Drivable Area Detection Method Capable of Distinguishing Vegetation Area on Country Road

Abstract

The v-disparity method is one of the most widely used algorithms for detecting the drivable area based on stereo vision. However, it mistakes vegetation of county roads as the drivable area. Thus, this paper proposes the drivable area detection method that addresses the problem of treating the roadside vegetation as the drivable area. The experimental results show that the proposed method is approximately 6.86% more accurate than the previous v-disparity method.