Improving the performance of traffic sign detection using blob tracking

Abstract

We propose a new approach for tracking circular traffic signs from image sequences to improve the performance of traffic sign detection, by reducing search region and suppressing misdetection caused by temporal occlusion or poor quality of image. Our proposed tracking, called two-layered blobs tracking, does not require an accurate model of the fixed object-moving camera system, which is essential in the Kalman-Filter tracking. The experimental results show that the proposed approach could track the circular tra. c signs from a moving camera effectively, without any restrictions on speed and movement of the vehicle, and camera installation, thus it is easy to be implemented in real situation.