基于尾灯的夜间前方车辆检测与跟踪方法
|
摘要
针对夜间环境下车辆难以检测的问题,提出一种基于尾灯的夜间前方车辆检测与跟踪方法。首先根据光晕特征和亮度特征进行车辆尾灯提取,对尾灯进行配对后根据尾灯对估计车辆的位置并实现对车辆的检测,然后利用改进的粒子滤波算法对已检测车辆的尾灯进行跟踪,进而实现对车辆的跟踪。最后结合检测和跟踪方法提出一种车辆检测与跟踪系统。实验结果表明:本文方法具有检测率高的特点,对车辆检测率可达96%,车辆检测与跟踪系统可解决车辆互相遮挡情况下的车辆检测问题,并可提升车辆检测率至98%。
To solve the problem that the vehicle is difficult to detect in night environment, a method of preceding vehicle detection and tracking at night based on taillights was proposed. Firstly, the taillights were extracted according to the characteristics of halo and brightness, and the vehicles were detected after the taillights were paired and its location were estimated by pairs of taillights. Then the improved particle filter algorithm was used to track the taillights of the detected vehicles, and vehicles were tracked according to the tracked taillights. Finally, a vehicle detection and tracking system was proposed combined with the detection and tracking method. According to the data collected, the experiment results show that the detection rate of the proposed detection method can reach96%. The vehicle detection and tracking system can solve the problem of vehicle detection under the condition of mutual occlusion of vehicles, and can improve the detection rate of vehicles to 98%.
To solve the problem that the vehicle is difficult to detect in night environment, a method of preceding vehicle detection and tracking at night based on taillights was proposed. Firstly, the taillights were extracted according to the characteristics of halo and brightness, and the vehicles were detected after the taillights were paired and its location were estimated by pairs of taillights. Then the improved particle filter algorithm was used to track the taillights of the detected vehicles, and vehicles were tracked according to the tracked taillights. Finally, a vehicle detection and tracking system was proposed combined with the detection and tracking method. According to the data collected, the experiment results show that the detection rate of the proposed detection method can reach96%. The vehicle detection and tracking system can solve the problem of vehicle detection under the condition of mutual occlusion of vehicles, and can improve the detection rate of vehicles to 98%.
引文
[1]FLEYEH H,MOHAMMED I.Night time vehicle detection[J].Journal of Intelligent Systems,2012,21(2):143-165.
[2]LIORCA D F,SANCHEZ S,MANUEL O,et al.Vision-based traffic data collection sensor for automotive applications[J].Sensors,2010,10(1):860-875.
[3]LIN S,CHEN Y,WU B.A real-time multiple-vehicle detection and tracking system with prior occlusion detection and resolution[C]//Proceedings of the 18th International Conference on Pattern Recognition.Hong Kong:IEEE,2006:828-831.
[4]SUN Z,BEBIS G,MILLER R.On-road vehicle detection using optical sensors:A review[C]//The International IEEE Conference on Intelligent Transportation Systems,2004 Proceedings.Washington D.C.:IEEE,2004:585-590.
[5]刘勃,周荷琴,魏铭旭.基于颜色和运动信息的夜间车辆检测方法[J].中国图象图形学报,2005,10(2):187-191.LIU B,ZHOU H Q,WEI M X.Vehicle detection at night using color and motion information[J].Journal of Image and Graphics,2005,10(2):187-191(in Chinese).
[6]刘尊洋,叶庆,李菲,等.基于亮度与颜色四阈值的尾灯检测算法[J].计算机工程,2010,36(21):202-203,206.LIU Z Y,YE Q,LI F,et al.Taillight detection algorithm based on four thresholds of brightness and color[J].Computer Engineering,2010,36(21):202-203,206(in Chinese).
[7]ALT N,CLAUS C,STECHELE W.Hardware/software architecture of an algorithm for vision-based real-time vehicle detection in dark environments[C]//Design,Automation and Test in Europe.Munich:IEEE,2008:176-181.
