计算机科学 ›› 2017, Vol. 44 ›› Issue (8): 22-26.doi: 10.11896/j.issn.1002-137X.2017.08.004
周华争,马小虎
ZHOU Hua-zheng and MA Xiao-hu
摘要: 在严重遮挡时,时空上下文STC(Spatio-Temporal Context)算法对目标位置的判断是正确的,而均值漂移MS(Mean Shift)算法对目标位置的判断会发生很大幅度的抖动,甚至跟踪错误目标。在遮挡结束后,时空上下文算法很难重新跟踪到正确目标,而均值漂移算法可以重新检测到跟踪目标。结合二者的优缺点,提出基于均值漂移算法和时空上下文算法的目标跟踪算法MSandSTC。该算法主要解决目标被严重遮挡的问题。在许多具有挑战性的数据集上的实验表明所提算法具有较好的实时性和鲁棒性。
[1] YILMAZ A,JAVED O,SHAH M.Object tracking:A survey[J].ACM Computing Surveys,2006,38(4):1-45. [2] WU Y,LIM J,YANG M H.Online object tracking:A benchmark[C]∥Proc of IEEE Conference on Computer Vision and Pattern Recognition.2013:2411-2418. [3] KALAZ Z,MIKOLAJCZYK K,MATAS J.Tracking-learning-detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1409-1422. [4] KWON J,LEE K M.Visual tracking decomposition[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.2010:1269-1276. [5] LI H,SHEN C,SHI Q.Real-time visual tracking using com-pressive sensing[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.2011:1305-1312. [6] SEVILLA-LARA L,LEARNED-MILLER E.Distribution fields for tracking[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.2012:1910-1917. [7] GRABNER H,LEISTNER C,BISCHOF H.Semi-supervised on-line boosting for robust tracking[C]∥European Conference on Computer Vision.2008:234-247. [8] ZHANG K,ZHANG L,YANG M H.Fast Compressive Trac-king[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(10):2002-2015. [9] BABENKO B,YANG M H,BELONGIE S.Robust object trac-king with online multiple instance learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632. [10] COMANICIU D,RAMESH V,MEER P.Kernel-based objecttracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577. [11] ZHANG K,ZHANG L,LIU Q,et al.Fast visual tracking viadense spatio-temporal context learning[C]∥European Confe-rence on Computer Vision.2014:127-141. [12] WEN L,CAI Z,LEI Z,et al.online spatio-temporal structure context learning for visual tracking[C]∥European Conference on Computer Vision.2012:716-729. [13] LUO H L,SHAN S Y,KONG F S.Mean Shift Tracking Based on Ensemble Multiple Instance Learning[J].Journal of Compu-ter-Aided Design and Computer Graphics,2015,27(2):226-237.(in Chinese) 罗会兰,单顺勇,孔繁胜.基于集成多示例学习的Mean Shift 跟踪算法[J].计算机辅助设计与图形学学报,2015,27(2):226-237. [14] MA L,CHANG F L,QIAO Y Z.Target Tracking Based onMean Shift Algorithm and Particle Filtering Algorithm[J].Pattern Recognition and Artificial Intelligence,2006,19(6):787-793.(in Chinese) 马丽,常发亮,乔谊正.基于均值漂移算法和粒子滤波算法的目标跟踪[J].模式识别与人工智能,2006,19(6):787-793. [15] LIU Q,HOU J H,MOU H J,et al.Object detection and trac-king combining generative and discriminative model[J].Journal of Image and Graphics,2013,18(10):1293-1301.(in Chinese) 刘倩,侯建华,牟海军,等.联合生成与判别模型的目标检测与跟踪[J].中国图象图形学报,2013,18(10):1293-1301. [16] MA B,SHEN J,LIU Y,et al.Visual tracking using strong classifier and structural local sparse descriptors[J].IEEE Trans.on Multimedia,2015,17(10):1818-1828. [17] MA B,HU H,SHEN J,et al.Linearization to Nonlinear Lear-ning for Visual Tracking[C]∥IEEE ICCV.2015:4400-4407. |
No related articles found! |
|