Su Mon Thwin, Khin Thuzar Win
Traffic sign detection and recognition (TSDR) system is a vital component of intelligent transport system. It plays an important role by enhancing the safety of drivers, pedestrians and vehicles as traffic signs provide important information of the traffic environment of the road and assist the drivers to drive more safely and easily. During night time driving, visibility is affected by low light or even drivers might get dazzled by on-coming headlights. Hence, it is very important to have an automatic system that can recognize warning and prohoibitory traffic signs and give early warning to the drivers which in turns can avert potential hazard. The main idea of this system is to detect and recognize the traffic sign in night conditions by using feature matching method. Firstly, color input image is converted from RGB to grayscale image. Secondly, edge detection is done by using Sobel edge detection and segmentation is done by adaptive threshold. Then, potential signs are compared with the template signs as given in the database by using feature matching methods SURF features (Speed Up Robust Feature). In this paper, the images have been tested for off-line situations. From the experimental results, it is seen that this method can match the traffic sign effectively for night conditions.
Traffic Sign Detection, Sobel Edge Detection, Speed Up Robust Feature, Advanced Driver Assistance System