基于图像处理技术的行人运动轨迹提取方法
|
摘要
为了实现复杂场景中多运动行人目标的检测和跟踪,采用计算机视觉技术对真实场景下行人运动视频进行处理。利用基于高斯混合模型的背景消减法提取运动目标前景,并通过形态学运算进行目标清晰化处理。采用基于预测的Kalman滤波算法对运动目标进行跟踪,并对画面中的人数进行实时统计和更新。输出多运动行人目标的实时坐标和运动轨迹。研究结果表明:本文提出的算法能够快速准确地检测和追踪多运动行人目标,初步提取行人运动轨迹。
In order to achieve detection and tracking of multi-sport pedestrians in complex scenes, we processed the pedestrians' motion video in real scenes based on computer vision technology.First, the foreground of the moving object was extracted using the background subtraction method based on Gaussian mixture model.Morphological operation method was used to obtain clearer target.Then, Kalman filtering algorithm was applied to track the moving targets, calculating and updating the number of people in the screen. Finally, the real-time coordinates and motion trajectories of multi-motion pedestrians were output. The results indicate that the algorithm proposed in this paper can quickly and accurately detect and track multiple moving pedestrians, and extract pedestrian moving trajectories.
In order to achieve detection and tracking of multi-sport pedestrians in complex scenes, we processed the pedestrians' motion video in real scenes based on computer vision technology.First, the foreground of the moving object was extracted using the background subtraction method based on Gaussian mixture model.Morphological operation method was used to obtain clearer target.Then, Kalman filtering algorithm was applied to track the moving targets, calculating and updating the number of people in the screen. Finally, the real-time coordinates and motion trajectories of multi-motion pedestrians were output. The results indicate that the algorithm proposed in this paper can quickly and accurately detect and track multiple moving pedestrians, and extract pedestrian moving trajectories.
引文
[1]HELBING D,FARKAS I,VICSEK T.Simulating dynamical features of escape panic[J].Nature,2000,407(6803):487-490.
[2]KIRCHNER A,NISHINARI K,SCHADSCHNEIDER A.Friction effects and clogging in a cellular automaton model for pedestrian dynamics[J].Phys Rev E,2003,67(5):56-62.
[3]SONG W G,XU X,WANG BH,et al.Simulation of evacuation processes using a multi-grid model for pedestrian dynamics[J].Physica A,2006,363(2):492-500.
[4]MURAMATSU M,IRIE T,NAGATANI T.Jamming transition in pedestrian counter flow[J].Physica A,1999,267(3):487-498.
[5]KULIGOWSKI E D,PEACOCK R D,RENEKE PA,et al.Movement on stairs during building evacuations[R].NIST technical note,2015.
[6]KOBES M,HELSLOOT I,VRIES B,et al.Way finding during fire evacuation;an analysis of unannounced fire drills in a hotel at night[J].Build Environ,2010,45:537-548.
[7]MA J,SONG W G,FANG Z M,et al.Experimental study on microscopic moving characteristics of pedestrians in built corridor based on digital image processing[J].Building and Environment,2010,45(10):2160-2169.
[8]ZHANG Y C,XIE W,CHEN S M,et al.Experimental study on descent speed on stairs of individuals and small groups under different visibility conditions[J].Fire Technology,2018,54(2):1-16.
[9]XIE W,ZHANG Y C,CHENG YY,et al.Experimental study on movement speed and route choice of individuals and small groups under different visibility conditions[J].Proceida Engineering,2018,211:830-836.
[10]谢玮,张玉春.能见度对个体疏散速度及路径选择的影响研究[J].中国安全生产科学技术,2017,13(7):62-67.
[11]HOOGENDOORN S P,DAAMEN W.Pedestrian behavior at bottlenecks[J].Transportation Science,2005,39(2):147-159.
[12]LIU X,SONG W G,ZHANGJ.Extraction and quantitative analysis of microscopic evacuation characteristics based on digital image processing[J].Physica A,2009,388:2717-2726.
[13]刘轩,宋卫国,马剑,等.基于数字图像处理的人员运动参数提取方法研究[J].火灾科学,2008,(4):201-208.
[14]AFSAR P,CORTEZ P,SANTOS H.Automatic visual detection of human behavior:A review from 2000 to 2014[J].Expert Systems with Applications,2015,42(20):6935-6956.
[15]CONTE D,FOGGIA P,PERCANNELLA G,et al.A method for counting moving people in video surveillance videos[J].EUR-ASIP Journal on advances in signal processing,2010:231-240.
[16]YAMAGUCHI K,BERG A C,ORTIZ L E,et al.Who are you with and where are you going?[J].In Computer Vision and Pattern Recognition(CVPR).IEEE,2011:1345-1352.
[17]MABROUK A B,ZAGROUBA E.Abnormal behavior recognition for intelligent video surveillance systems:a review[J].Expert Systems with Applications,2018,91:480-491.
[18]CHOI W,SAVARESE S.Understanding collective activities of people from videos[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2014,36(6):1242-1257.
[19]ALAHI A,GOEL K,RAMANATHAN V,et al.Social LSTM:Human trajectory prediction in crowded spaces[J].2016 IEEEConference on Computer Vision and Pattern Recognition(CVPR),2016:961-971.
