New Ground Plane Segmentation Method for Electronic Cane

Abstract

In this paper, a new ground plane segmentation method is proposed for obstacle detection to improve the mobility of the visually impaired people by means of a novel electronic cane Smartcane. Monocular camera was used which has the merits to get simple computation and cheap hardware and it's promising to realize real time navigation. The proposed method is based on an appearance-based approach by combining both color and texture information extracted from monocular image. The algorithm is tested with a challenging indoor image set. It gives better obstacle detection than available color based obstacle detection approaches. 