CLARK: a heterogeneous sensor fusion method for finding lanes and obstacles

被引：23

作者：

Beauvais, M ^{[1
]}

Lakshmanan, S ^{[1
]}

机构：

[1] Univ Michigan, Dept Elect & Comp Engn, Dearborn, MI 48128 USA

来源：

IMAGE AND VISION COMPUTING | 2000年 / 18卷 / 05期

关键词：

Bayesian detection; intelligent vehicles; deformable templates; global shape matching;

D O I：

10.1016/S0262-8856(99)00035-9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes Combined Likelihood Adding Radar Knowledge (CLARK), a new method for detecting lanes and obstacles by fusing information from two forward-looking vehicle mounted sensors-vision and radar. CLARK has three stages: (1) obstacle detection using a novel template matching approach; (2) lane detection using a modified version of the Likelihood Of Image Shape algorithm; (3) simultaneous estimation of both obstacle and lane positions by locally maximizing a combined likelihood function. Experimental results illustrating the efficacy of these components are presented. CLARK detects the position of lanes and obstacles accurately, even under significantly noisy conditions. (C) 2000 Elsevier Science B.V. All rights reserved.

引用

页码：397 / 413

页数：17

共 50 条

[1]

*AAMA, 1996, MOT VEH FACTS FIG 19

[2] Development of rear-end collision avoidance system [J].

Araki, H ;

Yamada, K ;

Hiroshima, Y ;

Ito, T .

PROCEEDINGS OF THE 1996 IEEE INTELLIGENT VEHICLES SYMPOSIUM, 1996, :224-229

[3]

Azevedo S., 1997, IEEE Potentials, V16, P15, DOI 10.1109/45.580443

[4]

BEAUVAIS M, 1997, P 1 IEEE INT TRANSP

[5] Real-time lane and obstacle detection on the gold system [J].

Bertozzi, M ;

Broggi, A .

PROCEEDINGS OF THE 1996 IEEE INTELLIGENT VEHICLES SYMPOSIUM, 1996, :213-218

[6]

BLINCOE LJ, 1994, EC COST MOTOR VEHICL

[7] REAL-TIME OBSTACLE AVOIDANCE FOR FAST MOBILE ROBOTS [J].

BORENSTEIN, J ;

KOREN, Y .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1989, 19 (05) :1179-1187

[8]

BULUSWAR S, 1997, COLOR MACHINE VISION

[9]

CARTER R, 1996, P SPIE TRANSP SENS C, V2902, P250

[10]

CARTER R, 1996, P HUM FACT ERG SOC 4, V2, P1017

← 1 2 3 4 5 →