计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 220-226.
朱浩楠,许明敏,沈瑛
ZHU Hao-nan, XU Ming-min,SHEN Ying
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。
中图分类号:
[1]FLEISCHER K,NAGEL H H.Machin-vesion-based detection and tracking of stationary infrastructural objects beside inner-city 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 real-time computer vision system for vehicle tracking and traffic surveillance[J].Transportation research.Part C,Emerging techno-logies,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 trac- king based on adaptive fusion of multiple cues[J].Acta Automa-tica 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 gra- dient 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 trac- king 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 Real-Time Travel Time Estimation[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(2):540-552. |
[1] | 萧蕴诗,赵彦青,程成. 基于单位超球面上Mean Shift聚类的地震子波盲估计 Blind Estimation of Seismic Wavelet on Unit Hypersphere with Mean Shift 计算机科学, 2017, 44(5): 33-36. https://doi.org/10.11896/j.issn.1002-137X.2017.05.006 |
[2] | 邹青志,黄山. 基于改进型LTP的均值漂移目标跟踪算法 Mean Shift Tracking Algorithm Based on Improved LTP Feature Extraction 计算机科学, 2017, 44(4): 306-311. https://doi.org/10.11896/j.issn.1002-137X.2017.04.062 |
[3] | 邹青志,黄山. 一种基于Mean Shift的快速跟踪算法 Fast Tracking Algorithm Based on Mean Shift Algorithm 计算机科学, 2017, 44(3): 278-282. https://doi.org/10.11896/j.issn.1002-137X.2017.03.057 |
[4] | 任帅,赵祥模,张弢,石方夏,慕德俊. 基于局部高度与Mean Shift的三维模型信息隐藏算法 Information Hiding Scheme for 3D Models Based on Local Height and Mean Shift Clustering Analysis 计算机科学, 2017, 44(3): 187-191. https://doi.org/10.11896/j.issn.1002-137X.2017.03.040 |
[5] | 周扬,孙瑾,牛犇. 一种基于改进Mean Shift滤波的Retinex彩色图像增强算法 Retinex-based Color Image Enhancement Algorithm by Improved Mean Shift Filtering 计算机科学, 2014, 41(Z6): 160-163. |
[6] | 朱二喜,徐敏. 一种新型智能交通违章信息采集器的研究与设计 New Research and Design of Intelligent Information Collector of Traffic Violation 计算机科学, 2014, 41(Z11): 478-481. |
[7] | 周君. 基于时空马尔可夫随机场交通参数采集系统研究 Research on Traffic Parameter Acquisition System Based on ST-MRF Model 计算机科学, 2013, 40(10): 292-295. |
[8] | 张文娟,冯象初. 基于区域的图切割算法求解Mumford-Shah图像分割模型 Region-based Graph Cut Algorithm for Mumford-Shah Image Segmentation Model 计算机科学, 2012, 39(2): 297-301. |
|