Abstract
Visual odometry (VO) is one of the promising techniques that estimates pose using the camera and does not necessarily require other sensor aiding. With increasing automation and the use of miniaturized systems such as mobile devices, wearable gadgets, & gaming consoles, demand for efficient algorithms have risen. In this paper, an attempt is made to remove the redundant features from the VO pipeline that do not have a significant effect on the estimation process. A probabilistic approach based on fast mutual information (MI) computation is suggested here as the basis for removing features. The MI value acts as a beacon for selecting distinct features while eliminating the redundant ones, thus improving the overall system speed and reducing storage requirements. The proposed MI-based feature selection framework for VO has been experimented on the KITTI vision benchmark suite and EuRoC MAV datasets available publicly. The estimated trajectory results have shown that the proposed technique is better in terms of computational efficiency and has similar accuracy as compared to the normal VO pipeline. Further investigations have also been carried out over the VSLAM framework to test its applicability in a real-time system.
Similar content being viewed by others
References
Scaramuzza, D., Fraundorfer, F.: Visual odometry [tutorial]. IEEE robotics & automation magazine. 18, 80–92 (2011)
H. P. Moravec, "Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover.," 1980
D. Nister, O. Naroditsky and J. Bergen, "Visual Odometry," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2004
S. Poddar, R. Kottath and V. Karar, "Evolution of Visual Odometry Techniques," arXiv preprint arXiv:1804.11142, 2018
S. Poddar, R. Kottath and V. Karar, "Motion Estimation Made Easy: Evolution and Trends in Visual Odometry," in Recent Advances in Computer Vision, Springer, 2019, pp. 305–331
D. A. Pomerleau, "ALVINN: An Autonomous Land Vehicle in a Neural Network," in Advances in neural information processing systems, 1989
Setiono, R., Liu, H.: Neural-network feature selector. IEEE Trans. Neural Netw. 8, 654–662 (1997)
B. Kitt, A. Geiger and H. Lategahn, "Visual Odometry Based on Stereo Image Sequences with RANSAC-Based Outlier Rejection Scheme," in IEEE Intelligent Vehicles Symposium (IV), 2010
I. Cvisic and I. Petrovic, "Stereo Odometry Based on Careful Feature Selection and Tracking," in European Conference on Mobile Robots (ECMR), 2015
B. Kitt, F. Moosmann and C. Stiller, "Moving on to Dynamic Environments: Visual Odometry Using Feature Classification," in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2010
W. Zhou, H. Fu and X. An, "a Classification-Based Visual Odometry Approach," in International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2016
G. Zhang and P. A. Vela, "Good Features to Track for Visual Slam," in IEEE conference on computer vision and pattern recognition (CVPR), 2015
D. B. Russakoff, C. Tomasi, T. Rohlfing and C. R. Maurer, "Image Similarity Using Mutual Information of Regions," in European Conference on Computer Vision (ECCV), 2004
T. Cieslewski and D. Scaramuzza, "SIPS: Unsupervised Succinct Interest Points," arXiv preprint arXiv:1805.01358, 2018
T. Tuytelaars, K. Mikolajczyk and others, "Local invariant feature detectors: a survey," Foundations and trends in computer graphics and vision, vol. 3, pp. 177–280, 2008
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
H. Bay, T. Tuytelaars and L. Van Gool, "SURF: Speeded Up Robust Features," in European conference on computer vision (ECCV), 2006
E. Rublee, V. Rabaud, K. Konolige and G. R. Bradski, "ORB: An efficient alternative to SIFT or SURF.," in ICCV, 2011
Yousif, K., Bab-Hadiashar, A., Hoseinnezhad, R.: An overview to visual odometry and visual SLAM: applications to mobile robotics. Intelligent Industrial Systems. 1, 289–311 (2015)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM. 24, 381–395 (1981)
