单双摄像头切换的车辆车距侦测算法研究
|
摘要
在车道线被侦测出的前提下,前方车辆的侦测(Range of Interest,ROI)范围将会依赖这些车道线特征进行限定,随后根据车底阴影、车辆竖直方向上的特征以及车尾灯特征锁定前方车辆的位置,并且这些车辆的特征信息最终会转换成车距的信息。由于文中算法对白天以及夜晚两种不同情况做了相应差异化处理,且采用单双摄像头切换测距的方式,使得系统在中短距离的车距侦测具有优良的性能。实验表明,文章所设计的系统能够准确的侦测出多车道以及前方中短距离车距,系统的运行效率也能够达到实时性的要求,总体上很好的实现了预期的功能。
The range of interest(ROI) of the vehicle detection is defined after the lane has been detected, then according to the characteristics of the vehicle vertical direction, shadow under vehicles and taillight features to lock the front vehicle position, and the feature information of vehicles are converted into vehicle distance information finally. The algorithm proposed in this paper treats differently with day and night, and utilizes the strategy of single and double camera handover to detect the vehicle distance, which makes the system in short distance vehicle distance detecting with excellent performance. Experiments show that, this system designed in the paper, achieves the anticipated function, can accurately detect multi-lane and short distance vehicle distance,and the efficiency of the system also meets the real-time requirement.
The range of interest(ROI) of the vehicle detection is defined after the lane has been detected, then according to the characteristics of the vehicle vertical direction, shadow under vehicles and taillight features to lock the front vehicle position, and the feature information of vehicles are converted into vehicle distance information finally. The algorithm proposed in this paper treats differently with day and night, and utilizes the strategy of single and double camera handover to detect the vehicle distance, which makes the system in short distance vehicle distance detecting with excellent performance. Experiments show that, this system designed in the paper, achieves the anticipated function, can accurately detect multi-lane and short distance vehicle distance,and the efficiency of the system also meets the real-time requirement.
引文
[1]黄海波,蒋伟荣,刘勇,等.基于SOPC的智能车辆道路识别与跟踪[J].仪器仪表学报,2012,33(2):321-326.HUANG H B,JIANG W R,LIU Y,et al.Road recognition and tracking for intelligent vehicle based on SOPC[J].Journal of Instrumentation and Instrumentation,2012,33(2):321-326.
[2]刘志强,温华.基于单目视觉的车辆碰撞预警系统[J].计算机应用,2007,8(27):2056-2058.LIU Z Q,WEN H.Vehicle collision warning system based on monocular vision[J].Journal of Computer Applications,2007,8(27):2056-2058.
[3]齐永龙,文菠.一种无线车辆检测传感器的设计[J].国外电子测量技术,2014,33(1):50-53.QI Y L,WEN B.Design of a wireless vehicle detection sensor[J].Foreign Electronic Measurement Technology,2014,33(1):50-53.
[4]沈舒,吴聪,李勃,等.基于优化SVM的高速公路交通事件检测[J].电子测量技术,2012,35(5):40-44.SHEN S,WU C,LI B,et al.Based on the optimization of SVMhighway traffic incident detection[J].Electronic Measurement Technology,2012,35(5):40-44.
[5]沈峘,李舜酩,柏方超,等.结构化道路中车道线的单目视觉检测方法[J].仪器仪表学报,2010,31(2):397-403.SHEN H,LI S M,BAI F C,et al.A method of monocular vision detection for lane lines in structured roads[J].Journal of Instrumentation and Instruments,2010,31(2):397-403.
[6]曹奎,冯玉才,曹忠升.基于颜色和形状特征的彩色图像表示与检索技术[J].计算机辅助设计与图形学学报,2001,3(10):906-91.CAO K,FENG Y C,CAO Z S.Color Image Representation and Retrieval Technology Based on Color and Shape Features[J].Journal of Computer-Aided Design&Computer Graphics,2001,3(10):906-91.
[7]朱周,路小波.基于椭圆拟合的车辆遮挡处理算法[J].仪器仪表学报,2015,36(1):209-214.ZHU Z,LU X B.Algorithm of Vehicle Occlusion Based on Ellipse Fitting[J].Chinese Journal of Scientific Instrument,2015,36(1):209-214.
[8]孙书诚,郎朗,王虎.基于路径识别的寻迹智能车设计与实现[J].安徽工程大学学报,2012,27(1):60-63.SUN S C,LANG L,WANG H.Design and Implementation of Tracing Intelligent Vehicle Based on Path Recognition[J].Journal of Anhui University of Technology,2012,27(1):60-63.
[9]王宁,蔡顺燕.考虑角度不定的车距视觉自动测量方法[J].科学技术与工程,2016,16(4):226-230.WANG N,CAI S Y.An Automated Vision Measurement Method Based on Uncertain Angle[J].Science Technology and Engineering,2016,16(4):226-230.
[10]漆月.一种基于视频传感器的嵌入式车距测试系统[J].西南师范大学学报(自然科学版),2012,37(1):104-107.QI Y.An Embedded System Based on Video Sensor is a Distance Test System[J].Journal of Southwest China Normal University(Natural Science Edition),2012,37(1):104-107.
