Layered Ground Floor Detection for Vision-based Mobile Robot Navigation

초록

This paper proposes a method of detecting ground floor in local map building for visual navigation of a mobile robot. The algorithm is to detect and segment the ground floor by computing plane normals from motion fields in image sequences. The plane normals are combined together with iterative refinement processes based on image segmentation techniques and then allow the robot to detect and segment the ground floor accurately although mismatched point correspondences are detected in image sequences. The preliminary experiments demonstrate the effectiveness of the proposed method by experiments on real data.