Detection of Stop Line Violations Using the Hough Transform

Abstract

The number of road users, in particular those using motor vehicles, is constantly increasing. It is imperative that these users obey road markings, in order to ensure traffic safety. However, the number of traffic violations is still very high. One example is violation of stop line before a pedestrian crossing. This paper proposes an automatic detection of this type of traffic violation. The approach is based on the Hough transform. This experiment show that the approach can achieve accuracy rate for the morning and afternoon dataset are 89% and for the evening dataset is approximately 69% (or 71% using an alternative set of parameters). So, the overall average of accuracy rate of the system is 82.33 % (or 83 %, with an alternative set of parameters). The main factors affecting the system performance is the availability of adequate lighting and the quality of the stop line marking.