Real-time lane departure warning system based on principal component analysis of grayscale distribution and risk evaluation model
来源期刊:中南大学学报(英文版)2014年第4期
论文作者:ZHANG Wei-wei(张伟伟) SONG Xiao-lin(宋晓琳) ZHANG Gui-xiang(张桂香)
文章页码:1633 - 1642
Key words:lane departure warning system; lane detection; lane tracking; principal component analysis; risk evaluation model; ARM-based real-time system
Abstract: A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and then each search bar was tracked using Kalman filter between frames. The lane detection performance was evaluated and demonstrated in ways of receiver operating characteristic, dice similarity coefficient and real-time performance. For lane departure detection, a lane departure risk evaluation model based on lasting time and frequency was effectively executed on the ARM-based platform. Experimental results indicate that the algorithm generates satisfactory lane detection results under different traffic and lighting conditions, and the proposed warning mechanism sends effective warning signals, avoiding most false warning.
ZHANG Wei-wei(张伟伟), SONG Xiao-lin(宋晓琳), ZHANG Gui-xiang(张桂香)
(State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body (Hunan University),
Changsha 410082, China)
Abstract:A technology for unintended lane departure warning was proposed. As crucial information, lane boundaries were detected based on principal component analysis of grayscale distribution in search bars of given number and then each search bar was tracked using Kalman filter between frames. The lane detection performance was evaluated and demonstrated in ways of receiver operating characteristic, dice similarity coefficient and real-time performance. For lane departure detection, a lane departure risk evaluation model based on lasting time and frequency was effectively executed on the ARM-based platform. Experimental results indicate that the algorithm generates satisfactory lane detection results under different traffic and lighting conditions, and the proposed warning mechanism sends effective warning signals, avoiding most false warning.
Key words:lane departure warning system; lane detection; lane tracking; principal component analysis; risk evaluation model; ARM-based real-time system