Abstract：Within a probabilistic framework, based on principal component analysis neural networks, a novel Monte Carlo tracking technique is suggested for autonomous navigation of land vehicles on unstructured roads. The straight road model is used to represent road edges and its status is predicted by the second-order autoregressive model. Color information and local spatial features are combined in the HSV color space in order to obtain principal components by principal component analysis neural networks. The status of the road is estimated by particle filters according to statistical features of road edge windows. Experimental results show that the unstructured road tracking can be robustly realized by the method.
[1] Turk M A, Morgenthaler D C, Gremban K D, et al.VITS:a vision system for autonomous land vehicle navigation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(3):342-361. [2] Jeong H, Oh Y, Park J H,et al.Vision-based adaptive and recursive tracking of unpaved roads[J].Pattern Recognition Letters,2002,23(2-3):73-82. [3] 程洪,郑南宁,刘铁,等.基于均值移动和特征聚类的道路识别方法[J].模式识别与人工智能,2002,15(4):484-488. [4] Papamarkos N, Antonis E A, Strouthopoulos C P. Adaptive color reduction[J].IEEE Transactions on System, Man, and CyberneticsPart B: Cybernetics, 2002,32(1):44-56. [5] Haykin S. Neural networks: A Comprehensive Foundation [M]. Beijing: Tsinghua University Press,2001. [6] Isard M, Blake A. Condensation-conditional density propagation for visual tracking[J]. International Journal of Computer Vision,1998,29(1):5-28. [7] Perez P, Hue C, Vermaak J, et al. Color-based probabilistic tracking[A]. Proceedings of the 7th European Conference on Computer Vision [C].Berlin, Germany: Springer-Verlag,2002.661-675.
