摘要
为了提高多视频下目标车辆跟踪的准确率,提出了一种基于Mean Shift结合视觉词袋的车辆跟踪方法。该方法采用Mean Shift提供的轮廓和颜色信息进行初匹配,并进行跟踪;针对车辆在不同视频下车辆视角、环境不同的情况,提出了尺度不变的识别方法,即利用视觉词袋特征作为车辆特征进行再次匹配。该方法能够利用高速路网中摄像机拍摄的视频确定目标车辆的具体位置。实验表明,基于Mean Shift的多视频车辆跟踪方法能够有效提高车辆跟踪的准确率。
In order to improve the accuracy of target tracking in multi video,a vehicle tracking method based on Mean Shift combined with visual words was proposed.The method uses Mean Shift to provide the contour and the color information to carry on the initial match and the track.A scale invariant identification method was proposed for the situation of vehicle viewing angle and environment in different video,which regards the visual word bag feature as the vehicle features for match again.The method can be used to determine the specific location of the target vehicle by using the video camera in the high-speed network.Experimental results show that the Shift Mean based multi video vehicle tracking method can improve the accuracy of vehicle tracking.
引文
[1]FLEISCHER K,NAGEL H H.Machin-vesion-based detection and tracking of stationary infrastructural objects beside innercity roads[J].IEEE Proceedings Intelligent Transortation Systems,2001,1(1):525-530.
[2]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,25(3):225-237.
[3]COIFMAN B,BEYMER D,MC LAUCHLAN P,et al.A realtime computer vision system for vehicle tracking and traffic surveillance[J].Transportation research.Part C,Emerging technologies,1998,6(4):271-288.
[4]NAGEL H H.Tracking of complex driving manoeuvres in traffic image sequences[J].Image and Vision Computing,1998,16(8):517-527.
[5]WANG Y Z,LIANG Y,ZHAO C H,et al.Kernel-based tracking based on adaptive fusion of multiple cues[J].Acta Automatica Sinica,2008,34(4):393-399.
[6]GU X,WANG H T,WANG L F,et al.Fusing multiple features for object tracking based on uncertainty measurement[J].Acta Automatica Sinica,2011,5(37):550-558.
[7]TAI J,TSENG S,LIN C,et al.Real-time image tracking for automatic traffic monitoring and enforcement applications[J].Image and Vision Computing,2004,22(6):485-501.
[8]PAI C J,TYAN H R,LIANG Y M,et al.Pedestrian detection and tracking at crossroads[J].Pattern Recognition,2003,37(5):1025-1034.
[9]FUKUNAGA K,HOSTETLER L.The estimation of the gradient of a density function,with applications in pattern recognition[J].Information Theory,21(1):111-123.
[10]HE X H,ZHAO L.Moving object real-time detection and tracking based on improved Gaussian mixture model[J].Jisuanji Yingyong Yanjiu,2010,27(12):4768-4771.
[11]陈伟宏,肖德贵.一种费重叠多摄像头的实时监控系统[J].计算机工程与应用,2006,42(18):218-220.
[12]磨少清,刘正光.多车道路面的大车车型分类特征及提取方法[J].计算机应用,2009,29(2):586-589.
[13]叶永伟,任设东,陆俊杰,等.基于SVM的汽车涂装线设备故障诊断[J].浙江工业大学学报,2015,43(6):670-675.
[14]SONOYAMA S,TAMAKI T,Hirakawat,et al.Trade-off between speed and performance for colorectal endoscopic NBI image classification[J].Medical Imaging,2015,12(3):15-18.
[15]FISHLER M A,BOLLES R C.Random sample consensus:A paradigm for model fitting with applications to image analysis and auto mated cartography[J].Comm.of the ACM,1981,24(6):726-740.
[16]WANG J,INDRA-PAYOONG N,SUMALEE A,et al.Vehicle Reidentification With Self-Adaptive Time Windows for RealTime Travel Time Estimation[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(2):540-552.