A vision system for detecting and tracking of stop-lines

Abstract

This paper presents a computer vision algorithm that detects, by analyzing lane-marking detection results, stop-lines and tracks, using an unscented Kalman filter, the detected stop-line over time. To detect lateral and longitudinal lane-markings, our method applies a spatial filter emphasizing the intensity contrast between lane-marking pixels and their neighboring pixels. We then examine the detected lane-markings to identify perpendicular, geometry layouts between longitudinal and lateral lane-markings for stop-line detection. To provide reliable stop-line recognition, we developed an unscented Kalman filter to track the detected stop-line over frames. Through the testings with real-world, busy urban street videos, our method demonstrated promising results, in terms of the accuracy of the initial detection accuracy and the reliability of the tracking.