http://cs.unc.edu/~ccwu/siftgpu/.

K Zhang, L Zhang, MH Yang. Real-time compressive tracking. 2012. Proc. 12th European Conf. on Computer Vision. 864-877. DOI:10.1007/978-3-642-33712-3_62http://doi.org/10.1007/978-3-642-33712-3_62.

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Joint compressed sensing imaging and phase adjustment via an iterative method for multistatic passive radar

Compressed sensing-based structured joint channel estimation in a multi-user massive MIMO system

Ultra-wideband FMCW ISAR imaging with a large rotation angle based on block-sparse recovery

Related Author

Jue WANG

Jun WANG

ZHANG Ruo-yu

ZHAO Hong-lin

JIA Shao-bo

JIN Ke

LAI Tao

LI Gong-quan

Related Institution

National Laboratory of Radar Signal Processing, Xidian University

Communication Research Center, Harbin Institute of Technology

Zhengzhou Institute of Information Science and Technology

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