《计算机应用研究》|Application Research of Computers

样本分块稀疏表示判决式目标跟踪

Sample blocking sparse representation discriminative target tracker

免费全文下载 (已被下载 次)  
获取PDF全文
作者 侯跃恩,李伟光
机构 1.嘉应学院 计算机学院,广东 梅州 514000;2.华南理工大学 机械工程学院,广州 510640
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)08-2510-04
DOI 10.3969/j.issn.1001-3695.2018.08.068
摘要 为了提高目标跟踪算法的鲁棒性和准确性,提出了一种粒子滤波框架下的样本分块稀疏表示判决式跟踪算法。算法在首帧提取目标模板和背景模板,并将这些模板进行分块,构建模板字典。然后将候选目标进行分块处理,并使用模板字典稀疏重构候选目标分块,从而获得候选目标的稀疏系数和残差,进而构建一款贝叶斯分类器。分类器的输入为候选目标稀疏系数和残差中提取的相似度信息,输出为候选目标与真实目标的相似度。分类器通过跟踪过程中获得的正负样本进行训练,使之能够适应目标和背景的变化。最后,将所提算法在八组具有挑战性的视频中进行测试,平均跟踪误差为5.9个像素,跟踪成功率为89%。与选取的三种先进的算法比较,所提算法具有更高的鲁棒性和准确性。
关键词 粒子滤波;样本分块;稀疏表示;分类器
基金项目 国家“863”计划资助项目(2015AA043005)
国家高等教育教学改革重点项目(JYJG20170109)
本文URL http://www.arocmag.com/article/01-2018-08-068.html
英文标题 Sample blocking sparse representation discriminative target tracker
作者英文名 Hou Yue’en, Li Weiguang
机构英文名 1.SchoolofComputer,JiayingUniversity,MeizhouGuangdong514000,China;2.CollegeofMechanicalEngineering,SouthChinaUniversityofTechnology,Guangzhou510640,China
英文摘要 For improving the robustness and accuracy of tacking algorithm, this paper proposed a sample blocking sparse representation discriminative tracking algorithm, which was under the particle filter framework. Firstly, the algorithm sampled target and background templates in the first frame, and divided each template into several patches, and built a template dictionary. Secondly, each candidate target was divided into several patches. It sparsely rebuilt each patch by the template dictionary, and obtained the coefficients and residual errors of candidate targets. Thirdly, it constructed a Bayes classifier. The classifier’s input was similar information extracted from coefficients and residual errors while the output was the likelihood between the candidate target and the real target. For adapting the changes of the target and the background, it trained the classifier by positive and negative samples, which were obtained during the tracking process. It tested the proposed tracker in 8 challenging video sequences. The average tracking error is 8.9 pixels, and the average success rate is 89%. Compared with 3 state-of-the-art trackers, the proposed tracker is more robust and accurate.
英文关键词 particle filter; sample blocking; sparse representation; classifier
参考文献 查看稿件参考文献
  [1] 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.
[2] Mei Xue, Ling Haibin. Robust visual tracking and vehicle classification via sparse representation[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 2011, 33(11):2259-2272.
[3] 侯跃恩, 李伟光, 容爱琼, 等. 融合背景信息的分块稀疏表示跟踪算法[J] . 华南理工大学学报:自然科学版, 2013, 41(8):21-27.
[4] Bao Chenglong, Wu Yi, Ling Haibin, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2012:1830-1837.
[5] Zhuang Bohan, Lu Huchuan, Xiao Ziyang, et al. Visual tracking via discriminative sparse similarity map[J] . IEEE Trans on Image Processing, 2014, 23(4):1872-1881.
[6] Wang Dong, Lu Huchuan, Yang Minghsuan. Least soft-threshold squares tracking[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2013:2371-2378.
[7] 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.
[8] Lan Xiangyuan, Ma A J, Yuan Pongchi. Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2014:1194-1201.
[9] Bai Tianxiang, Li Y F. Robust visual tracking with structured sparse representation[J] . Pattern Recognition, 2012, 45(6):2390-2404.
[10] Xu Jia, Lu Huchuan, Yang Minghsuan. Visual tracking via adaptive structural local sparse appearance model[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2012:1822-1829.
[11] 程帅, 孙俊喜, 曹永刚, 等. 增量深度学习目标跟踪[J] . 光学精密工程, 2015, 23(4):1161-1170.
[12] 陈东成, 朱明, 高文, 等. 在线加权多示例学习实时目标跟踪[J] . 光学精密工程, 2014, 22(6):1661-1667.
[13] Zhang Kaihua, Zhang Lei, Yang Minghsuan. Real time compressive tracking[C] //Proc of European Conference on Computer Vision. Berlin:Springer, 2012:864-877.
[14] 孙晓燕, 常发亮. 梯度特征稀疏表示目标跟踪[J] . 光学精密工程, 2013, 21(12):3191-3196.
[15] Zhang Lei, Yang Meng, Feng Xiangchu. Sparse representation or collaborative representation:which helps face recognition[C] //Proc of IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2011:471-478.
[16] Diaconis P, Freedman D. Asymptotics of graphical projection pursuit[J] . The Annals of Statistics, 1984, 12(3):793-815.
[17] Zhong Wei, Lu Huchuan, Yang Minghsuan. Robust object tracking via sparsity-based collaborative model[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2012:1838-1845.
[18] Everingham M, Gool L V, CKI Williams C K I, et al. The pascal visual object classes (VOC) challenge[J] . International Journal of Computer Vision, 2010, 88(2):303-338.
收稿日期 2017/3/29
修回日期 2017/5/17
页码 2510-2513,2531
中图分类号 TP391
文献标志码 A