面向车辆自主驾驶的行人跟踪算法
|
摘要
基于背景感知相关滤波框架和车辆前方行人运动的特点,建立了运动行人尺度快速估计和选择性更新的行人跟踪算法。首先,在线训练学习待跟踪行人的背景感知相关滤波器。其次,针对行人的尺度变化训练一个一维的尺度相关滤波器对尺度进行精细搜索,使算法更适应车载的快速尺度变化。再次,利用峰值旁瓣比评价行人状态,建立两相关滤波器的选择性更新机制。最后,基于吉林大学车载试验数据库JLU-PDS、德国奔驰Daimler、美国OTB共享国际测试库,与卡尔曼车载行人跟踪算法进行对比测试,试验结果表明本文算法具有较好的尺度适应和抗遮挡性能,更能满足车辆自主驾驶的需求。
Pedestrian tracking is the base for pedestrian behavior analysis and driving decision-making.There exist several problems such as the fast scale change of pedestrian caused by rapid movement of vehicle, the pedestrian occlusion, etc, which make the traditional tracking algorithm difficult to track pedestrians accurately, and it is more difficult to analyze pedestrian movement. To overcome the problems,a new pedestrian tracking method is presented in the paper. In the method, scale estimation and selective updating strategy were used to deal with fast scale change of pedestrian and occluded in the framework of background-aware correlation filter. First, a background-aware correlation filter was trained online for the pedestrian to be tracked. Secondl an one-dimensional scale correlation filter was trained to search the scale of pedestrians carefully, so that the algorithm is more adaptable to fast scale change in the case of vehicle driving. Finally, a selective updating mechanism of the correlation filters was set up by using the peak sidelobe ratio to evaluate the pedestrian status. In experiments, the proposed method was compared with Kalman filter pedestrian tracking algorithm on JLU-PDS, Daimler Pedestrian Benchmark Data Set and some video sequences from Object Tracking Benchmark. The results show that the proposed method has better scale adaptation and anti occlusion performance, and it is more adaptable to the autonomous driving.
Pedestrian tracking is the base for pedestrian behavior analysis and driving decision-making.There exist several problems such as the fast scale change of pedestrian caused by rapid movement of vehicle, the pedestrian occlusion, etc, which make the traditional tracking algorithm difficult to track pedestrians accurately, and it is more difficult to analyze pedestrian movement. To overcome the problems,a new pedestrian tracking method is presented in the paper. In the method, scale estimation and selective updating strategy were used to deal with fast scale change of pedestrian and occluded in the framework of background-aware correlation filter. First, a background-aware correlation filter was trained online for the pedestrian to be tracked. Secondl an one-dimensional scale correlation filter was trained to search the scale of pedestrians carefully, so that the algorithm is more adaptable to fast scale change in the case of vehicle driving. Finally, a selective updating mechanism of the correlation filters was set up by using the peak sidelobe ratio to evaluate the pedestrian status. In experiments, the proposed method was compared with Kalman filter pedestrian tracking algorithm on JLU-PDS, Daimler Pedestrian Benchmark Data Set and some video sequences from Object Tracking Benchmark. The results show that the proposed method has better scale adaptation and anti occlusion performance, and it is more adaptable to the autonomous driving.
引文
[1]李文辉,周强,王莹,等.基于均值偏移粒子滤波的自适应跟踪[J].吉林大学学报:工学版,2012,42(2):407-411.Li Wen-hui,Zhou Qiang,Wang Ying,et al.Adaptive tracking algorithm based on particle filter-mean shift[J].Journal of Jilin University(Engineering and Technology Edition),2012,42(2):407-411.
[2]赵宏伟,冯嘉,臧雪柏,等.一种实用的运动目标检测和跟踪算法[J].吉林大学学报:工学版,2009,39(增刊2):386-390.Zhao Hong-wei,Feng Jia,Zang Xue-bai,et al.Practical moving target detection and tracking algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2009,39(Sup.2):386-390.
[3]李鹏,宋申民,陈兴林,等.基于迭代sigma点粒子滤波的再入目标跟踪[J].吉林大学学报:工学版,2009,39(6):1585-1589.Li Peng,Song Shen-min,Chen Xing-lin,et al.Iterative Sigma point filter in target tracking on reentry[J].Journal of Jilin University(Engineering and Technology Edition),2009,39(6):1585-1589.
