计算机科学 ›› 2017, Vol. 44 ›› Issue (3): 307-312.doi: 10.11896/j.issn.1002-137X.2017.03.062
侯跃恩,李伟光
HOU Yue-en and LI Wei-guang
摘要： 目标跟踪技术在日常生活和生产中有着广泛的应用,但是设计一种具有鲁棒性、准确性和实时性的跟踪算法仍具有很大的难度。为了提高跟踪算法的性能,设计了一种帧间连续结构稀疏表示目标跟踪算法。该算法在粒子滤波框架下进行,采用结构稀疏表示的原理重构候选目标。首先采用目标和背景样本构建稀疏字典, 以提高算法对目标和背景的区分能力。然后,构建含有帧间连续约束项的结构稀疏表示目标方程,该目标方程可以有效利用目标状态的连续性来确定目标状态。进而,根据重构残差设计了一种相似度描述方法,与传统方法相比,该方法对相似目标不敏感。最后,通过6组对比实验证明该算法具有较高的鲁棒性和准确性。
| [1] YILMAZ A,JAVED O,SHAH M.Object tracking:a survey[J].ACM Computing Surveys,2006,38(4). [2] HUANG K Q,CHEN X T,KANG Y F,et al.Intelligent visual surveillance:a review[J].China Journal of Computers,2015,38(6):1093-1118.(in Chinese) 黄凯奇,陈晓棠,康运锋,等.智能视频监控技术综述[J].计算机学报,2015,38(6):1093-1118. [3] WRIGHT J,YANG A Y,ARVIND G,et al.Robust face recognition via sparse representation[J].Pattern Analysis and Machine Intelligence,2008,31(2):210-227. [4] YANG M,FENG X C.Sparse representation or collaborativerepresentation:Which helps face recognition [C]∥IEEE International Conference on Computer Vision.Barcelona,IEEE,2011:471-478. [5] YANG M,ZHANG L,ZHANG D,et al.Relaxed collaborative representation for pattern classification[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI,IEEE,2012:2224-2231. [6] AGARWAL S,ROTH D.Learning a sparse representation for object detection[J].Computer Science,2006,2353:97-101. [7] MEI X,LING H.Robust visual tracking using 1 minimization[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2009:1436-1443. [8] MEI X,LING H,WU Y,et al.Minimum error bounded efficient L1 tracker with occlusion detection[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Kyoto,IEEE,2011:1257-1264. [9] BAO C,WU Y,LING H,et al.Real time robust L1 tracker using accelerated proximal gradient approach[C]∥IEEE Confe-rence on Computer Vision and Pattern Recognition.Providence,RI,IEEE,2012:1830-1837. [10] ZHUANG B H,LU H C,XIAO Z Y,et al.Visual tracking via discriminative sparse similarity map[J].IEEE Transactions on Image Processing,2014,23(4):1872-1881. [11] WANG B X,ZHAO B J,TANG L B,et al.Robust visual trac-king algorithm based on bidirectional sparse representation[J].Acta Phys.Sin.,2014,63(23):234201.(in Chinese) 王保宪,赵保军,唐林波,等.基于双向稀疏表示的鲁棒目标跟踪算法[J].物理学报,2014,63(23):234201. [12] WANG D,LU H,YANG M H.Online object tracking withsparse prototypes[J].IEEE Trans.on Image Process,2013,22(1):314-325. [13] LAN X Y,MA A J,YUAN P C.Multi-Cue visual tracking using robust feature-level fusion based on joint sparse representation[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Columbus,2014:1194-1201. [14] ZHANG X D,CHEN Z H,HU L M,et al.Object trackingmethod based on sparse representation of joint template[J].Control and Decision,2015,30(9):1696-1700.(in Chinese) 张旭东,陈仲海,胡良梅,等.基于联合模板稀疏表示的目标跟踪算法[J].控制与决策,2015,30(9):1696-1700. [15] BAI T,LI Y F.Robust visual tracking with structured sparse representation[J].Pattern Recognition,2012,45(6):2390-2404. [16] JIA X,LU H C,YANG M H.Visual tracking via adaptive structural local sparse appearance model[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI,IEEE,2012:1822-1829. [17] ZHONG W,LU H,Yang M H.Robust object tracking via sparsity-based collaborative model[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI,IEEE,2012:1838-1845. [18] EVERINGHAM M.The Pascal visual object classes (voc) challenge[J].International Journal of Computer Vision,2010,88(2):303-338. [19] BAI T,LI Y F.Robust visual tracking with structured sparse representation[J].Pattern Recognit,2012,45(6):2390-2404. |
| No related articles found! |
|
||
首页