On-Line Adaptation to Illumination Change for Mobile Robot Based on Omni-Directional Vision

Abstract:

In this paper a method of on-line adaptation to illumination is proposed for mobile robot based on omni-directional in a changing illumination environment. Illumination condition is represented by an average luminance distribution of a reference object in a time series images. Illumination change is detected by computing the KL-divergence between two different distributions. A dual-threshold strategy is used to classify the current illumination into known conditions or an unknown one. According to illumination the robot decides to switch to a corresponding color calibration or learn a new one. Experiments have been carried out on the soccer robot M-TR. Experimental results show the efficiency of the proposed method.

• Periodical: Advanced Materials Research (Volume 462)
• Pages: 252-258
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.462.252
• Online since: February 2012
• Authors: Xin Luan, Wei Wei Qi, Tie Yi Zhu, Fang Jie Yu, Da Lei Song
• Keywords: Illumination Changes, KL-Divergence, Luminance Distribution, Mobile Robot

References

[1] F. Anzani, D. Bosisio, M. Matteucci and D. G. Sorrenti: On-Line Color Calibration in Non-Stationary Environments. The Ninth International RoboCup Symposium, Osaka, Japan, (2005).

DOI: 10.1007/11780519_35

[2] Sridharan M. and Stone P.: Towards illumination invariance in the legged league. The Eighth International RoboCup Symposium, Springer-Verlag, Berlin Heidelberg, p.196–208, (2005).

DOI: 10.1007/978-3-540-32256-6_16

[3] M. Jüngel, J. Hoffmann, and M. Lotzsch: A real-time auto-adjusting vision system for robotic soccer. 7th International Workshop on RoboCup 2003 (Robot World Cup Soccer Games and Conferences), Lecture Notes in Artificial Intelligence, Springer, (2004).

DOI: 10.1007/978-3-540-25940-4_19

[4] Parameswaran Vasu, Singh Maneesh and Ramesh Visvanathan: Illumination Compensation Based Change Detection Using Order Consistency. 23rd IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, p.1982 – 1989, (2010).

DOI: 10.1109/cvpr.2010.5539873

[5] G. Sapiro: Color and illuminant voting. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, no. 11, pp.1210-1215, (1999).

DOI: 10.1109/34.809114

[6] Neves. A, Corrente. G and Pinho. A: An omnidirectional vision system for soccer robots. Progress in artificial intelligence. Lecture notes in artificial intelligence, vol. 4874, Springer, pp.499-507, (2007).

DOI: 10.1007/978-3-540-77002-2_42

[7] S. Fidler, and A. Leonardis: Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts. The International Conference on Computer Vision and Pattern Recognition (CVPR), (2007).

DOI: 10.1109/cvpr.2007.383269

[8] Sridharan M. and Stone P.: Color Learning and Illumination Variance on Mobile Robots: A Survey. Robotics and Autono- mousSystem, Vol. 75(1), pp.1-38, (2009).

[9] S. Thrun, W. Burgard and D. Fox, Probabilistic Robotics, MIT Press, Cambridge, USA, (2005).

[10] J. E. Bresenham: Algorithm for computer control of a digital plotter. IBM Systems J., Vol 4(1), p.25–30, (1965).

DOI: 10.1147/sj.41.0025

[11] Xin Luan, Wei-Wei Qi, Da-Lei Song, Ming Chen, Tie-Yi Zhu and Li Wang: Illumination Invariant Color Model for Object Recognition in Robot Soccer. Advances in Swarm Intelligence. Lecture Notes in Computer Science, Springer, Vol. 6146/2010, pp.680-687, (2010).

DOI: 10.1007/978-3-642-13498-2_89