Real time Detection of Lane Markers in Urban Streets

被引：500

作者：

Aly, Mohamed ^{[1
]}

机构：

[1] CALTECH, Computat Vis Lab Elect Engn, Pasadena, CA 91125 USA

来源：

2008 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3 | 2008年

关键词：

D O I：

10.1109/ivs.2008.4621152

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：

We present a robust and real time approach to lane marker detection in urban streets. It is based on generating a top view of the road, filtering using selective oriented Gaussian filters, using RANSAC line fitting to give initial guesses to a new and fast RANSAC algorithm for fitting Bezier Splines, which is then followed by a post-processing step. Our algorithm can detect all lanes in still images of the street in various conditions, while operating at a rate of 50 Hz and achieving comparable results to previous techniques.

引用

页码：165 / 170

页数：6

共 15 条

[1]

[Anonymous], CURVES SURFACES COMP

[2]

Bertozzi M, 1997, IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, P1010, DOI 10.1109/ITSC.1997.660612

[3]

BERTOZZI M, 1996, INT VEH S 1996 P 199, P213

[4]

Forsyth DA, 2002, COMPUTER VISION MODE

[5] Autonomous driving goes downtown [J].

Franke, U ;

Gavrila, D ;

Gorzig, S ;

Lindner, F ;

Paetzold, F ;

Wohler, C .

IEEE INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 1998, 13 (06) :40-48

[6]

FRANKE U, 1996, INT VEH S TOK, P339

[7]

HONG W, 2006, INT TRANSP SYST P IE, P1226

[8]

Kim Z., 2006, P IEEE C INT TRANSP, P1149

[9]

KLUGE K, 1994, INT VEH S, P109

[10] LANA: A lane extraction algorithm that uses frequency domain features [J].

Kreucher, C ;

Lakshmanan, S .

IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 1999, 15 (02) :343-350

← 1 2 →