[4]Li Fu-liang,Zhang Rong-hui,You Feng.Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment[J].Iet Image Processing,2017,11(10):833-840.
[5]Kwak J Y,Ko B,Nam J Y.Pedestrian tracking using online boosted random ferns learning in far-infrared imagery for safe driving at night[J].IEEE Transactions on Intelligent Transportation Systems,2017,18(1):1-13.
[6]Lee J Y,Yu W.Moving object tracking in driving environment[C]∥8th International Conference on Ubiquitous Robots&Ambient Intelligence,Incheon,Korea,2011:139-141.
[7]Fan Zi-pei,Wang Ze-liang,Cui Jin-shi,et al.Monocular pedestrian tracking from a moving vehicle[C]∥Asian Conference on Computer Vision,2012:335-346.
[8]Guo Lie,Li Lin-hui,Zhao Yi-bing,et al.Pedestrian tracking based on camshift with kalman prediction for autonomous vehicle[J].International Journal of Advanced Robotic Systems,2016,13(3):1-9.
[9]郭烈,张广西,葛平淑,等.基于特征组合粒子滤波的行人跟踪方法[J].计算机应用与软件,2013,30(11):4-7.Guo Lie,Zhang Guang-xi,Ge Ping-shu,et al.Pedestrian tracking based on particle filter with features combination[J],Computer Applications and Software,2013,30(11):4-7.
[10]李锴,冯瑞.基于粒子滤波的多特征融合视频行人跟踪算法[J].计算机工程,2012,38(24):141-145.Li Kai,Feng Rui.Pedestrian tracking algorithm in video of multi-feature fusion based on particle filter[J].Computer Engineering,2012,38(24):141-145.
[11]Xuan T N,Thomas M,Alois K.Robust pedestrian detection and tracking from a moving vehicle[J].Proceedings of the SPIE,2011,7878(6):536-547.
[12]Galoogahi H K,Fagg A,Lucey S.Learning background-aware correlation filters for visual tracking[J/OL].[2018-02-26].http:∥ci2cv.net/media/papers/436.pdf.
[13]李志慧,胡永利,赵永华,等.基于车载的运动行人区域估计方法[J].吉林大学学报:工学版,2018,48(3):694-703.Li Zhi-hui,Hu Yong-li,Zhao Yong-hua,et al.Locating moving pedestrian from running vehicle[J].Journal of jilin University(Engineering and Technology Edition),2018,48(3):694-703.
[14]Enzweiler M,Gavrila D M.Monocular pedestrian detection:survey and experiments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2179-2195.
[15]Wu Y,Lim J,Yang M H.Object Tracking Benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[16]Bolme D S,Beveridge J R,Draper B A,et al.Visual object tracking using adaptive correlation filters[C]∥2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,San Francisco,CA,USA,2010:1-10.
[17]Henriques J F,Caseiro R,Martins P.High-speed tracking with kernelized correlation filters[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
[18]Henriques J F,Caseiro R,Martins P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[J].Lecture Notes in Computer Science,2012,7575:702-715.
[19]Kiani H,Sim T,Lucey S.Correlation filters with limited boundaries[J].2015 IEEE Conference on Computer Vision and Pattern Recognition,Boston,Massachusetts,2015:4630-4638.
[20]Boyd S,Parikh N,Chu E,et al.Distributed optimization and statistical learning via the alternating direction method of multipliers[J].Foundations&Trends in Machine Learning,2010,3(1):1-122.
[21]Sherman J,Morrison W J.Adjustment of an inverse matrix corresponding to a change in one element of a given matrix[J].Annals of Mathematical Statistics,1950,21(1):124-127.
[22]Pathan S S,Al-Hamadi A,Michaelis B.Intelligent feature-guided multi-object tracking using kalman filter[C]∥2nd International Conference on Computer,Control and Communication,Karachi,Pakistan,2009:1-6.
[2]赵宏伟,冯嘉,臧雪柏,等.一种实用的运动目标检测和跟踪算法[J].吉林大学学报:工学版,2009,39(增刊2):386-390.Zhao Hong-wei,Feng Jia,Zang Xue-bai,et al.Practical moving target detection and tracking algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2009,39(Sup.2):386-390.
