Detection of pedestrian crossings with projective invariants from image data
Tadayoshi Shioyama, Mohammad Shorif Uddin · Measurement Science and Technology · 2004
This paper proposes a method for detecting frontal pedestrian crossings from image data obtained with a single camera as a travel aid for the blind. The process of detecting a crossing is a pre-process followed by the process for detecting the state of the traffic lights. It is important for the blind to know whether or not a frontal area is a crossing. The existence of a crossing is detected in two steps. In the first step, feature points for a crossing are extracted by operating a filter on greyscale image data using the Fisher criterion. In the second step, the existence of a crossing is detected by checking the periodicity of white lines on the road using projective invariants. From the experimental results, it is found that the proposed method successfully detects whether or not there is a pedestrian crossing, for 194 real images out of 196.