Abstract
Keywords:
Traffic sign recognition, Traffic signal recognition, Pattern recognition, Image sensor, Image processing
Abstract
Numerous traffic accidents and dangerous situations arise from careless driving where drivers may not recognize the traffic environment including traffic signals and speed limit signboards. Recently, various kinds of intelligent systems have been developed to promote driving safety and convenience. In this paper, an algorithm to recognize the traffic signals and speed limit signboards using an image sensor is proposed and the test results are shown with various road situations and environments. In this algorithm, candidate traffic signals can be chosen by checking the ratios of heights and widths of candidate boxes because the ratios for the traffic signals are standardized. The position of red, yellow, green, and direction signs of the traffic signal are also standardized, so final decision to recognize the traffic signals can be made easily and the colors of the traffic signals are identified based on brightness. Speed limit signboard can be also recognized using standardized color and shape information and the speed limit number can be identified using a fast and effective pattern recognition algorithm which is appropriate for real time application. The recognized information of traffic signal or speed limit signboard is informed to driver through display device and speaker