Outdoor Navigating Scene Labeling Using Importance Factor Based I-RELIEF and Feature Weighted Support Vector Machines

Abstract:

Feature selection plays an important role in terrain classification for outdoor robot navigation. For terrain classification, the image data usually have a large number of feature dimensions. The better selection of features usually results in higher labeling accuracy. In this work, a novel approach for terrain perception using Importance Factor based I-Relief algorithm and Feature Weighted Support Vector Machines (IFIR-FWSVM) is put forward. Firstly, the weight of each feature for classification is computed by using Importance Factor based I-Relief algorithm (IFIR) and the irrelevant features are eliminated. Then the weighted features are used to compute the kernel functions of SVM and trained the classifier. Finally, the trained SVM is employed to predict the terrain label in the far-field regions. Experimental results based on DARPA datasets show that the proposed method IFIR-FWSVM is superior over traditional SVM.

• Periodical: Applied Mechanics and Materials (Volumes 511-512)
• Pages: 467-474
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.511-512.467
• Online since: February 2014
• Authors: Jun Tu*, Cheng Liang Liu, Zhong Hua Miao
• Keywords: Feature Selection, Machine Vision, Robot Navigation, Support Vector Machine (SVM), Terrain Classification

References

[1] Z. G. Zhou: Journal of Computational Infor Vol. 7 (2011), p. (2006).

[2] H. Jin, Q. T. Wang: An improved UKF for BD/SINS integrated navigation system, J Comput Infor Sys Vol. 8 (2012), p.4855.

[3] L. Matthies: Int J Comput Vision Vol. 8 (1992), pp.71-91.

[4] A. Rieder, B. Southall, in: Proc. IEEE Intelligent Vehicle Symposium (2003).

[5] W. H. Huang, M. Ollis, M. Happold, B. A. Stancil: J Field Robot Vol. 26 (2009), p.196.

[6] L. D. Jackel, E. Krotkov, M. Perschbacher, J. Pippine, C. Sullivan: J Field Robot Vol. 23 (2006), p.945.

[7] M. J. Procopio, J. Mulligan, and G. Grudic: J Field Robot Vol. 26 (2009), p.145.

[8] H. Dahlkamp, A. Kaehler, D. Stavens, S. Thrun, G. Bradski: Robotics: Science & Systems (2006).

DOI: 10.15607/rss.2006.ii.005

[9] M. Happold, M. Ollis, N. Johnson: Robotics: Science and System (2006).

[10] M. Bajracharya, A. Howard, L. H. Matthies, B. Tang, M. Turmon: J Field Robot Vol. 26 (2009), p.3.

[11] R. Manduchi: Auton Robot Vol. 18 (2005), p.81.

[12] I. Halatci, C. A. Brooks, K. Iagnemma, in: IEEE Aerospace Conference Proceedings (2007).

[13] I. Halatci, C. A. Brooks, K. Iagnemma: Robotica Vol. 26 (2008), p.767.

[14] X. Ren, J. Malik, in: IEEE International Conference on Computer Vision (2003).

[15] P. Felzenszwalb, D. Huttenlocher: Int J Comput Vision Vol. 59 (2004), p.167.

[16] R. Kohavi, G. H. John: Artif Intell Vol. 97 (1997), p.273.

[17] K. Kira, L. A. Rendell, in: Proceedings of the Ninth International Workshop on Machine Learning (1992).

[18] T. G. Dietterich: Ai Mag Vol. 18 (1997), p.97.

[19] Y. Sun: IEEE T Pattern Anal Vol. 29 (2007), p.1035.

[20] C. Cortes, V. Vapnik: Mach Learn Vol. 20 (1995), p.273.

[21] K. Wang, X. Wang, Y. Zhong, in: International Conference on Measuring Technology and Mechatronics Automation (2010).