[3]李鹏,宋申民,陈兴林,等.基于迭代sigma点粒子滤波的再入目标跟踪[J].吉林大学学报:工学版,2009,39(6):1585-1589.Li Peng,Song Shen-min,Chen Xing-lin,et al.Iterative Sigma point filter in target tracking on reentry[J].Journal of Jilin University(Engineering and Technology Edition),2009,39(6):1585-1589.
[4]Li Fu-liang,Zhang Rong-hui,You Feng.Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment[J].Iet Image Processing,2017,11(10):833-840.
[5]Kwak J Y,Ko B,Nam J Y.Pedestrian tracking using online boosted random ferns learning in far-infrared imagery for safe driving at night[J].IEEE Transactions on Intelligent Transportation Systems,2017,18(1):1-13.
[6]Lee J Y,Yu W.Moving object tracking in driving environment[C]∥8th International Conference on Ubiquitous Robots&Ambient Intelligence,Incheon,Korea,2011:139-141.
[7]Fan Zi-pei,Wang Ze-liang,Cui Jin-shi,et al.Monocular pedestrian tracking from a moving vehicle[C]∥Asian Conference on Computer Vision,2012:335-346.
[8]Guo Lie,Li Lin-hui,Zhao Yi-bing,et al.Pedestrian tracking based on camshift with kalman prediction for autonomous vehicle[J].International Journal of Advanced Robotic Systems,2016,13(3):1-9.
[9]郭烈,张广西,葛平淑,等.基于特征组合粒子滤波的行人跟踪方法[J].计算机应用与软件,2013,30(11):4-7.Guo Lie,Zhang Guang-xi,Ge Ping-shu,et al.Pedestrian tracking based on particle filter with features combination[J],Computer Applications and Software,2013,30(11):4-7.
[10]李锴,冯瑞.基于粒子滤波的多特征融合视频行人跟踪算法[J].计算机工程,2012,38(24):141-145.Li Kai,Feng Rui.Pedestrian tracking algorithm in video of multi-feature fusion based on particle filter[J].Computer Engineering,2012,38(24):141-145.
[11]Xuan T N,Thomas M,Alois K.Robust pedestrian detection and tracking from a moving vehicle[J].Proceedings of the SPIE,2011,7878(6):536-547.
[12]Galoogahi H K,Fagg A,Lucey S.Learning background-aware correlation filters for visual tracking[J/OL].[2018-02-26].http:∥ci2cv.net/media/papers/436.pdf.
[13]李志慧,胡永利,赵永华,等.基于车载的运动行人区域估计方法[J].吉林大学学报:工学版,2018,48(3):694-703.Li Zhi-hui,Hu Yong-li,Zhao Yong-hua,et al.Locating moving pedestrian from running vehicle[J].Journal of jilin University(Engineering and Technology Edition),2018,48(3):694-703.
[14]Enzweiler M,Gavrila D M.Monocular pedestrian detection:survey and experiments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2179-2195.
[15]Wu Y,Lim J,Yang M H.Object Tracking Benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[16]Bolme D S,Beveridge J R,Draper B A,et al.Visual object tracking using adaptive correlation filters[C]∥2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,San Francisco,CA,USA,2010:1-10.
[17]Henriques J F,Caseiro R,Martins P.High-speed tracking with kernelized correlation filters[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
[18]Henriques J F,Caseiro R,Martins P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[J].Lecture Notes in Computer Science,2012,7575:702-715.
[19]Kiani H,Sim T,Lucey S.Correlation filters with limited boundaries[J].2015 IEEE Conference on Computer Vision and Pattern Recognition,Boston,Massachusetts,2015:4630-4638.
[20]Boyd S,Parikh N,Chu E,et al.Distributed optimization and statistical learning via the alternating direction method of multipliers[J].Foundations&Trends in Machine Learning,2010,3(1):1-122.
[21]Sherman J,Morrison W J.Adjustment of an inverse matrix corresponding to a change in one element of a given matrix[J].Annals of Mathematical Statistics,1950,21(1):124-127.
[22]Pathan S S,Al-Hamadi A,Michaelis B.Intelligent feature-guided multi-object tracking using kalman filter[C]∥2nd International Conference on Computer,Control and Communication,Karachi,Pakistan,2009:1-6.
© 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 |