IJBTT

World Scale Estimation Monocular Visual Odometry with Ground Feature

	International Journal of Recent Engineering Science (IJRES)
	© 2017 by IJRES Journal
	Volume-4 Issue-6
	Year of Publication : 2017
	Authors : Xiang Liu, Zuolei Sun, Weijie Chen
	DOI : 10.14445/23497157/IJRES-V4I6P109

How to Cite?

Xiang Liu, Zuolei Sun, Weijie Chen, "World Scale Estimation Monocular Visual Odometry with Ground Feature," International Journal of Recent Engineering Science, vol. 4, no. 6, pp. 43-48, 2017. Crossref, https://doi.org/10.14445/23497157/IJRES-V4I6P109

Abstract
Scaleambiguity is the major challenge in the application of monocular visual odometry (MVO). A sound approach to MVO world scale estimation is proposed in this paper. Firstly, the Speed Up Robust Feature (SURF) is employed to extract features and KLT (Kanade-Lucas-Tomasi) optical flow functions as the visual feature matcher between the consecutive images. Then RANSAC is used to refine the feature matching to reduce the mismatches introduced by noise, the procedure can improve the accuracy of fundamental matrix. In order to get good ground feature which is used to overcome the scale ambiguity, the region of interest (ROI) where the ground in the images is selected and adaptively adjusted when the camera view is changed. The performance of the proposed approach is demonstrated with the widely used KITTI benchmark and compared with the classical MVO algorithm.

Keywords
Accurate scale, Image processing, Motion estimation, Visual odometry

Reference
[1] Howard A. Real-time stereo visual odometry for autonomous ground vehicles, F, 2008 [C]. IEEE.3946-3952.
[2] Matthies L, Shafer SA. Error modeling in stereo navigation [J]. Robotics and Automation, IEEE Journal of, 1987, 3(3): 239-248.
[3] Scaramuzza D, Fraundorfer F. Visual odometry [tutorial] [J]. Robotics & Automation Magazine, IEEE, 2011, 18(4): 80-92.
[4] Hartley R, Zisserman A. Multiple view geometry in computer vision [M]. Cambridge university press, 2003.
[5] Harris C, Stephens M. A combined corner and edge detector; proceedings of the Alvey vision conference, F, 1988 [C]. Citeseer.50.
[6] Bay H, Tuytelaars T, Van Gool L. Surf: Speeded up robust features [M]. Computer vision–ECCV 2006. Springer. 2006: 404-417.
[7] Ng PC, Henikoff S. SIFT: Predicting amino acid changes that affect protein function [J]. Nucleic acids research, 2003, 31(13): 3812-3814.
[8] Daniel Lélis Baggio, Emami S. et al. Mastering OpenCV with Practical Computer Vision Projects [M]. Packt Publishing Ltd, 2012.
[9] Muja M, Lowe D G. Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration[J]. VISAPP (1), 2009, 2: 331-340.
[10] Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision; proceedings of the IJCAI, F, 1981 [C].674-679.
[11] Scaramuzza D, Fraundorfer F, Siegwart R. Real-time monocular visual odometry for on-road vehicles with 1-point ransac; proceedings of the Robotics and Automation, 2009 ICRA'09 IEEE International Conference on, F, 2009 [C]. IEEE.4293-4299.
[12] Sami Brandt.Maximum Likelihood Robust Regression with Known and Unknown Residual Models, Statistical Methods in Video Processing Workshop,2008
[13] Richard Szeliski. Computer Vision:Algorithms and Applications.Springer-Verlag New York, Inc. , 2010 , 21 (8) :2601-2605
[14] Kitt BM, Rehder J, Chambers AD, et al. Monocular visual odometry using a planar road model to solve scale ambiguity [J]. 2011.
[15] Davison AJ, Reid ID, Molton ND, et al. MonoSLAM: Realtime single camera SLAM [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2007, 29(6): 1052-1067.
[16] Klein G, Murray D. Parallel tracking and mapping for small AR workspaces, F, 2007 [C]. IEEE.225-234.
[17] Hartley RI. ªIn Defense of the Eight-Point Algorithm [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1997, 19(6): 580-593.
[18] Geiger A, Lenz P, Stiller C, et al. Vision meets robotics: The KITTI dataset [J]. The International Journal of Robotics Research, 2013, 0278-3649.
[19] Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? the kitti vision benchmark suite; proceedings of the Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, F, 2012 [C]. IEEE.3354-3361.
[20] J Deigmoeller, J Eggert.Stereo Visual Odometry Without Temporal Filtering. Springer International Publishing , 2016
[21] M Buczko, V Willert. How to Distinguish Inliers from Outliers in Visual Odometry for High-speed Automotive Applications.Intelligent Vehicles Symposium , 2016
[22] M Buczko, VWillert..Flow-Decoupled Normalized Reprojection Error for Visual Odometry. IEEE International Conference on Intelligent Transportation Systems, 2016
[23] I Cvišić, I Petrović. Stereo odometry based on careful feature selection and tracking. European Conference on Mobile Robots , 2015 :1-6
[24] J Zhang, S Singh.Visual-lidar Odometry and Mapping: Lowdrift, Robust. IEEE International Conference on Robotics & Automation , 2015 , 2015 :2174-2181