Improving Traffic Sign Detection with Temporal Information
Proceedings of the 23rd Computer Vision Winter Workshop, 2018
Traffic sign detection is a frequently addressed research and application problem, and many solutions to this problem have been proposed. A vast majority of the proposed approaches perform traffic sign detection on individual images, although a video recordings are often available. In this paper, we propose a method that exploits also the temporal information in image sequences. We propose a three-stage traffic sign detection approach. Traffic signs are first detected on individual images. In the second stage, visual tracking is used to track these initial detections to generate multiple detection hypotheses. These hypotheses are finally integrated and refined detections are obtained. We evaluate the proposed approach by detecting 91 traffic sign categories in a video sequence of more than 18.000 frames. Results show that the traffic signs are better localized and detected with a higher accuracy, which is very beneficial for applications such as maintenance of the traffic sign records.