一種魯棒的基于集成學(xué)習(xí)的核相關(guān)紅外目標(biāo)跟蹤算法

謝濤; 吳恩斯

doi:10.11999/JEIT170527

一種魯棒的基于集成學(xué)習(xí)的核相關(guān)紅外目標(biāo)跟蹤算法

doi: 10.11999/JEIT170527

謝濤¹,
吳恩斯²

1.
(西南大學(xué)計算機與信息科學(xué)學(xué)院重慶 400715) ②(重慶師范大學(xué)教務(wù)處重慶 401331)

基金項目:

教育部-中國移動科研基金(MCM20160405)

計量
- 文章訪問數(shù): 1149
- HTML全文瀏覽量: 219
- PDF下載量: 273
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-05-31
- 修回日期: 2017-12-05
- 刊出日期: 2018-03-19

A Robust Kernelized Correlation Tracking Algorithm for Infrared Targets Based on Ensemble Learning

XIE Tao¹,
WU Ensi²

1.
(College of Computer and Information Science, Southwest University, Chongqing 400715, China)
2.
(Office of Educational Administration, Chongqing Normal University, Chongqing 401331, China)

Funds:

The Ministry of Education-China Mobile Research Fund Project (MCM20160405)

摘要

摘要: 在紅外目標(biāo)跟蹤中，由于目標(biāo)所處的背景信息復(fù)雜多變和目標(biāo)外觀的顯著變化，單一的分類器不足以擬合多模態(tài)的數(shù)據(jù)。該文結(jié)合核相關(guān)濾波器(KCF)將多個核相關(guān)分類器通過集成學(xué)習(xí)整合到一個框架中。利用KCF分類器具有解析解的特點平衡跟蹤魯棒性與實時性之間的矛盾，從而解決單個分類器無法處理復(fù)雜背景與顯著的外觀變化問題，并顯著提升目標(biāo)跟蹤的性能與穩(wěn)定性。為了驗證算法的有效性，該文利用兩個核相關(guān)跟蹤器聯(lián)合學(xué)習(xí)出1個強分類器。大量的定性定量實驗表明所提的算法的跟蹤性能超過傳統(tǒng)的KCF算法，且跟蹤速度也超過大多數(shù)比較算法。
- 目標(biāo)跟蹤 /
- 集成學(xué)習(xí) /
- 判別式分類器 /
- 核相關(guān)跟蹤
Abstract: In the infrared object tracking, the single classifier is not enough to fit the multimodal data due to the complex background information of the target and the significant change in the appearance. In this paper, Kernelized Correlation Filters (KCF) tracking algorithm is used to integrate kernelized correlation classifiers into one framework through ensemble learning. It uses the KCF classifier that has analytical solutions to balance the contradiction between the robustness and instantaneity, thereby addressing the complex background and significant appearance changes, and consequently significantly improving the tracking performance and stability. To verify the effectiveness of the algorithm, this paper uses two kernelized correlation trackers to learn a strong classifier. The qualitative and quantitative experiments show that the proposed algorithm outperforms the traditional KCF algorithm, and the tracking speed is superior to most of the comparison algorithms.
- Object tracking /
- Ensemble learning /
- Discriminant classifier /
- Kernelized correlation tracking

HTML全文

參考文獻(27)

李少毅, 梁爽, 張凱, 等. 基于紅外壓縮成像的點目標(biāo)跟蹤方法研究[J]. 電子與信息學(xué)報, 2015, 37(7): 1639-1645. doi: 10.11999/JEIT141324.

LI Shaoyi, LIANG Shuang, ZHANG Kai, et al. Research of infrared compressive imaging based point target tracking method[J]. Journal of Electronics Information Technology, 2015, 37(7): 1639-1645. doi: 10.11999/JEIT 141324.

袁廣林, 薛模根. 基于稀疏稠密結(jié)構(gòu)表示與在線魯棒字典學(xué)習(xí)的視覺跟蹤[J]. 電子與信息學(xué)報, 2015, 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.

