基于超像素与BoF的运动目标跟踪算法Motion target tracking algorithm based on superpixel and BoF
邱晓荣,彭力,刘全胜
摘要(Abstract)：
针对由遮挡、光照、形变等干扰产生的漂移问题,提出基于超像素和BoF的运动目标跟踪算法。此算法首先利用SLIC方法对运动目标的观测区域进行超像素分割,然后基于超像素构造中层视觉线索的超像素字典以及低层像素特征的BoF字典,实现对运动目标表观模型的混合建模,最后引入粒子滤波框架和在线字典更新,以适应目标和背景的变化。实验结果表明,该算法能够很好地应对严重遮挡、非刚性变换、复杂背景等干扰因素的影响,具有很好的稳定性和鲁棒性。
关键词(KeyWords)： 目标跟踪;表观模型;中层视觉线索;超像素;BoF;粒子滤波框架
基金项目(Foundation): 国家自然科学基金项目资助(61374047);; 江苏高校品牌专业建设工程资助项目(PPZY2015C240)~~
作者(Author): 邱晓荣,彭力,刘全胜
DOI: 10.16652/j.issn.1004-373x.2018.06.009
参考文献(References)：
- [1]WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1834-1848.
- [2]KWON J,LEE K M.Visual tracking decomposition[C]//Proceedings of IEEE Computer Society Conference on Computer Vision&Pattern Recognition.San Francisco:IEEE Computer Society,2010:1269-1276.
- [3]MEI X,LING H.Robust visual tracking and vehicle classification via sparse representation[J].IEEE transactions on pattern analysis and machine intelligence,2011,33(11):2259-2272.
- [4]BAO C,WU Y,LING H,et al.Real time robust L1 tracker using accelerated proximal gradient approach[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Providence:IEEE,2012:1830-1837.
- [5]CHENG X,LI N,ZHANG S,et al.Robust visual tracking with SIFT features and fragments based on particle swarm optimization[J].Circuits systems&signal processing,2014,33(5):1507-1526.
- [6]BABENKO B,YANG M H,BELONGIE S.Visual tracking with online multiple instance learning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Miami:IEEE,2009:983-990.
- [7]KALAL Z,MIKOLAJCZYK K,MATAS J.Tracking-learningdetection[J].IEEE transactions on pattern analysis and machine intelligence,2012,34(7):1409-1422.
- [8]YANG F,LU H,ZHANG W,et al.Visual tracking via bag of features[J].IET image processing,2012,6(2):115-128.
- [9]YANG M H,LU H,ZHONG W.Robust object tracking via sparsity-based collaborative model[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition.Providence:IEEE,2012:1838-1845.
- [10]YANG F,LU H,YANG M H.Robust superpixel tracking[J].IEEE transactions on image processing,2014,23(4):1639-1651.