Traffic sign recognition system for autonomous vehicle using cascade SVM classifier

Abstract

In past two decades, developing a system that can navigate vehicle autonomously becomes more interesting problem. The vehicle is equipped by sensors, such as radar, laser, GPS, and camera for sensing the surrounding. Among them, utilization of camera with computer vision technique is the most adopted method for constructing such a system. It is because camera provides a lot of information and is low-cost device rather than other sensors. Traffic road sign, as one of the important information from camera, carries a lot of useful information that are required for navigating. Thus, in this work, traffic sign detection and recognition is addressed. First, the input image is converted into normalize red and blue color space, as traffic sign usually appear with red and blue color. Second, maximally extremal stable region is then performed for extracting candidate region. Using heuristic rule of geometry properties, the false region will be excluded. Third, histogram of oriented gradient method is applied in order to extract feature from candidate region. Lastly, cascade support vector machine classifier is then processed to classify region belong to certain class of traffic sign. The extensive experiment would be carried out over German traffic sign recognition database and video. The experimental results demonstrate the effectiveness of our systems.

Circular Traffic Sign Detection in Natural Scenes

“…Intelligent transportation systems (ITS) have emerged. Among these new technologies, traffic sign recognition has been extensively studied [1], [2]. A traffic sign recognition system has an on-board camera that captures images, then uses image detection to precisely determine the traffic sign position and deliver information to drivers.…”

Use of Emerging Internet of Things Technologies for Developing Infrastructure-to-Vehicle Communication Systems

“…Because of the nature of the existing transportation infrastructure, where information is almost exclusively delivered to the drivers visually through traffic signs, most of the research in the field of autonomous driving and advanced driving assistance systems focuses on vision-based detection and recognition of traffic signs (10)(11)(12)(13)(14). Although vision-based methods have been rapidly improving in accuracy and detection speed throughout the last decade, they still have some weak points (15).…”

“…Although vision-based methods have been rapidly improving in accuracy and detection speed throughout the last decade, they still have some weak points ( 15 ). These include cases when the traffic sign is partially covered or occluded by objects such as trees and when the sign shape is deformed or rotated ( 12 , 13 ). Other problems reported in the literature include high sensitivity to light and weather conditions and sensitivity to traffic sign color relative to its background ( 16 ).…”