The Performance Analysis of Stereo Visual Odometry Assisted Low-Cost INS/GPS Integration System

被引:4
作者
Chen, Li-Hung [1 ]
Chiang, Kai-Wei [1 ]
机构
[1] Natl Cheng Kung Univ, Dept Geomat, Tainan 70101, Taiwan
关键词
Visual odometry; INS; GPS;
D O I
10.1080/23080477.2015.11665650
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Visual Odometry (VO) is a new method using sequence images acquired from the vehicle which is in motion to estimate the movement. In this research, a novel method is proposed for assisting low-cost INS/GPS integration system with VO system. When GPS signal vanishes, VO can be applied as the backup for GPS to reduce the INS accumulation errors. In order to evaluate the proposed system, the tactical INS/GNSS trajectory is used as the reference trajectory. The Distances Traveled (DT) by low-cost INS/GPS and VO modes are calculated. In addition, this study also investigates the accuracy variation in both monocular and stereo-vision VO system, respectively. The purpose is to verify the argument presented in related work. According to the preliminary results, the stereo VO performs well and the position errors in three directions are reduced by using the assisted information including VO position and velocity. It verifies that the proposed integrated system is helpful and efficient in the aspect of increasing the accuracy when GPS signal blockages.
引用
收藏
页码:148 / 156
页数:9
相关论文
共 10 条
[1]  
Badino H., 2004, Complex Motion. First International Workshop, IWCM 2004. Revised Papers (Lecture Notes in Computer Science Vol. 3417), P198
[2]  
Bosse M, 1997, IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, P1028, DOI 10.1109/ITSC.1997.660615
[3]   Camera Motion Estimation Using Monocular and Stereo-Vision [J].
Bota, Silviu ;
Nedevschi, Sergiu .
2008 IEEE 4TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING, PROCEEDINGS, 2008, :275-278
[4]  
Geiger A, 2011, IEEE INT VEH SYM, P963, DOI 10.1109/IVS.2011.5940405
[5]  
Helmick DM, 2004, AEROSP CONF PROC, P772
[6]   Visual Odometry based on Stereo Image Sequences with RANSAC-based Outlier Rejection Scheme [J].
Kitt, Bernd ;
Geiger, Andreas ;
Lategahn, Henning .
2010 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2010, :486-492
[7]  
Lidholm J., 2009, P IEEE C EM TECHN FA, P1, DOI [10.1109/ETFA.2009.5347105, DOI 10.1109/ETFA.2009.5347105]
[8]  
NISTER D, 2004, PROC CVPR IEEE, P652, DOI DOI 10.1109/CVPR.2004.1315094
[9]  
Parra I., 2011, 2011 IEEE 20th International Symposium on Industrial Electronics (ISIE 2011), P832, DOI 10.1109/ISIE.2011.5984266
[10]   A New Approach to Vision-Aided Inertial Navigation [J].
Tardif, Jean-Philippe ;
George, Michael ;
Laverne, Michel ;
Kelly, Alonzo ;
Stentz, Anthony .
IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, :4161-4168