An Improved Image Enhancement Method for Traffic Sign Detection

Abstract

Traffic sign detection (TRD) is an essential component of advanced driver-assistance systems and an important part of autonomous vehicles, where the goal is to localize image regions that contain traffic signs. Over the last decade, the amount of research on traffic sign detection and recognition has significantly increased. Although TRD is a built-in feature in modern cars and several methods have been proposed, it is a challenging problem due to the high computational demand, the large number of traffic signs, complex traffic scenes, and occlusions. In addition, it is not clear how can we perform real-time traffic sign detection in embedded systems. In this paper, we focus on image enhancement, which is the first step of many object detection methods. We propose an improved probability-model-based image enhancement method for traffic sign detection. To demonstrate the efficiency of the proposed method, we compared it with other widely used image enhancement approaches in traffic sign detection. The experimental results show that our method increases the performance of object detection. In combination with the Selective Search object proposal algorithm, the average detection accuracies were 98.64% and 99.1% on the GTSDB and Swedish Traffic Signs datasets. In addition, its relatively low computational cost allows for its usage in embedded systems.

Traffic Sign Detection and Recognition Using Multi-Frame Embedding of Video-Log Images

“…Some researchers have improved model performance without changing the detector by using pre-processing techniques, such as image enhancement based on probabilistic models [31], highlighting edge features of traffic signs [32], and enhancing the hue of dark areas of images [33]. In addition, on-board cameras typically take high-resolution images for sensing the vehicle's surroundings but increase the search range for traffic signs.…”