基于編碼遷移的快速魯棒視覺跟蹤

薛模根; 劉文琢; 袁廣林; 秦曉燕

doi:10.11999/JEIT160966

基于編碼遷移的快速魯棒視覺跟蹤

doi: 10.11999/JEIT160966

1.
(陸軍軍官學院偏振光成像探測技術安徽省重點實驗室合肥 230031) ②(陸軍軍官學院十一系合肥 230031)

基金項目:

國家自然科學基金(61175035, 61379105)

計量
- 文章訪問數(shù): 1228
- HTML全文瀏覽量: 125
- PDF下載量: 373
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-09-26
- 修回日期: 2017-02-08
- 刊出日期: 2017-07-19

Fast Robust Visual Tracking Based on Coding Transfer

1.
(Anhui Province Key Laboratory of Polarization Imaging Detection Technology, Army Officer Academy of PLA, Hefei 230031, China)
2.
(Eleventh Department, Army Officer Academy of PLA, Hefei 230031, China)

Funds:

The National Natural Science Foundation of China (61175035, 61379105)

摘要

摘要: L1跟蹤表示模型的稀疏性約束，使其對局部遮擋具有良好的魯棒性，但同時也造成了跟蹤速度慢的問題。針對此問題，該文提出使用編碼遷移方法進行視覺跟蹤。該方法利用低分辨率字典計算候選目標表示系數(shù)，并使用高分辨率字典構造觀測似然，有效地減小了跟蹤過程中的計算量。為了提高編碼遷移的精度和字典適應背景干擾的能力，提出一種在線魯棒判別式聯(lián)合字典學習模型用于字典更新。實驗結(jié)果表明所提方法具有良好的魯棒性和較快的跟蹤速度。
- L1跟蹤 /
- 編碼遷移 /
- 字典學習 /
- 粒子濾波
Abstract: The sparsity constraint of the L1 trackers representation model makes it have good robustness towards partial occlusion. However, the tracking speed of the L1 tracker is slow. To solve this study, this paper proposes a coding transfer method for visual tracking. By making use of the low-resolution dictionary to calculate coefficients of the candidate targets and the high-resolution dictionary to construct the observation likelihood model, the method reduces calculation amount effectively in the process of tracking. In order to improve the precision of coding transfer and the ability of the dictionary to overcome the background clutters, this study proposes an online robust discrimination joint dictionary learning model to update the dictionaries. The experimental results demonstrate that the proposed method has good robustness and superior tracking speed.
- L1 tracker /
- Coding transfer /
- Dictionary learning /
- Particle filter

HTML全文

參考文獻(20)

WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227. doi: 10.1109/TPAMI.2008.79.

MEI X and LING H B. Robust visual tracking using L1 minimization[C]. IEEE International Conference on Computer Vision, Kyoto, Japan, 2009: 1436-1443. doi: 10.1109/ICCV.2009.5459292.

WANG D, LU H C, and YANG M H. Least soft-thresold squares tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013: 2371-2378. doi: 10.1109/CVPR.2013.307.

ZHANG X Q, LI W, HU W M, et al. Block covariance based L1 tracker with a subtle template dictionary[J]. Pattern Recognition, 2013, 46(7): 1750-1761. doi: 10.1016/j.patcog. 2012.08.015.

WANG L J, OUYANG W L, WANG X G, et al. Visual tracking with fully convolutional networks[C]. IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3119-3127. doi: 10.1109/ICCV.2015. 357.

薛模根, 朱虹, 袁廣林. 基于在線判別式字典學習的魯棒視覺跟蹤[J]. 電子與信息學報, 2015, 37(7): 1654-1659. doi: 10.11999/JEIT141325.

XUE Mogen, ZHU Hong, and YUAN Guanglin. Robust visual tracking based on online discrimination dictionary learning[J]. Journal of Electronics Information Technology, 2015, 37(7): 1654-1659. doi: 10.11999/JEIT141325.

薛模根, 朱虹, 袁廣林. 在線魯棒判別式字典學習視覺跟蹤[J]. 電子學報, 2016, 44(4): 838-845. doi: 10.3969/j.issn.0372- 2112.2016.04.012.

XUE Mogen, ZHU Hong, and YUAN Guanglin. Online robust discrimination dictionary learning for visual tracking[J]. Acta Electronica Sinica, 2016, 44(4): 838-845. doi: 10.3969/j.issn.0372-2112.2016.04.012.

LIU B Y, LIN Y, HUANG J Z, et al. Robust and fast collaborative tracking with two stage sparse optimization[C]. Europe Conference on Computer Vision, Crete, Greece, 2010: 624-637. doi: 10.1007/978-3-642-15561-1_45.

MEI X, LING H B, WU Y, et al. Minimum error bounded efficient L1 tracker with occlusion detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011: 1257-1264. doi: 10.1109/ CVPR. 2011.5995421.

BAO C L, WU Y, LING H B, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, America, 2012: 1830-1837. doi: 10.1109/CVPR.2012.6247881.

ZHANG T Z, GHANEM B, LIU S, et al. Robust visual tracking via multi-task sparse learning[J]. International Journal of Computer Vision, 2013, 101(2): 367-383. doi: 10.1109/CVPR.2012.6247908.

袁廣林, 薛模根. 基于稀疏稠密結(jié)構表示與在線魯棒字典學習的視覺跟蹤[J]. 電子與信息學報, 2015, 37(3): 536-542. doi: 10.11999/JEIT140507.

YUAN Guanglin and XUE Mogen. Visual tracking based on sparse dense structure representation and online robust dictionary learning[J]. Journal of Electronics Information Technology, 2015, 37(3): 536-542. doi: 10.11999/JEIT140507.

袁廣林, 薛模根. 基于稀疏度約束與動態(tài)組結(jié)構稀疏編碼的魯棒視覺跟蹤[J]. 電子學報, 2015, 43(8): 1499-1505. doi: 10.3969/j.issn.0372-2112.2015.08.005.

YUAN Guanglin and XUE Mogen. Sparsity-constrained and dynamic group structured sparse coding for robust visual tracking[J]. Acta Electronica Sinica, 2015, 43(8): 1499-1505. doi: 10.3969/j.issn.0372-2112.2015.08.005.

YANG J C, WRIGHT J, HUANG T, et al. Image super- resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873. doi: 10.1109/TIP. 2010.2050625.

WU Y, LING H B, YU J Y, et al. Blurred target tracking by blur-driven tracker[C]. International Conference on Computer Vision, Barcelona, Spain, 2011: 1100-1107. doi: 10.1109/ICCV.2011.6126357.

WU Y, LIM J, and YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013: 24112418. doi: 10.1109/CVPR.2013.312.

施引文獻

資源附件(0)

訪問統(tǒng)計