计算机科学 ›› 2016, Vol. 43 ›› Issue (11): 1-5.doi: 10.11896/j.issn.1002-137X.2016.11.001

• 目次 •    下一篇

基于相关滤波器的视觉目标跟踪综述

魏全禄,老松杨,白亮   

  1. 国防科学技术大学信息系统工程重点实验室 长沙410073,国防科学技术大学信息系统工程重点实验室 长沙410073,国防科学技术大学信息系统工程重点实验室 长沙410073
  • 出版日期:2018-12-01 发布日期:2018-12-01

Visual Object Tracking Based on Correlation Filters:A Survey

Wei Quanlu, Lao Songyang and Bai Liang   

  • Online:2018-12-01 Published:2018-12-01

摘要: 视觉跟踪是一个重要的计算机视觉任务,有着广泛的应用,由于 现实场景中存在着众多困难,视觉跟踪仍是一个活跃的研究领域。判别式分类器是现代跟踪方法中的一个核心组成部分,其在线学习一个二值分类器以在每一帧中区分目标与背景,充分利用机器学习中丰富的学习算法,取得了许多突破。相关滤波器已成功应用到目标检测和识别中,其由于计算效率高,近年来作为一种判别式跟踪方法被应用到视觉跟踪领域,取得了很好的效果。首先简要介绍了判别式跟踪算法;然后对相关滤波器基本理论及几种典型的相关滤波器构造方法进行了描述;最后重点介绍了近年来相关滤波器在视觉跟踪中的应用及研究进展,并总结了可能的研究方向和发展趋势。

关键词: 视觉跟踪,判别式学习方法,相关滤波器

Abstract: ion Based on Object Detection and TrackingTIAN He-lei et al.(297) Medical CT Image Enhancement Algorithm Based on Laplacian Pyramid and Wavelet TransformLV Li-zhi et al.(300) Image Compression Based on Discrete Tchebichef Moments and Soft Decision QuantizationLU Gang et al.(304) Image Co-segmentation by Constraints of ShapePAN Xiang et al.(309) Image Registration Algorithm for Infrared and Visible Light Based on Non-subsampled Contourlet TransformLIU Gang et al.(313) Fractal Dimension Based Wavelet Packet EBCOT Core Image CompressionTANG Guo-wei et al.(317) 《计算机科学》审编委员会The Editorial Board of Computer Science(以姓氏拼音为序) 到稿日期:2015-10-30 返修日期:2016-03-15 魏全禄 男,博士生,主要研究方向为计算机视觉、多媒体信息系统,E-mail:blessyou668@163.com;老松杨 男,博士,教授,主要研究方向为多媒体信息系统与虚拟现实、人机交互、指挥决策分析等;白 亮 男,博士,副教授,主要研究方向为数字视频、音频处理和检索等。 基于相关滤波器的视觉目标跟踪综述 魏全禄 老松杨 白 亮 (国防科学技术大学信息系统工程重点实验室 长沙410073) 摘要 视觉跟踪是一个重要的计算机视觉任务,有着广泛的应用,由于 现实场景中存在着众多困难,视觉跟踪仍是一个活跃的研究领域。判别式分类器是现代跟踪方法中的一个核心组成部分,其在线学习一个二值分类器以在每一帧中区分目标与背景,充分利用机器学习中丰富的学习算法,取得了许多突破。相关滤波器已成功应用到目标检测和识别中,其由于计算效率高,近年来作为一种判别式跟踪方法被应用到视觉跟踪领域,取得了很好的效果。首先简要介绍了判别式跟踪算法;然后对相关滤波器基本理论及几种典型的相关滤波器构造方法进行了描述;最后重点介绍了近年来相关滤波器在视觉跟踪中的应用及研究进展,并总结了可能的研究方向和发展趋势。 关键词 视觉跟踪,判别式学习方法,相关滤波器 中图法分类号 TP391 文献标识码 A DOI 10.11896/j.issn.1002-137X.2016.11.001 Visual Object Tracking Based on Correlation Filters:A Survey WEI Quan-lu LAO Song-yang BAI Liang (Science and Technology on Information Systems Engineering Laboratory,National University of Defense Technology,Changsha 410073,China) Abstract Visual object tracking is a fundamental task in many computer vision applications which is still an active research field due to the challenges in real scenes.The core component of most modern trackers is a discriminative classi-fier which can use the abundant algorithms in machine learning to learn a binary classifier online to separate the object from the surrounding environment.Due to the high computational efficiency,as a discriminative tracking method,correlation filters which have been successfully applied to a variety of pattern recognition applications are introduced to the topic of visual tracking in recent years.The discriminative learning methods in visual tracking were introduced briefly firstly.Then the fundamental theory and some kinds of the typical methods of correlation filters were described.Finally,a detailed review of the applications of the correlation filters in visual tracking was provided,and the future applications and research trends were discussed.