[20]KIM S,GUY S,LIU J,et al.Brvo:Predicting pedestrian trajectories using velocity-space reasoning[J].The International Journal of Robotics Research,2015,34(2):201-217.
[21]KANAGAMALLIGA S,VASUKI S.Contour-based object tracking in video scenes through optical flow and gabor features[J].Optik,2018,157:787-797.
[22]BRAGA N.Object-based image analysis using multiscale connectivity[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27(6):892-907.
[23]SANDEEP S,SUSANTA M.Motion detection using block based bi-directional optical flow method[J].Journal of Visual Communication and Image Representation,2017,49:89-103.
[24]陈娟.基于多特征融合的视频火焰探测方法研究[D].合肥:中国科学技术大学,2009:20-24.
[25]YU K C,WATSON N R,ARRILLAGA J.An adaptive Kalman filter foe dynamic harmonic state estimation and harmonic injection tracking[J].IEEE Transaction on Power Delivery,2005,20(2):1577-1584.
[2]KIRCHNER A,NISHINARI K,SCHADSCHNEIDER A.Friction effects and clogging in a cellular automaton model for pedestrian dynamics[J].Phys Rev E,2003,67(5):56-62.
[3]SONG W G,XU X,WANG BH,et al.Simulation of evacuation processes using a multi-grid model for pedestrian dynamics[J].Physica A,2006,363(2):492-500.
[4]MURAMATSU M,IRIE T,NAGATANI T.Jamming transition in pedestrian counter flow[J].Physica A,1999,267(3):487-498.
[5]KULIGOWSKI E D,PEACOCK R D,RENEKE PA,et al.Movement on stairs during building evacuations[R].NIST technical note,2015.
[6]KOBES M,HELSLOOT I,VRIES B,et al.Way finding during fire evacuation;an analysis of unannounced fire drills in a hotel at night[J].Build Environ,2010,45:537-548.
[7]MA J,SONG W G,FANG Z M,et al.Experimental study on microscopic moving characteristics of pedestrians in built corridor based on digital image processing[J].Building and Environment,2010,45(10):2160-2169.
[8]ZHANG Y C,XIE W,CHEN S M,et al.Experimental study on descent speed on stairs of individuals and small groups under different visibility conditions[J].Fire Technology,2018,54(2):1-16.
[9]XIE W,ZHANG Y C,CHENG YY,et al.Experimental study on movement speed and route choice of individuals and small groups under different visibility conditions[J].Proceida Engineering,2018,211:830-836.
[10]谢玮,张玉春.能见度对个体疏散速度及路径选择的影响研究[J].中国安全生产科学技术,2017,13(7):62-67.
[11]HOOGENDOORN S P,DAAMEN W.Pedestrian behavior at bottlenecks[J].Transportation Science,2005,39(2):147-159.
[12]LIU X,SONG W G,ZHANGJ.Extraction and quantitative analysis of microscopic evacuation characteristics based on digital image processing[J].Physica A,2009,388:2717-2726.
[13]刘轩,宋卫国,马剑,等.基于数字图像处理的人员运动参数提取方法研究[J].火灾科学,2008,(4):201-208.
[14]AFSAR P,CORTEZ P,SANTOS H.Automatic visual detection of human behavior:A review from 2000 to 2014[J].Expert Systems with Applications,2015,42(20):6935-6956.
[15]CONTE D,FOGGIA P,PERCANNELLA G,et al.A method for counting moving people in video surveillance videos[J].EUR-ASIP Journal on advances in signal processing,2010:231-240.
[16]YAMAGUCHI K,BERG A C,ORTIZ L E,et al.Who are you with and where are you going?[J].In Computer Vision and Pattern Recognition(CVPR).IEEE,2011:1345-1352.
[17]MABROUK A B,ZAGROUBA E.Abnormal behavior recognition for intelligent video surveillance systems:a review[J].Expert Systems with Applications,2018,91:480-491.
[18]CHOI W,SAVARESE S.Understanding collective activities of people from videos[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2014,36(6):1242-1257.
[19]ALAHI A,GOEL K,RAMANATHAN V,et al.Social LSTM:Human trajectory prediction in crowded spaces[J].2016 IEEEConference on Computer Vision and Pattern Recognition(CVPR),2016:961-971.
[20]KIM S,GUY S,LIU J,et al.Brvo:Predicting pedestrian trajectories using velocity-space reasoning[J].The International Journal of Robotics Research,2015,34(2):201-217.
[21]KANAGAMALLIGA S,VASUKI S.Contour-based object tracking in video scenes through optical flow and gabor features[J].Optik,2018,157:787-797.
[22]BRAGA N.Object-based image analysis using multiscale connectivity[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27(6):892-907.
[23]SANDEEP S,SUSANTA M.Motion detection using block based bi-directional optical flow method[J].Journal of Visual Communication and Image Representation,2017,49:89-103.
[24]陈娟.基于多特征融合的视频火焰探测方法研究[D].合肥:中国科学技术大学,2009:20-24.
[25]YU K C,WATSON N R,ARRILLAGA J.An adaptive Kalman filter foe dynamic harmonic state estimation and harmonic injection tracking[J].IEEE Transaction on Power Delivery,2005,20(2):1577-1584.