基于ML和L2范数的视频目标跟踪算法

姜明新, 王洪玉, 王洁, 王彪

电子学报 ›› 2013, Vol. 41 ›› Issue (11) : 2307-2313.

PDF(11960 KB)
PDF(11960 KB)
电子学报 ›› 2013, Vol. 41 ›› Issue (11) : 2307-2313. DOI: 10.3969/j.issn.0372-2112.2013.11.031
科研通信

基于ML和L2范数的视频目标跟踪算法

  • 姜明新1,2, 王洪玉1, 王洁1, 王彪1
作者信息 +

Visual Object Tracking Algorithm Based on ML and L2-Norm

  • JIANG Ming-xin1,2, WANG Hong-yu1, WANG Jie1, WANG Biao1
Author information +
文章历史 +

摘要

目标跟踪是计算机视觉领域的一个具有挑战性的问题,本文提出了一种基于ML(最大似然)估计和L2范数的视频目标跟踪算法.建立基于稀疏限制的ML模型,给样本中的异常像素分配较小的权值,减少异常像素对跟踪算法的影响.利用L2范数最小化进行稀疏编码求解.采用贝叶斯估计得出目标跟踪结果.与其他典型算法相比,本算法降低了计算的复杂度,对遮挡,旋转,尺度变化,光照变化等异常变化具有较强的鲁棒性.

Abstract

The tracking of target is a challenging issue in computer vision.In this paper,we propose a visual object tracking algorithm based on ML estimation and L2-norm.Firstly,the model of sparsity constrained ML is established.Abnormal pixels in the samples will be assigned with low weights to reduce their affects on the tracking algorithm.Then,L2-norm minimization is used to solve the sparse coding.Finally,the object tracking results is obtained using Bayesian MAP estimation.Compared with other popular methods,our proposed method reduces the computational complexity and has stronger robustness to abnormal changes(e.g.occlusion,rotation,scale change,illumination,etc.)

关键词

稀疏限制 / 最大似然 / L2范数最小化 / 贝叶斯MAP估计

Key words

sparsity constraint / maximum likelihood (ML) / L2-norm minimization / Bayesian MAP(maximum a posteriori probability) estimation

引用本文

导出引用
姜明新, 王洪玉, 王洁, 王彪. 基于ML和L2范数的视频目标跟踪算法[J]. 电子学报, 2013, 41(11): 2307-2313. https://doi.org/10.3969/j.issn.0372-2112.2013.11.031
JIANG Ming-xin, WANG Hong-yu, WANG Jie, WANG Biao. Visual Object Tracking Algorithm Based on ML and L2-Norm[J]. Acta Electronica Sinica, 2013, 41(11): 2307-2313. https://doi.org/10.3969/j.issn.0372-2112.2013.11.031
中图分类号: TP391.41   

参考文献

[1] 刘晨光,程丹松,刘家锋,黄剑华,唐降龙.一种基于交互式粒子滤波器的视频中多目标跟踪算法[J].电子学报,2011,39(2):260-267. Liu Chenguang,Cheng Dansong,et al.Interactive particle filter based algorithm for tracking multiple objects in videos[J].Acta Electronica Sinica,2011,39(2):260-267.(in Chinese)
[2] Kristan M,Kovacic S,Leonardis A,Pers J.A two-stage dynamic,odel for visual tracking[J].IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2010,40(6):1505-1520.
[3] 冯巍,胡波,杨成,林青,杨涛.基于贝叶斯理论的分布式多视角目标跟踪算法[J].电子学报,2011,39(2):316-321. Feng Wei,Hu Bo,Yang Cheng,Lin Qing,Yang Tao.A distributed multi-view object tracking algorithm under the bayesian framework[J].Acta Electronica Sinica,2011,39(2):316-321.(in Chinese)
[4] Wright J,Yang A Y,Ganesh A,Sastry S S,Ma Y.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(1):210-227.
[5] Wagner A,Wright J,Ganesh A,Zhou Z H,Mobahi H.Toward a practical face recognition system:robust alignment and illumination by sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):372-386.
[6] Meng Y,Zhang L,Yang J,Zhang D.Robust sparse coding for face recognition[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Colorado Springs,USA:2011.625-632.
[7] Zhang L,Meng Y,Feng X C.Sparse representation or collaborative representation:which helps face recognition[A].IEEE International Conference on Computer Vision[C].Barcelona,Spain,2011.471-478.
[8] 亓晓振,王庆.一种基于稀疏编码的多核学习图像分类方法[J].电子学报,2012,40(4):773-779. Qi Xiaozhen,Wang Qing.An image classification approach based on sparse coding and multiple kernel learning[J].Acta Electronica Sinica,2012,40(4):773-779.( in Chinese)
[9] Dong W S,Li X,Zhang L,Shi G M.Sparsity-based image denoising via dictionary learning and structural clustering.IEEE Conference on Computer Vision and Pattern Recognition.Colorado Springs,USA,2011.457-464.
[10] Mei X,Ling H B.Robust visual tracking and vehicle classification via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(11):2259-2272.
[11] Han Z J,Jiao J B,Zhang B C,Ye Q X,Liu J Z.Visual object tracking via sample-based adaptive sparse representation[J].Pattern Recognition,2011,44(9):2170-2183.
[12] Donoho D.For most large underdetermined systems of linear equations the minimal L1-norm solution is also the sparsest solution[J].Communications on Pure and Applied Mathematics,2006,59(6):797-829.
[13] Ross D,Lim J,Lin R S,Yang M H.Incremental learning for robust visual tracking.International Journal of Computer Vision,2008,77(1-3):125-141.
[14] Kalal Z,Matas J,Mikolajczyk K.P-n learning:bootstrapping binary classifiers by structural constraints[A].IEEE Conference on Computer Vision and Pattern Recognition[C]San Francisco,USA,2010.49-56.
[15] Kwon J,Lee K M.Visual tracking decomposition[A].IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA,2010.1269-1276.
[16] Babenko B,Yang M H,Belongie S,Visual tracking with online multiple instance learning[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Miami Beach,USA,2009.983-990.
[17] Adam A,Rivlin E,Shimshoni I.Robust fragments based tracking using the integral histogram[A].IEEE Conference on Computer Vision and Pattern Recognition[C].New York,USA,2006.798-805.

基金

国家自然科学基金 (No.61172058); 中央高校自主基金 (No.DC10010103); 辽宁省教育厅资助项目 (No.L2012476)
PDF(11960 KB)

2105

Accesses

0

Citation

Detail

段落导航
相关文章

/