[8]O′MALLEY R,JONES E,GLAVIN M.Rear-lamp vehicle detection and tracking in low-exposure color video for night conditions[J].IEEE Transactions on Intelligent Transportation Systems,2010,11(2):453-462.
[9]肖志涛,王悦,耿磊,等.基于团块几何和位置特征的夜间前方车辆检测方法[J].河北工业大学学报,2013,42(5):13-18.XIAO Z T,WANG Y,GENG L,et al.Preceding vehicle detecting method for night based on geometry and position features of blobs[J].Journal of Hebei University of Technology,2013,42(5):13-18(in Chinese).
[10]KUNG D C,LIN J,HSIA P,et al.Object-oriented real time systems modeling and verification[C]//In Proceedings of Third International Workshop on Object-Ori ented Real-Time Dependable Systems 1997.Newport Beach:IEEE,1997:224-231.
[11]KATO T,NINOMIYA Y,MASAKI I.Preceding vehicle recognition based on learning from sample images[J].IEEE Transactions on Intelligent Transportation Systems,2002,3(4):252-260.
[12]查宇飞,毕笃彦,杨源.视频目标跟踪方法[M].北京:国防工业出版社,2015:8-9,228-234.ZHA Y F,BI D Y,YANG Y.Video Object Tracking Method[M].Beijing:National Defense Industry Press,2015:8-9,228-234(in Chinese).
[13]GORMER S,MULLER D,HOLD S,et al.Vehicle recognition and TTC estimation at night based on spotlight pairing[C]//International IEEE Conference on Intelligent Transportation Systems.St.Louis:IEEE,2009:1-6.
[14]OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on System Man and Cybernetic,1979,9(1):62-66.
[15]LIN Y C,LIN C C,CHEN L T.Adaptive IPM-based lane filtering for night forward vehicle detection[C]//IEEE Conference on Industrial Electronics and Applications.Beijing:ICIEA,2011.
[16]蔡荣太,吴元昊,王明佳,等.视频目标跟踪算法综述[J].电视技术,2010,34(12):135-138.CAI R T,WU Y H,WANG M J,et al.Survey of visual object tracking algorithms[J].TV Technology,2010,34(12):135-138(in Chinese).
[17]LIU J S,CHEN R.Sequetial Monto Carlo methods for dynamical systems[J].Journal of American Statistical Association,1998,93(443):1032-1044.
[18]QING M,JO K H.A novel particle filter implementation for a multiple-vehicle detection and tracking system using tail light segmentation[J].International Journal of Control,Automation and Systems,2013,11(3):577-585.
[19]刘婕.复杂场景多特征融合粒子滤波目标跟踪[D].重庆:重庆理工大学,2015.LIU J.Multi-feature fusion target tracking based on particle filter in complex scene[D].Chongqing:Chongqing University of Technology,2015(in Chinese).
[20]FRANK J A,NEIL A T,PETER I R.The Bhattacharyya metric as an absolute similarity measure for frequency coded data[J].Kybernetika,1998,34(4):363-368.
[21]THOMAS S,CARLOWITZC V,ZOLLNERJ M.On-road vehicle detection during dusk and at night[C]//IEEE Intelligent vehicles symposium.La Jolla,CA,USA:IEEE,2010:418-423.
[2]LIORCA D F,SANCHEZ S,MANUEL O,et al.Vision-based traffic data collection sensor for automotive applications[J].Sensors,2010,10(1):860-875.
[3]LIN S,CHEN Y,WU B.A real-time multiple-vehicle detection and tracking system with prior occlusion detection and resolution[C]//Proceedings of the 18th International Conference on Pattern Recognition.Hong Kong:IEEE,2006:828-831.
[4]SUN Z,BEBIS G,MILLER R.On-road vehicle detection using optical sensors:A review[C]//The International IEEE Conference on Intelligent Transportation Systems,2004 Proceedings.Washington D.C.:IEEE,2004:585-590.
