Abstract
In this paper, we propose a new Intelligent Traffic Sign Recognition (ITSR) system with illumination preprocessing capability. Our proposed Dark Area Sensitive Tone Mapping (DASTM) technique can enhance the illumination of only dark regions of an image with little impact on bright regions. We used this technique as a pre-processing module for our new traffic sign recognition system. We combined DASTM with a TS detector, an optimized version of YOLOv3 for the detection of three classes of traffic signs. We trained ITSR on a dataset of Korean traffic signs with prohibitory, mandatory, and danger classes. We achieved Mean Average Precision (MAP) value of 90.07% (previous best result was 86.61%) on challenging Korean Traffic Sign Detection (KTSD) dataset and 100% on German Traffic Sign Detection Benchmark (GTSDB). Result comparisons of ITSR with latest D-Patches, TS detector, and YOLOv3 show that our new ITSR significantly outperforms in recognition performance.
Highlights
Development of automatic traffic sign recognition systems with high accuracy is a very important issue because this system can alert the driver about the road conditions and speed limits by recognizing the traffic signs from a large distance
Korean Traffic Sign Detection (KTSD) dataset, dataset, and and we we developed a new system with illumination preprocessing developed a new Intelligent Traffic Sign Recognition (ITSR) system with illumination preprocessing capability
We have developed a new tone mapping method, Dark Area Sensitive Tone Mapping (DASTM), in which the luminance range is divided into multiple regions, and different tone mapping functions are used for the divided regions
Summary
Development of automatic traffic sign recognition systems with high accuracy is a very important issue because this system can alert the driver about the road conditions and speed limits by recognizing the traffic signs from a large distance. Low illumination on a traffic sign region due to bright background affects the recognition process and detector may fail to detect these traffic signs. ITSR intelligent system detect traffic traffic signs of prohibitory, mandatory, and danger classes, even in low illumination condition. This system is signs of prohibitory, mandatory, and danger classes, even in low illumination condition This system fast and efficient as compared to other detection methods and the detection accuracy of ITSR is. We applied technique illumination ofofdark dark traffic signs, we used classical tone mapping technique Wethis applied this on test dataset and analyzed the results. The luminance of dark traffic signs enhanced, this technique on test dataset and analyzed the results.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