K. Ni, H. Jin and F. Dellaert, "GROUPSAC: Efficient Consensus in the Presence of Groupings," in International Conference on Computer Vision, 2009
Nister, D.: Preemptive RANSAC for live structure and motion estimation. Mach. Vis. Appl. 16, 321–329 (2005)
Torr, P.H.S., Zisserman, A.: MLESAC: a new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. 78, 138–156 (2000)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Liu, H., Yu, L.: Toward integrating feature selection algorithms for classification and clustering. IEEE Trans. Knowl. Data Eng. 17, 491–502 (2005)
Li, Y., Li, T., Liu, H.: Recent advances in feature selection and its applications. Knowl. Inf. Syst. 53, 551–577 (2017)
Peng, H., Long, F., Ding, C.: Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1226–1238 (2005)
Mitra, P., Murthy, C.A., Pal, S.K.: Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell. 24, 301–312 (2002)
M. A. Hall, "Correlation-Based Feature Selection of Discrete and Numeric Class Machine Learning," 2000
Sharaf, A.I., El-Soud, M.A., El-Henawy, I.: A feature selection algorithm based on mutual information using local non-uniformity correction estimator. Int. J. Adv. Comput. Sci. Appl. 8, 418–423 (2017)
Kwak, N., Choi, C.-H.: Input feature selection for classification problems. IEEE Trans. Neural Netw. 13, 143–159 (2002)
Escalera, A., Izquierdo, E., Martin, D., Musleh, B., Garcia, F., Armingol, J.M.: Stereo visual odometry in urban environments based on detecting ground features. Robot. Auton. Syst. 80, 1–10 (2016)
R. Kottath, D. P. Yalamandala, S. Poddar, A. P. Bhondekar and V. Karar, "Inertia Constrained Visual Odometry for Navigational Applications," in International Conference on Image Information Processing (ICIIP), 2017
De-Maeztu, L., Elordi, U., Nieto, M., Barandiaran, J., Otaegui, O.: A temporally consistent grid-based visual odometry framework for multi-core architectures. J. Real-Time Image Proc. 10, 759–769 (2015)
Qiu, P., Gentles, A.J., Plevritis, S.K.: Fast calculation of pairwise mutual information for gene regulatory network reconstruction. Comput. Methods Prog. Biomed. 94, 177–180 (2009)
Burri, M., Nikolic, J., Gohl, P., Schneider, T., Rehder, J., Omari, S., Achtelik, M.W., Siegwart, R.: The EuRoC micro aerial vehicle datasets. The International Journal of Robotics Research. 35, 1157–1163 (2016)
D. Schlegel, M. Colosi and G. Grisetti, "Proslam: Graph SLAM from a programmer's Perspective," in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018
Kummerle, R., Steder, B., Dornhege, C., Ruhnke, M., Grisetti, G., Stachniss, C., Kleiner, A.: On measuring the accuracy of SLAM algorithms. Auton. Robot. 27, 387–407 (2009)
Umeyama, S.: An eigen decomposition approach to weighted graph matching problems. IEEE Trans. Pattern Anal. Mach. Intell. 10, 695–703 (1988)
A. Geiger, P. Lenz and R. Urtasun, "Are we Ready for Autonomous Driving? The Kitti Vision Benchmark Suite," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
Mur-Artal, R., Tardos, J.D.: ORB-SLAM: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans. Robot. 33, 1255–1262 (2017)
Acknowledgements
The authors would like to thank Director, CSIR-CSIO for providing the opportunity and support required to carry out this research. The authors would also like to thank Mr. Igor Cvisic, Leading Researcher, University of Zagreb, and Dr. Laurent Kneip, Mobile Perception Lab, ShanghaiTech University, for their insightful suggestion and guidance. This research has been supported by DRDO-Aeronautical Research & Development Board through grant-in-aid project on design and development of visual odometry system.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kottath, R., Poddar, S., Sardana, R. et al. Mutual Information Based Feature Selection for Stereo Visual Odometry. J Intell Robot Syst 100, 1559–1568 (2020). https://doi.org/10.1007/s10846-020-01206-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-020-01206-z