A Boosting Approach to Visual Servo-Control of an Underwater Robot
We present an application of the ensemble learning algorithm in the area of visual tracking and servoing. In particular, we investigate an approach based on the Boosting technique for robust visual tracking of color objects in an underwater environment. To this end, we use AdaBoost, the most common variant of the Boosting algorithm, to select a number of low-complexity but moderately accurate color feature trackers and we combine their outputs. From a significantly large number of “weak” color trackers, the training process selects those which exhibit reasonably good performance (in terms of mistracking and false positives), and assigns positive weights to these trackers. The tracking process applies these trackers on the input video frames, and the final tracker output is chosen based on the weights of the final array of trackers. By using computationally inexpensive but somewhat accurate trackers as members of the ensemble, the system is able to run at quasi-real time, and thus, is deployable on-board our underwater robot. We present quantitative cross-validation results of our visual tracker, and conclude by pointing out some difficulties faced and subsequent shortcomings in the experiments we performed, along with directions of future research on the area of ensemble tracking in real-time.
KeywordsVideo Sequence Visual Tracking Tracker Output AdaBoost Algorithm Underwater Robot
Unable to display preview. Download preview PDF.
- 1.Arbter, K., Langwald, J., Hirzinger, G., Wei, G., Wunsch, P.: Proven techniques for robust visual servo control. In: IEEE International Conference on Robotics and Automation, Workshop WS2, Robust Vision for Vision-Based Control of Motion, pp. 1–13 (1998)Google Scholar
- 3.Chernova, S., Veloso, M.: An evolutionary approach to gait learning for four-legged robots. In: Proceedings of 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2004), vol. 3, 28 September -2 October 2004, pp. 2562–2567 (2004)Google Scholar
- 4.Dudek, G., Jenkin, M., Prahacs, C., Hogue, A., Sattar, J., Giguère, P., German, A., Liu, H., Saunderson, S., Ripsman, A., Simhon, S., Torres-Mendez, L.A., Milios, E., Zhang, P., Rekleitis, I.: A visually guided swimming robot. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Edmonton, Alberta, Canada (August 2005)Google Scholar
- 5.Freund, Y.: Boosting a weak learning algorithm by majority. In: COLT: Proceedings of the Workshop on Computational Learning Theory. Morgan Kaufmann Publishers, San Francisco (1990)Google Scholar
- 7.Giguere, P., Dudek, G.: Clustering sensor data for terrain identification using a windowless algorithm. In: Robotics: Science and Systems. The MIT Press, Cambridge (2008) (in press)Google Scholar
- 9.Ma, Y., Kosecka, J., Sastry, S.: Vision guided navigation for a nonholonomic mobile robot. In: IEEE Conference on Decision and Control (1997)Google Scholar
- 10.Schapire, R.E.: The strength of weak learnability. Machine Learning 5, 197–227 (1990)Google Scholar
- 11.Schapire, R.E.: A brief introduction to boosting. In: International Joint Conference on Artificial Intelligence (1999)Google Scholar
- 14.Xu, A., Dudek, G., Sattar, J.: A natural gesture interface for operating robotic systems. In: Proceedings of the IEEE International Conference on Robotics and Automation, ICRA, Pasadena, California (May 2008)Google Scholar
- 15.Xu, R.Y.D., Allen, J.G., Jin, J.S.: Robust mean-shift tracking with extended fast colour thresholding. In: International Symposium on Intelligent Multimedia, Video and Speech Processing (ISIMP 2004), Hong Kong, October 2004, pp. 542–545 (2004)Google Scholar