Outdoor stairway segmentation using vertical vanishing point and directional filter

Abstract

In this paper we propose to detect the localization and recognition of outdoor stairway. This problem is the most fundamental step in solving the problem of autonomous stair climbing navigation. An autonomous system must be able to recognize parameters that can describe stairways in unknown environments. First, we proposed to extract the longest segments of diagonal lines from the edge image in order to identify a set of diagonal line segments candidate. This can provide information itself. Based on the vanishing point we defined the area where the stair candidate is located. We then applied the Gabor filter to detect the horizontal line. Finally, after combining the previous two steps, the algorithm defined the candidate stair area in the image. A set of stair images were used within a variety of conditions in our proposed method. As a result, testing was able to prove its effectiveness.