Online self-supervised learning for road detection
Mll Marco Rompen, WP Willem Sanberg, Gijs Dubbelman · TU/e Research Portal · 2014
We present a computer vision system for intelligent vehicles that distinguishes obstacles from roads by exploring online and self-supervised learning. It uses geometric information, derived from stereo-based obstacle detection, to obtain weak training labels for an SVM classifier. Subsequently, the SVM improves the road detection result by classifying image regions on basis of appearance information. In this work, we experimentally evaluate different image features to model road and obstacle appearances. It is shown that using both geometric information and HueSaturation appearance information improves the road detection task.