Bipolarity and Projective Invariant-Based Zebra-Crossing Detection for the Visually Impaired

Abstract

A safe road-crossing system is an extreme necessity to improve the mobility of the visually impaired. It is important for a blind person to know whether a frontal area is a crossing or not. A crossing is characterized by zebra pattern i.e. by constant width periodic white stripes on a usual black road surface, which can be treated as a bipolar pattern. In this paper, a fast and stable algorithm for detecting the location of a pedestrian crossing using an image captured by a single camera is presented. This is achieved through bipolarity-based segmentation and projective invariant-based recognition. The algorithm includes three steps. First, we segment the image on the basis of bipolarity and pick the crossing candidates on the basis of area. Second, feature points are extracted on the candidate area based on Fisher criterion. Third, we use projective invariants to recognize the crossing. The experiments on a large number of street scenes with and without crossing demonstrate the effectiveness of the proposed algorithm.