Similar articles

Abstract: Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. active learning is used for automatically dealing with problems caused by the selection, labeling and classification of large numbers of training sets. mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ‘common’ water hazards, which usually have the features of both high brightness and low texture, but also ‘special’ water hazards that may have lots of ripples or low brightness.

[1] Comaniciu, D., Meer, P., 2002. Mean-shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619.

[2] Dima, C., 2004. Classifier Fusion for Outdoor Obstacle Detection. IEEE Int. Conf. on Robotics and Automation, 1:665-671.

[3] Dima, C., 2006. Active Learning for Outdoor Perception. PhD Thesis, the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA.

[4] Dima, C., Hebert, M., Stentz, A., 2004. Enabling Learning from Large Datasets: Applying Active Learning to Mobile Robotics. Proc. Int. Conf. on Robotics and Automation, 1:108-114.

[5] Forsyth, D., Ponce, J., 2002. Computer Vision: A Modern Approach. Professional Technical Reference, Prentice Hall.

[6] Gray, A.G., Moore, A.W., 2003. Rapid Evaluation of Multiple Density Models. Proc. 9th Int. Workshop on Artificial Intelligence and Statistics.

[7] Hong, T., Chang, T., Rasmussen, C., Shneier, M., 2002. Feature Detection and Tracking for Mobile Robots Using a Combination of Radar and Color Images. IEEE Proc. on Robotics and Automation, p.4340-4345.

[8] Matthies, L., Bellutta, P., McHenry, M., 2003. Detecting Water Hazards for Autonomous Off-road Navigation. SPIE, 5083:231-242.

[9] Nguyen, N., Milanfar, P., Golub, G., 2001. Efficient generalized cross-validation with application parametric image restoration and resolution enhancement. IEEE Trans. Image Processing, 10(9):1299-1308.

[10] Nigam, K., 2001. Using Unlabeled Data to Improve Text Classification. PhD Thesis, Carnegie Mellon University, Pittsburgh, PA, USA.

[11] Rankin, A., Matthies, L., Huertas, A., 2004. Daytime Water Detection by Fusing Multiple Cues for Autonomous Off-road Navigation. Proc. 24th Army Science Conf., p.177-184.

[12] Sarwal, A., Nett, J., Simon, D., 2004. Detection of Small Water-bodies. Technical Report, PercepTek Robotics, USA.

[13] Scholz, M., Vigario, R., 2002. Nonlinear PCA: A New Hierarchical Approach. Proc. European Symp. on Artificial Neural Networks, p.439-444.

[14] Wald, I., Havran, V., 2006. On Building Fast kd-trees for Ray Tracing, and on Doing That in O(NlogN). IEEE Symp. on Interactive Ray Tracing, p.61-70.

[15] Yao, T.Z., Xiang, Z.Y., Liu, J.L., Xu, D., 2007. Multi-feature Fusion Based Outdoor Water Hazards Detection. Proc. IEEE Conf. on Mechatronics and Automation, p.652-656.