An adaptive detection approach for autonomous forest path following using stereo vision

Abstract

In this paper, an image-based segmentation method to improve autonomous robot navigation in the forest is presented. The detection is supported by a filtered image generated from a stereo-based pre-processing which is a byproduct of our obstacles detection system. To cope with the large variability of forest paths, the classifier is dynamically adapted to the current situation and the segmentation relies on different image features to ensure robustness against illumination changes. Furthermore, it is summarized how the detection results are transformed to the 3D space, using a plane which is extracted from the stereo data, to be stored and maintained in a probabilistic grid map.