羅會蘭, 鐘寶康, 孔繁勝. 帶權(quán)分塊壓縮感知的預(yù)測目標(biāo)跟蹤算法[J]. 電子與信息學(xué)報, 2015, 37(5): 1160-1166. doi: 10.11999/JEIT140997.

LUO Huilan, ZHONG Baokang, and KONG Fansheng. Tracking using weighted block compressed sensing and location prediction[J]. Journal of Electronics Information Technology, 2015, 37(5): 1160-1166. doi: 10.11999/JEIT 140997.

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. doi: 10.1007/s11263-007-0075 -7.

ZHONG W, LU H, and YANG M H. Robust object tracking via sparse collaborative appearance model[J]. IEEE Transactions on Image Processing, 2014, 23(5): 2356-2368. doi: 10.1109/TIP.2014.2313227.

薛一哲, 王拓. 基于代價敏感 Adaboost 目標(biāo)跟蹤[J]. 中國圖像圖形學(xué)報, 2016, 21(5): 544-555.

XUE Yizhe and WANG Tuo. Object tracking based on cost-sensitive Adaboost algorithm[J]. Chinese Journal of Image and Graphics, 2016, 21(5): 544-555.

ZHANG K and SONG H. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013, 46(1): 397-411. doi: 10.1016/j.patcog.2012.07.013.

BABENKO B, YANG M H, and BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632. doi: 10.1109/TPAMI. 2010.226.

HU J, LU J, and TAN Y P. Deep metric learning for visual tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2016, 26(11): 2056-2068. doi: 10.1109/ TCSVT.2015.2477936.

KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. Imagenet classification with deep convolutional neural networks[C]. Proceedings of the Advances in Neural Information Processing Systems, Nevada, USA, 2012: 1097-1105. doi: 10.1145/3065386.

TANG Z, WANG S, HUO J, et al. Bayesian framework with non-local and low-rank constraint for image reconstruction [C]. Proceedings of the Journal of Physics, 2017, 787: 012008. doi: 10.1088/1742-6596/787/1/012008.

HENRIQUES J F, CASEIRO R, MARTINS P, et al. High- speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596. doi: 10.1109/TPAMI.2014.2345390.

LIU T, WANG G, and YANG Q. Real-time part-based visual tracking via adaptive correlation filters[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 4902-4912. doi: 10.1109/ CVPR.2015.7299124.

MATTHEWS L, ISHIKAWA T, and BAKER S. The template update problem[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(6): 810-815. doi: 10.1109/TPAMI.2004.16.

侯志強, 黃安奇, 余旺盛, 等. 基于局部分塊和模型更新的視覺跟蹤算法[J]. 電子與信息學(xué)報, 2015, 37(6): 1357-1364. doi: 10.11999/JEIT141134.

HOU Zhiqiang, HUANG Anqi, YU Wangsheng, et al. Visual object tracking method based on local patch model and model update[J]. Journal of Electronics Information Technology, 2015, 37(6): 1357-1364. doi: 10.11999/JEIT 141134.

薛模根, 朱虹, 袁廣林. 基于在線判別式字典學(xué)習(xí)的魯棒視覺跟蹤[J]. 電子與信息學(xué)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/JEIT 141325.

蘇巧平, 劉原, 卜英喬, 等. 基于稀疏表達的多示例學(xué)習(xí)目標(biāo)追蹤算法[J]. 計算機工程, 2013, 39(3): 213-217.

SHU Qiaoping, LIU Yuan, BU Yingqiao, et al. Multi-example learning target tracking algorithm based on sparse expression [J]. Computer Engineering, 2013, 39(3): 213-217.

VIOLA P, JONES M J, and SNOW D. Detecting pedestrians using patterns of motion and appearance[J]. International Journal of Computer Vision, 2005, 63(2): 153-161. doi: 10.1007/s11263-005-6644-8.

KALAL Z, MIKOLAJCZYK K, and MATAS J. Tracking- learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422. doi: 10.1109/TPAMI.2011.239

ZHANG K, ZHANG L, LIU Q, et al. Fast visual tracking via dense spatio-temporal context learning[C]. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 2014: 127-141. doi: 10.1007/978-3-319-10602- 1_9.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計