[11]顾兆伦,邵雨辰,谢扬振,等.多环境下的实时前车检测与车距测量[J].信号处理,2015,31(9):1188-1194.GU Z L,SHAO Y C,XIEY Z,et al.Real-time vehicle detection and vehicle distance measurement in multi-environment[J].Signal Processing,2015,31(9):1188-1194.
[12]Gopalan T,saihong,Shneier,et al.Approach Towards Detection and Tracking of Lane Marking[J].Intelligent Transportation Systems,2012,13(3):1088-1098.
[13]Huang A S,Teller S.Lane boundary and curb estimation with lateral uncertainties[C].The 2009 International Conference on Autonomic and Trusted Computing,2012:330-336.
[14]Chang C Y,Lin C H.An Efficient Method for Lane-Mark Extraction in Complex Conditions[C].In 9th International Conference on Autonomic and Trusted Computing,2012:330-336.
[15]Zhuang J,Chen Y P,Xie J M,et al.Model-based Lane Detection and Lane Following for Intelligent Vehicles[C].Intermnation Conference on Intelligent Human-Machine Systems and Cybernetics,2010:170-175.
[2]刘志强,温华.基于单目视觉的车辆碰撞预警系统[J].计算机应用,2007,8(27):2056-2058.LIU Z Q,WEN H.Vehicle collision warning system based on monocular vision[J].Journal of Computer Applications,2007,8(27):2056-2058.
[3]齐永龙,文菠.一种无线车辆检测传感器的设计[J].国外电子测量技术,2014,33(1):50-53.QI Y L,WEN B.Design of a wireless vehicle detection sensor[J].Foreign Electronic Measurement Technology,2014,33(1):50-53.
[4]沈舒,吴聪,李勃,等.基于优化SVM的高速公路交通事件检测[J].电子测量技术,2012,35(5):40-44.SHEN S,WU C,LI B,et al.Based on the optimization of SVMhighway traffic incident detection[J].Electronic Measurement Technology,2012,35(5):40-44.
[5]沈峘,李舜酩,柏方超,等.结构化道路中车道线的单目视觉检测方法[J].仪器仪表学报,2010,31(2):397-403.SHEN H,LI S M,BAI F C,et al.A method of monocular vision detection for lane lines in structured roads[J].Journal of Instrumentation and Instruments,2010,31(2):397-403.
[6]曹奎,冯玉才,曹忠升.基于颜色和形状特征的彩色图像表示与检索技术[J].计算机辅助设计与图形学学报,2001,3(10):906-91.CAO K,FENG Y C,CAO Z S.Color Image Representation and Retrieval Technology Based on Color and Shape Features[J].Journal of Computer-Aided Design&Computer Graphics,2001,3(10):906-91.
[7]朱周,路小波.基于椭圆拟合的车辆遮挡处理算法[J].仪器仪表学报,2015,36(1):209-214.ZHU Z,LU X B.Algorithm of Vehicle Occlusion Based on Ellipse Fitting[J].Chinese Journal of Scientific Instrument,2015,36(1):209-214.
[8]孙书诚,郎朗,王虎.基于路径识别的寻迹智能车设计与实现[J].安徽工程大学学报,2012,27(1):60-63.SUN S C,LANG L,WANG H.Design and Implementation of Tracing Intelligent Vehicle Based on Path Recognition[J].Journal of Anhui University of Technology,2012,27(1):60-63.
[9]王宁,蔡顺燕.考虑角度不定的车距视觉自动测量方法[J].科学技术与工程,2016,16(4):226-230.WANG N,CAI S Y.An Automated Vision Measurement Method Based on Uncertain Angle[J].Science Technology and Engineering,2016,16(4):226-230.
[10]漆月.一种基于视频传感器的嵌入式车距测试系统[J].西南师范大学学报(自然科学版),2012,37(1):104-107.QI Y.An Embedded System Based on Video Sensor is a Distance Test System[J].Journal of Southwest China Normal University(Natural Science Edition),2012,37(1):104-107.
[11]顾兆伦,邵雨辰,谢扬振,等.多环境下的实时前车检测与车距测量[J].信号处理,2015,31(9):1188-1194.GU Z L,SHAO Y C,XIEY Z,et al.Real-time vehicle detection and vehicle distance measurement in multi-environment[J].Signal Processing,2015,31(9):1188-1194.
[12]Gopalan T,saihong,Shneier,et al.Approach Towards Detection and Tracking of Lane Marking[J].Intelligent Transportation Systems,2012,13(3):1088-1098.
[13]Huang A S,Teller S.Lane boundary and curb estimation with lateral uncertainties[C].The 2009 International Conference on Autonomic and Trusted Computing,2012:330-336.
[14]Chang C Y,Lin C H.An Efficient Method for Lane-Mark Extraction in Complex Conditions[C].In 9th International Conference on Autonomic and Trusted Computing,2012:330-336.
[15]Zhuang J,Chen Y P,Xie J M,et al.Model-based Lane Detection and Lane Following for Intelligent Vehicles[C].Intermnation Conference on Intelligent Human-Machine Systems and Cybernetics,2010:170-175.