Detection of street-parking vehicles from panoramic street image

Abstract

It is important to assess street-parking vehicles causing traffic problems in urban areas, however, it is performed manually and at high cost. It is a top priority for reducing cost, to develop a detection system of those vehicles. We address a spatio-temporal volume and two types of slice surfaces from the volume, and introduce two-types of panoramic street-images, which possibly provide useful information for our daily life. We propose two alternative detection methods, using a laser-range finder and a line-scan camera. In the former detection method, EPI analysis is applied to line-scan images. As a result of verification experiments in real roads, a detection rate reached 76.9%. In the latter detection method, two kinds of cluster analysis are applied to range points: one is for clustering points at each scan, and the other for clustering points over several scans. Each cluster of range points means a vehicle. As a result of verification experiments in real roads, a detection rate reached 90%.