JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 26, 735-752 (2010) 735 Real-Time Front Vehicle Detection Algorithm for an Asynchronous Binocular System * CHUNG-CHENG CHIU, MENG-LIANG CHUNG AND WEN-CHUNG CHEN Department of Electrical and Electronic Engineering Chung-Cheng Institute of Technology National Defense University Taoyuan, 335 Taiwan This paper describes a multi-resolution stereovision system for detecting the front- vehicle in advanced safety vehicles (ASVs). The two asynchronous CMOS cameras in the proposed system are mounted on a platform that can be easily clamped to the rear- view mirror of a vehicle for detecting vehicles ahead. The asynchronous binocular plat- form provides a small low-cost obstacle detection system for practical ASVs that is easy to set up. The system uses a stereovision vehicle detection algorithm for real-time matching because the exposure times of the CMOS cameras are not synchronous. The algorithm uses a line segment matching module to match the extreme points of the hori- zontal and vertical edge segments at different resolutions to decrease the search area and computing complexity. As the distance of each matched segment can be calculated from the disparity value, each vehicle can be detected by clustering the segments that have similar distances in a searching and distance estimation module. The system was evalu- ated using static and dynamic analyses. Experimental results show that the proposed sys- tem can robustly and accurately detect the front-vehicles in real time under different il- lumination and road conditions. Keywords: intelligent transportation system, driving safety, front-vehicle detection, bin- ocular system, stereovision 1. INTRODUCTION Passive safety systems such as air bags, seat belts, and anti-lock braking systems are widely used in vehicles. Combining these with active (pre-crash) safety sensors would increase passenger safety by helping to avoid collisions. According to the National High- way Traffic Safety Administration [1], forward collision warning systems (FCWS) can effectively reduce rear-end collisions by 21%. FCWS are on-board electronic systems that monitor the roadway in front of a vehicle and warn the driver when a potential collision risk exists. The devices currently available for detecting obstacles rely on vision sensors, laser radar, and millimeter-wave radar. Although millimeter-wave radar [2-5] has a good range, its angular resolution is low. Millimeter-wave radar systems have been used on commer- cial vehicles [6], but they are not suitable for distinguishing vehicles in complex back- grounds, such as urban areas or bumpy roads, and are still very expensive compared with other sensors. Other collision avoidance systems [7-9] have used laser radar as the sensor. Received March 31, 2009; accepted September 30, 2009. Communicated by Chih-Yung Chang, Chien-Chung Shen, Xuemin (Sherman) Shen, and Yu-Chee Tseng. * This work was also partially supported by National Science Council of Taiwan under the Grant No. NSC 96- 2221-E-606-026.