Key words: Visual tracking,Discriminative learning,Correlation filter

[1] Smeulders A W M,Chu D M,Calderara S,et al.Visual Tra-cking:an Experimental Survey[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2013,36(7):1442-1468
[2] Henriques J A F,Caseiro R,Martins P,et al.High-Speed Tra-cking with Kernelized Correlation Filters[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2014,37(3):583-596
[3] Zhang Huan-long,Hu Shi-qiang,Yang Guo-sheng.Video Object Tracking Based on Appearance Models Learning[J].Journal of Computer Research and Development,2015,52(1):177-190(in Chinese) 张焕龙,胡士强,杨国胜.基于外观模型学习的视频目标跟踪方法综述[J].计算机研究与发展,2015,2(1):177-190
[4] Bolme D S,Beveridge J R,Draper B A,et al.Visual object tra-cking using adaptive correlation filters[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2010:2544-2550
[5] Salti S,Cavallaro A,Stefano L D.Adaptive Appearance Mode-ling for Video Tracking:Survey and Evaluation[J].IEEE Tran-saction on Image Processing,2012,21(10):4334-4348
[6] Yang Han-xuan,Shao Ling,Zheng Feng,et al.Recent advances and trends in visual tracking:A review[J].Neurocomputing,2011,74(18):3823-3831
[7] Collins R T,Liu Yan-xi,Leordeanu M.Online selection of discriminative tracking features[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643
[8] Avidan S.Ensemble tracking[J].IEEE Transaction on PatternAnalysis and Machine Intelligence,2007,29(2):261-271
[9] Tian M,Zhang W,Liu F.Online ensemble SVM for robust object tracking[C]∥8th Asian Conference on Computer Vision.Tokyo,2007:355-364
[10] Grabner H,Bischof H.Real-time tracking via online boosting[C]∥Proceedings of the British Machine Vision Conference.Edinburgh,2006:47-56
[11] Saffari A,Leistner C,Santner J,et al.Online random forests[C]∥IEEE 12th International Conference on Computer Vision Workshops.Kyoto,2009:1393-1400
[12] Grabner H,Leistner C,Bischof H.Semi-supervised online boosting for robust tracking[C]∥10th European Conference on Computer Vision.Marseille,2008:234-247
[13] Babenko B,Yang M H,Belongie S.Visual tracking with online multiple instance learning[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Miami,2009:983-990
[14] Aeschliman C,Park J,Kak A.A probabilistic framework forjoint segmentation and tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,2010:1371-1378
[15] Zhang Kai-hua,Zhang Lei,Yang M H.Fast Compressive Tra-cking[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2014,36(10):2002-2015
[16] Kalal Z,Mikolajczyk K,Matas J.Tracking-Learning-Detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2012,34(7):1409-1422
[17] Hare S,Saffari A,Torr P H S.Struck:Structured OutputTracking with Kernels[C]∥IEEE International Conference on Computer Vision.Barcelona,2011:263-270
[18] Bolme D S.Theory and Application of Optimized CorrelationOutput[D].Colorado State University,2011
[19] Kumar B V K V,Mahalanobis A,Juday R D.Correlation Pattern Recognition[M].Cambridge University Press,2005
[20] Kumar B V K V,Fernandez J A,Rodriguez A,et al.Recent advances in correlation filter theory and application[J].Optical Pattern Recognition,2014,9094:909404-909404-13
[21] Bolme D S,Draper B A,Beveridge J R.Average of synthetic exa-ct filters[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Miami,2009:2105-2112
[22] Rodriguez A,Kumar B V K V.Maximum Margin CorrelationFilter:A New Approach for Localization and Classification[J].IEEE Transaction on Image Processing,2013,22(2):631-643
[23] Henriques J A F,Caseiro R,Martins P,et al.Exploiting the Circulant Structure of Tracking-by-Detection with Kernels[C]∥12th European Conference on Computer Vision,Florence.Italy,2012:702-715
[24] Zhang Lei,Wang Yan-jie,Liu Yan-ying,et al.Visual objecttracking algorithm based on correlation filters[J].Journal of Optoelectronics Laser,2015,26(7):1349-1357(in Chinese) 张雷,王延杰,刘艳滢,等.基于相关滤波器的视觉目标跟踪方法[J].光电子激光,2015,26(7):1349-1357
[25] Danelljan M,Khan F S,Felsberg M,et al.Adaptive Color At-tributes for Real-Time Visual Tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Columbus,2014:1090-1097
[26] Danelljan M,Hger G,Khan F S,et al.Accurate Scale Estimation for Robust Visual Tracking[C]∥Proceedings of the British Machine Vision Conference.2014:1-11
[27] Zhang K,Zhang L,Liu Q,et al.Fast visual tracking via dense spatio-temporal context learning[C]∥13th European Confe-rence on Computer Vision.Zurich,2014:127-141
[28] Ma Chao,Yang Xiao-kang,Zhang Chong-yang,et al.Long-term Correlation Tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2015:5388-5396
[29] Liu Ting,Wang Gang,Yang Qing-xiong.Real-time part-basedvisual tracking via adaptive correlation filters[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2015:4902-4912

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!