东南大学学报（自然科学版）
東南大學學報（自然科學版）
동남대학학보（자연과학판）
JOURNAL OF SOUTHEAST UNIVERSITY
2009年
5期
933-936
,共4页
机器视觉%车道偏离%摄像机模型%车道线
機器視覺%車道偏離%攝像機模型%車道線
궤기시각%차도편리%섭상궤모형%차도선
machine vision%lane departure%camera model%lane lines
针对车道偏离检测中较难解决的车载摄像机标定问题,从分析摄像机成像模型入手,根据图像中3条或3条以上车道线的消失点位置以及车道线斜率关系,在道路现场调整摄像机安装位置,以实现对摄像机外部参数的直接设定,从而避开了繁琐的摄像机参数标定过程.同时,推导出图像内车道线斜率比与车道偏离程度的简单函数关系,该函数与摄像机内外参数无关.因此,行车过程中只需测量图像中车道线的斜率,即可计算出车辆当前的车道偏离量.现场试验结果表明,在车辆直行时采用该方法测得的车道偏离率与手工实测结果相比,其相对误差小于5%,具备了较高的检测精度.
針對車道偏離檢測中較難解決的車載攝像機標定問題,從分析攝像機成像模型入手,根據圖像中3條或3條以上車道線的消失點位置以及車道線斜率關繫,在道路現場調整攝像機安裝位置,以實現對攝像機外部參數的直接設定,從而避開瞭繁瑣的攝像機參數標定過程.同時,推導齣圖像內車道線斜率比與車道偏離程度的簡單函數關繫,該函數與攝像機內外參數無關.因此,行車過程中隻需測量圖像中車道線的斜率,即可計算齣車輛噹前的車道偏離量.現場試驗結果錶明,在車輛直行時採用該方法測得的車道偏離率與手工實測結果相比,其相對誤差小于5%,具備瞭較高的檢測精度.
침대차도편리검측중교난해결적차재섭상궤표정문제,종분석섭상궤성상모형입수,근거도상중3조혹3조이상차도선적소실점위치이급차도선사솔관계,재도로현장조정섭상궤안장위치,이실현대섭상궤외부삼수적직접설정,종이피개료번쇄적섭상궤삼수표정과정.동시,추도출도상내차도선사솔비여차도편리정도적간단함수관계,해함수여섭상궤내외삼수무관.인차,행차과정중지수측량도상중차도선적사솔,즉가계산출차량당전적차도편리량.현장시험결과표명,재차량직행시채용해방법측득적차도편리솔여수공실측결과상비,기상대오차소우5%,구비료교고적검측정도.
To solve the calibration problem of camera in lane departure detection, the imaging model is analyzed and the installing position of camera can be adjusted according to the slope and vanishing point of three or more lane lines in the image. At the same time, external parameters of the camera are directly set without complicated calibration. Based on this, the relationship between lane departure and the ratio of lane line's slope is concluded as a simple function which is unconcerned with the parameters of camera. Therefore, the quantity of lane departure can be calculated so far as this ratio is measured. Actual experiment result demonstrates that the precision of lane departure detection by this method is high, and the relative error is less than 5 % compared with manual measurement.