[5]刘勃,周荷琴,魏铭旭.基于颜色和运动信息的夜间车辆检测方法[J].中国图象图形学报,2005,10(2):187-191.LIU B,ZHOU H Q,WEI M X.Vehicle detection at night using color and motion information[J].Journal of Image and Graphics,2005,10(2):187-191(in Chinese).
[6]刘尊洋,叶庆,李菲,等.基于亮度与颜色四阈值的尾灯检测算法[J].计算机工程,2010,36(21):202-203,206.LIU Z Y,YE Q,LI F,et al.Taillight detection algorithm based on four thresholds of brightness and color[J].Computer Engineering,2010,36(21):202-203,206(in Chinese).
[7]ALT N,CLAUS C,STECHELE W.Hardware/software architecture of an algorithm for vision-based real-time vehicle detection in dark environments[C]//Design,Automation and Test in Europe.Munich:IEEE,2008:176-181.
[8]O′MALLEY R,JONES E,GLAVIN M.Rear-lamp vehicle detection and tracking in low-exposure color video for night conditions[J].IEEE Transactions on Intelligent Transportation Systems,2010,11(2):453-462.
[9]肖志涛,王悦,耿磊,等.基于团块几何和位置特征的夜间前方车辆检测方法[J].河北工业大学学报,2013,42(5):13-18.XIAO Z T,WANG Y,GENG L,et al.Preceding vehicle detecting method for night based on geometry and position features of blobs[J].Journal of Hebei University of Technology,2013,42(5):13-18(in Chinese).
[10]KUNG D C,LIN J,HSIA P,et al.Object-oriented real time systems modeling and verification[C]//In Proceedings of Third International Workshop on Object-Ori ented Real-Time Dependable Systems 1997.Newport Beach:IEEE,1997:224-231.
[11]KATO T,NINOMIYA Y,MASAKI I.Preceding vehicle recognition based on learning from sample images[J].IEEE Transactions on Intelligent Transportation Systems,2002,3(4):252-260.
[12]查宇飞,毕笃彦,杨源.视频目标跟踪方法[M].北京:国防工业出版社,2015:8-9,228-234.ZHA Y F,BI D Y,YANG Y.Video Object Tracking Method[M].Beijing:National Defense Industry Press,2015:8-9,228-234(in Chinese).
[13]GORMER S,MULLER D,HOLD S,et al.Vehicle recognition and TTC estimation at night based on spotlight pairing[C]//International IEEE Conference on Intelligent Transportation Systems.St.Louis:IEEE,2009:1-6.
[14]OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on System Man and Cybernetic,1979,9(1):62-66.
[15]LIN Y C,LIN C C,CHEN L T.Adaptive IPM-based lane filtering for night forward vehicle detection[C]//IEEE Conference on Industrial Electronics and Applications.Beijing:ICIEA,2011.
[16]蔡荣太,吴元昊,王明佳,等.视频目标跟踪算法综述[J].电视技术,2010,34(12):135-138.CAI R T,WU Y H,WANG M J,et al.Survey of visual object tracking algorithms[J].TV Technology,2010,34(12):135-138(in Chinese).
[17]LIU J S,CHEN R.Sequetial Monto Carlo methods for dynamical systems[J].Journal of American Statistical Association,1998,93(443):1032-1044.
[18]QING M,JO K H.A novel particle filter implementation for a multiple-vehicle detection and tracking system using tail light segmentation[J].International Journal of Control,Automation and Systems,2013,11(3):577-585.
[19]刘婕.复杂场景多特征融合粒子滤波目标跟踪[D].重庆:重庆理工大学,2015.LIU J.Multi-feature fusion target tracking based on particle filter in complex scene[D].Chongqing:Chongqing University of Technology,2015(in Chinese).
[20]FRANK J A,NEIL A T,PETER I R.The Bhattacharyya metric as an absolute similarity measure for frequency coded data[J].Kybernetika,1998,34(4):363-368.
[21]THOMAS S,CARLOWITZC V,ZOLLNERJ M.On-road vehicle detection during dusk and at night[C]//IEEE Intelligent vehicles symposium.La Jolla,CA,USA:IEEE,2010:418-423.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |