Multiple sensor fusion for detecting location of curbs, walls, and barriers

被引:26
作者
Aufrère, R [1 ]
Mertz, C [1 ]
Thorpe, C [1 ]
机构
[1] Univ Clermont Ferrand, LASMEA, Clermont Ferrand, France
来源
IEEE IV2003: INTELLIGENT VEHICLES SYMPOSIUM, PROCEEDINGS | 2003年
关键词
D O I
10.1109/IVS.2003.1212896
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Knowledge of the location of curbs, walls, or barriers is important for guidance of vehicles or for the understanding of their surroundings. We have developed a method to detect such continous objects alongside and in front of a host vehicle. We employ a laser line striper, a vehicle state estimator, a video camera, and a laser scanner to detect the object at one location, track it alongside the vehicle, search for it in front of the vehicle and eliminate erroneous readings caused by occlusion from other objects.
引用
收藏
页码:126 / 131
页数:6
相关论文
共 10 条
[1]  
AUFRERE R, 2001, INT J MACHINE VISION, V13, P93
[2]   PARALLEL AND LOCAL FEATURE-EXTRACTION - A REAL-TIME APPROACH TO ROAD BOUNDARY DETECTION [J].
BROGGI, A .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1995, 4 (02) :217-223
[3]  
CANNY J, 1986, IEE T PATTERN ANAL M, V8
[4]   RECURSIVE 3-D ROAD AND RELATIVE EGO-STATE RECOGNITION [J].
DICKMANNS, ED ;
MYSLIWETZ, BD .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :199-213
[5]  
MERTZ C, 2002, IEEE INT VEH S JUN
[6]  
MERTZ C, 2000, P IEEE INT VEH S OCT
[7]  
POMERLEAU D, 1995, IEEE S INT VEH, P506
[8]  
Thorpe C., 2002, P 9 WORLD C INT TRAN
[9]  
THORPE C, P SPIE 4, V4715
[10]  
THORPE C, 2001, P INT ADV ROB PROGR