FINDING PASSABLE REGIONS FOR ROBOTS FROM A SINGLE STILL IMAGE

J. Tian,∗,∗∗ W. Dong,∗ and Y. Tang∗

Keywords

Monocular vision, MILN, depth cues, passable regions

Abstract

Vision-guided obstacle avoidance, especially in unstructured environments, is a challenging issue in robotics. The paper proposes a biological inspired method to find passable regions based on the estimation of relative depth in a single still colour image. In the method, Multiple-layer In-place Learning Network (MILN) is applied to learn the passable regions in images, choosing several depth-related features extracted from the images as inputs. The method proposed here does not need any special prior knowledge or assumptions. We test our method on practical images of different scenes. Experimental results validate our method.

Important Links:



Go Back