计算机科学 ›› 2014, Vol. 41 ›› Issue (9): 306-310.doi: 10.11896/j.issn.1002-137X.2014.09.059
杨国亮,张进辉
YANG Guo-liang and ZHANG Jin-hui
摘要: 检测跟踪(Tracking by detection)是近年来多目标跟踪领域的一个主要研究方向。遵循检测跟踪框架,提出一种基于分层关联的全局性的数据关联算法。首先利用目标检测器在整个视频上检测目标,得到检测响应;然后利用广义最小团图在视频片段中对检测响应进行数据关联,得到轨迹片段;最后再在整个视频中对轨迹片段进行分层关联,得到最终的轨迹。在公共数据集上的测试结果表明,该算法能够有效地对多个目标进行数据关联,具有较强的处理遮挡能力。
[1] Hao J,Fels S,Little J J.A Linear Programming Approach for Multiple Object Tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2007(CVPR’ 07). Minneapolis,MN,2007:1-8 [2] Li Z,Yuan L,Nevatia R.Global data association for multi-object tracking using network flows[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2008(CVPR 2008).Anchorage,AK,2008:1-8 [3] Pirsiavash H,Ramanan D,Fowlkes C C.Globally-optimal greedyalgorithms for tracking a variable number of objects[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI,2011:1201-1208 [4] Berclaz J,Fleuret F,Turetken E,et al.Multiple Object TrackingUsing K-Shortest Paths Optimization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(9):1806-1819 [5] Ben Shitrit H,Berclaz J,Fleuret F,et al.Tracking multiple people under global appearance constraints[C]∥2011 IEEE International Conference on Computer Vision (ICCV).Barcelona,2011:137-144 [6] Butt A A,Collins R T.Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow[C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Portland,OR,USA,2013:1846-1853 [7] Forsyth D,Torr P,Zisserman A,et al.Robust Object Tracking by Hier-archical Association of Detection Responses[M]∥Forsyth D,Torr P,Zisserman A.Computer Vision-ECCV 2008.Springer Berlin Heidelberg,2008:788-801 [8] Yuan L,Chang H,Nevatia R.Learning to associate:Hybrid-Boosted multi-target tracker for crowded scene[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).Miami,FL,2009:2953-2960 [9] Bo Y,Chang H,Nevatia R.Learning affinities and dependencies for multi-target tracking using a CRF model[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI,2011:1233-1240 [10] Brendel W,Amer M,Todorovic S.Multiobject tracking as maxi-mum weight independent set[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI,2011:1273-1280 [11] Andriyenko A,Schindler K.Multi-target tracking by continuous energy minimization[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI,2011:1265-1272 [12] Andriyenko A,Roth S,Schindler K.An analytical formulation of global occlusion reasoning for multi-target tracking[C]∥2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).Barcelona,2011:1839-1846 [13] Roshan Zamir A,Dehghan A,Shah M.GMCP-Tracker:GlobalMulti-object Tracking Using Generalized Minimum Clique Graphs[C]∥Computer Vision-ECCV.2012:343-356 [14] Suard F,Rakotomamonjy A,Bensrhair A,et al.Pedestrian Detection Using Infrared images and Histograms of Oriented Gradients[C]∥Intelligent Vehicles Symposium,2006.Tokyo:IEEE,2006:206-212 [15] Feremans C,Labbe M,Laporte G.Generalized network design problems[J].European Journal of Operational Research,2003,148(1):1-13 [16] Benfold B,Reid I.Stable multi-target tracking in real-time surveillance video[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI,2011:3457-3464 [17] Kasturi R,Goldgof D,Soundararajan P,et al.Framework forPerformance Evaluation of Face,Text,and Vehicle Detection and Tracking in Video:Data,Metrics,and Protocol[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):319-336 |
No related articles found! |
|