25 September 2003 Road recognition algorithm using principal component neural networks and K-means
Author Affiliations +
Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.538796
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China
Abstract
A new road recognition algorithm based on local statistical features and principal component analysis is introduced to improve whose robustness and adaptiveness. The weights of the principal component neural networks is trained with the aid of the algorithm of generalized Hebbian learning rule, and the input vectors of the local spatial features and image pixels value are transformed into feature vectors which are once clustered by K-means classifier, the road surface and un-road surface can be distinguished by the reference area finally. The simulation results confirm the fine robustness and adaptiveness of the newly proposed algorithm, especially, the improved performance to recognize road images affected by illumination variations or shadows.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hong Cheng, Hong Cheng, Nanning Zheng, Nanning Zheng, Qing Ling, Qing Ling, Zhenhai Gao, Zhenhai Gao, } "Road recognition algorithm using principal component neural networks and K-means", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); doi: 10.1117/12.538796; https://doi.org/10.1117/12.538796
PROCEEDINGS
4 PAGES


SHARE
RELATED CONTENT

Deinterlacing using modular neural network
Proceedings of SPIE (May 27 2004)
A vision-based detection algorithm for unmarked road
Proceedings of SPIE (November 27 2007)
A new method for ship classification and recognition
Proceedings of SPIE (November 03 2005)

Back to Top