車道偏離警示系統之設計與分析

Design and Analysis of Lane Departure Warning System

辜信彰(Hsin-Chang Ku)

指導教授 ： 陳柏全

國立臺北科技大學/機電學院/車輛工程系所/碩士(2005年)

摘要

一般交通事故發生的原因，常為駕駛人疏忽而導致車輛偏離車道。為了防止車輛偏離車道，本研究利用單一CCD照相機，架設在車內後照鏡之位置，以便擷取道路影像，接著利用二值化處理技術，分離出道路標線與路面，進行道路標線偵測及群組化。將所偵測到之道路標線特徵點，透過逆透視轉換的過程，轉換成從特定的高度觀察之俯視景觀，再利用二次曲線擬合方式，建構出車道模型。本研究利用自行車模型，預估車輛未來行駛路徑，並配合車道模型，計算出車道偏離時間，將依其大小，定義不同之警示層級，以發佈警示訊號，提醒駕駛者適當地修正行駛方向，避免發生車道偏離情形。

關鍵字

道路標線偵測 ； 預估 ； 偏離時間 ； 自行車模型 ； 車道偏離警示

並列摘要

In general, the cause of traffic accident is primarily due to that the driver is not conscious of the vehicle deviating from the lane. In order to avoid this, a lane departure warning system is proposed in this paper. A CCD camera is mounted on the rear-view mirror to capture the road image. Lane detection technology is used to separate the lane marking pixels form the road, which are them grouped into two parts. The characteristic points of the detected lane marking are transformed into the bird's view of the specific height via the Inverse Perspective Mapping (IPM). A second–order polynomial is used for curve fitting to obtain the lane model. A bicycle model is used to predict the future trajectory, which is them combined with the lane model to calculate the Time-to-Lane-Crossing (TLC). Based on the TLC, different warning levels are defined for issuing warning message, to remind the driver to correct his/her steering. Thus prevent the lane departure accident.

並列關鍵字

lane detection ； predict ； Time-to-Lane-Crossing ； bicycle model ； lane departure warning

參考文獻

[29] 莊舒云，車輛行駛車道偏離警示系統之開發研究，碩士論文，國立台灣大學工程科學與海洋工程研究所，台北，2004。

[9] Broggi, A., "A Massively Parallel Approach to Real-Time Vision-Based Road Markings Detection," Proceedings IEEE Intelligent Vehicles, 1995, pp. 84-89.

[11] Broggi, A., "Robust Real-Time Lane and Road Detection in Critical Shadow Conditions," International Symposium on Proceedings of Computer Vision, 1995 pp. 21-23.

[12] Bertozzi, M. and Broggi, A., "GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection," IEEE Transactions on Image Processing, Vol. 7, No.1, 1998, pp. 62-81.

[14] Gonzalez, J. P. and Ozguner, U., "Lane detection using histogram-based segmentation and decision trees," Intelligent Transportation Systems, 2000, pp. 346-351.