光照变化下基于稀疏表示的视觉跟踪算法研究
|
摘要
为提高光照变化下目标跟踪算法的精度和鲁棒性,基于稀疏表示理论,提出一种光照补偿和多任务稀疏表示联合优化算法。该算法首先根据目标模板与候选目标的平均亮度差异对目标模板光照补偿,而后利用候选目标构建过完备字典以稀疏表示光照补偿后的目标模板,并将所得问题转化为一个多任务优化问题,然后利用所得稀疏编码矩阵快速剔除无关候选目标,最后基于重构误差对剩余候选目标进行局部结构化评估,进而实现目标的精确跟踪。实验结果表明,与现有主流算法相比,剧烈光照变化情况下,所提方法可显著改善目标跟踪精度及鲁棒性。
To improve the accuracy and robustness of the target tracking algorithm under illumination changes,a joint optimization algorithm combining illumination compensation with multi-task sparse representation is proposed based on the sparse representation theory. First, the algorithm compensates for the illumination of the template according to the average brightness difference between the template and the candidate target.Then, the candidate target is used to construct an over-complete dictionary to represent the template after illumination compensation, and the problem is transformed into a multi-task optimization problem. Moreover, the sparse coding matrix is used to quickly eliminate unrelated candidates. Finally, based on the reconfiguration error, a local structured assessment is carried out on the remaining candidates,so as to realize accurate target tracking. Simulation results show that the proposed algorithm can significantly improve the accuracy and robustness of target tracking under severe illumination changes compared with the existing state-of-theart algorithms.
To improve the accuracy and robustness of the target tracking algorithm under illumination changes,a joint optimization algorithm combining illumination compensation with multi-task sparse representation is proposed based on the sparse representation theory. First, the algorithm compensates for the illumination of the template according to the average brightness difference between the template and the candidate target.Then, the candidate target is used to construct an over-complete dictionary to represent the template after illumination compensation, and the problem is transformed into a multi-task optimization problem. Moreover, the sparse coding matrix is used to quickly eliminate unrelated candidates. Finally, based on the reconfiguration error, a local structured assessment is carried out on the remaining candidates,so as to realize accurate target tracking. Simulation results show that the proposed algorithm can significantly improve the accuracy and robustness of target tracking under severe illumination changes compared with the existing state-of-theart algorithms.
引文
[1]FRADI H,LUVISON B,PHAM Q C.Crowd behavior analysis using local mid-level visual descriptors[J].IEEE Transactions on Circuits and Systems for Video Technology,2017,27(3):589-602.
[2]YU G,LI C,SHANG Z.Video monitoring method,video monitoring system and computer program product[P].United States Patent 9792505,2017-10-17.
[3]UENG S K,CHEN G Z.Vision based multi-user human computer interaction[J].Multimedia Tools and Applications,2016,75(16):10059-10076.
[4]WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[5]PAN Z,LIU S,FU W N.A review of visual moving target tracking[J].Multimedia Tools and Applications,2017,76(16):16989-17018.
[6]JENKINS M D,BARRIE P,BUGGY T,et al.Selective sampling importance resampling particle filter tracking with multibag subspace restoration[J].IEEE Transactions on Cybernetics,2018,48(1):264-276.
[7]WANG Y R,TANG X L,CUI Q.Dynamic appearance model for particle filter based visual tracking[J].Pattern Recognition,2012,45(12):4510-4523.
[8]NHAT V Q,LEE G.Illumination invariant object tracking with adaptive sparse representation[J].International Journal of Control,Automation and Systems,2014,12(1):195-201.
[9]DELAIL B A,BHASKAR H,ZEMERLY J,et al.Robust likelihood model for illumination invariance in particle filtering[J].IEEE Transactions on Circuits and Systems for Video Technology,2017.doi:10.1109/TCSVT.2017.2725322.
[10]BAO C L,WU Y,LING H B,et al.Real time robust L1tracker using accelerated proximal gradient approach[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2012:1830-1837.
[11]MA B,SHEN J B,LIU Y B,et al.Visual tracking using strong classifier and structural local sparse descriptors[J].IEEE Transactions on Multimedia,2015,17(10):1818-1828.
[12]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.
[13]ZHANG T Z,GHANEM B,LIU S,et al.Robust visual tracking via multi-task sparse learning[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2012:2042-2049.
[14]ROSS D A,LIM J,LIN R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2008,77(1):125-141.
[15]POLSON N,SOKOLOV V.Bayesian particle tracking of traffic flows[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(2):345-356.
[16]HE Z Y,YI S Y,CHEUNG Y M,et al.Robust object tracking via key patch sparse representation[J].IEEE Transactions on Cybernetics,2017,47(2):354-364.
[17]ZHANG K H,ZHANG L,YANG M H.Real-time compressive tracking[C]//European Conference on Computer Vision,2012:864-877.
[18]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision,2012:702-715.
[19]HARE S,SAFFARI A,TORR P H.Struck:structured output tracking with kernels[C]//Proceedings of IEEE International Conference on Computer Vision,2011:263-270.
[2]YU G,LI C,SHANG Z.Video monitoring method,video monitoring system and computer program product[P].United States Patent 9792505,2017-10-17.
[3]UENG S K,CHEN G Z.Vision based multi-user human computer interaction[J].Multimedia Tools and Applications,2016,75(16):10059-10076.
[4]WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[5]PAN Z,LIU S,FU W N.A review of visual moving target tracking[J].Multimedia Tools and Applications,2017,76(16):16989-17018.
[6]JENKINS M D,BARRIE P,BUGGY T,et al.Selective sampling importance resampling particle filter tracking with multibag subspace restoration[J].IEEE Transactions on Cybernetics,2018,48(1):264-276.
[7]WANG Y R,TANG X L,CUI Q.Dynamic appearance model for particle filter based visual tracking[J].Pattern Recognition,2012,45(12):4510-4523.
[8]NHAT V Q,LEE G.Illumination invariant object tracking with adaptive sparse representation[J].International Journal of Control,Automation and Systems,2014,12(1):195-201.
[9]DELAIL B A,BHASKAR H,ZEMERLY J,et al.Robust likelihood model for illumination invariance in particle filtering[J].IEEE Transactions on Circuits and Systems for Video Technology,2017.doi:10.1109/TCSVT.2017.2725322.
[10]BAO C L,WU Y,LING H B,et al.Real time robust L1tracker using accelerated proximal gradient approach[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2012:1830-1837.
[11]MA B,SHEN J B,LIU Y B,et al.Visual tracking using strong classifier and structural local sparse descriptors[J].IEEE Transactions on Multimedia,2015,17(10):1818-1828.
[12]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.
[13]ZHANG T Z,GHANEM B,LIU S,et al.Robust visual tracking via multi-task sparse learning[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2012:2042-2049.
[14]ROSS D A,LIM J,LIN R S,et al.Incremental learning for robust visual tracking[J].International Journal of Computer Vision,2008,77(1):125-141.
[15]POLSON N,SOKOLOV V.Bayesian particle tracking of traffic flows[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(2):345-356.
[16]HE Z Y,YI S Y,CHEUNG Y M,et al.Robust object tracking via key patch sparse representation[J].IEEE Transactions on Cybernetics,2017,47(2):354-364.
[17]ZHANG K H,ZHANG L,YANG M H.Real-time compressive tracking[C]//European Conference on Computer Vision,2012:864-877.
[18]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision,2012:702-715.
[19]HARE S,SAFFARI A,TORR P H.Struck:structured output tracking with kernels[C]//Proceedings of IEEE International Conference on Computer Vision,2011:263-270.