相关滤波视觉跟踪方法中深度上下文模型的研究

陈照云; 罗磊; 黄达飞; 文梅; 张春元

doi:10.1631/FITEE.1500389

Your Location：

Home >

Browse articles >

相关滤波视觉跟踪方法中深度上下文模型的研究

常规文章 | Updated：2022-05-19

- 相关滤波视觉跟踪方法中深度上下文模型的研究
- Exploiting a depth context model in visual tracking with correlation filter
- 信息与电子工程前沿（英文） 2017年18卷第5期页码：667-679
- Affiliations：
  
  1College of Computer, National University of Defense Technology, Changsha 410073, China
  2National Key Laboratory of Parallel and Distributed Processing, Changsha 410073, China
- Author bio：
  
  E-mail:chenzhaoyun@nudt.edu.cn
  E-mail:l.luo@nudt.edu.cn
- Funds：
  
  Project supported by the National Natural Science Foundation of China (Nos. 61502509, 61402504, and 61272145), the National High-Tech R&D Program (863) of China (No. 2012AA012706), and the Research Fund for the Doctoral Program of Higher Education of China (No. 21024307130004)
- DOI：10.1631/FITEE.1500389
  中图分类号： TP391.4
- 收稿：2015-11-10，
  
  录用：2016-6-6，
  
  纸质出版：2017-05
- Accepted：
Scan QR Code
陈照云, 罗磊, 黄达飞, 等. 相关滤波视觉跟踪方法中深度上下文模型的研究[J]. 信息与电子工程前沿（英文）, 2017,18(5):667-679.

Zhao-yun CHEN, Lei LUO, Da-fei HUANG, et al. Exploiting a depth context model in visual tracking with correlation filter[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 667-679.
陈照云, 罗磊, 黄达飞, 等. 相关滤波视觉跟踪方法中深度上下文模型的研究[J]. 信息与电子工程前沿（英文）, 2017,18(5):667-679. DOI： 10.1631/FITEE.1500389.

Zhao-yun CHEN, Lei LUO, Da-fei HUANG, et al. Exploiting a depth context model in visual tracking with correlation filter[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 667-679. DOI： 10.1631/FITEE.1500389.

摘要

近来，基于相关滤波器的跟踪器因具有较高的计算效率而颇受关注，但这一方法不能很好地处理遮挡和尺度变化。本文旨在将深度信息整合到基于相关滤波器的跟踪器中，以解决跟踪器在上述两种情况下的跟踪失败。同时利用RGB-D数据构建了一个深度上下文模型，用来描述目标与周边区域之间的空间相关性。此外，本文采用了区域生长法使跟踪器对遮挡和尺度变化的场景具有更高鲁棒性，并利用模型更新等优化方法来改进较长视频序列的性能。通过对极具挑战性的基准图像序列测试集的定性和定量评估，本文提出的跟踪器比最先进的算法具有更好的性能。

Abstract

Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However

they cannot handle occlusion and scale variation well enough. This paper aims at preventing the tracker from failure in these two situations by integrating the depth information into a correlation filter based tracker. By using RGB-D data

we construct a depth context model to reveal the spatial correlation between the target and its surrounding regions. Furthermore

we adopt a region growing method to make our tracker robust to occlusion and scale variation. Additional optimizations such as a model updating scheme are applied to improve the performance for longer video sequences. Both qualitative and quantitative evaluations on challenging benchmark image sequences demonstrate that the proposed tracker performs favourably against state-of-the-art algorithms.

关键词

Keywords

references

A Adam , , , E Rivlin , , , I Shimshoni . . Robust fragmentsbased tracking using the integral histogram . . 2006 . . IEEE Computer Society Conf. on Computer Vision and Pattern Recognition . . 798 - - 805 . . DOI: 10.1109/CVPR.2006.256 http://doi.org/10.1109/CVPR.2006.256 . .

R Adams , , , L Bischof . . Seeded region growing . . IEEE Trans. Patt. Anal. Mach. Intell. , , 1994 . . 16 ( ( 6 ): ): 641 - - 647 . . DOI: 10.1109/34.295913 http://doi.org/10.1109/34.295913 . .

DS Bolme , , , JR Beveridge , , , BA Draper , , , 等 . . Visual object tracking using adaptive correlation filters . . 2010 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 2544 - - 2550 . . DOI: 10.1109/CVPR.2010.5539960 http://doi.org/10.1109/CVPR.2010.5539960 . .

L Cehovin , , , M Kristan , , , A Leonardis . . An adaptive coupled-layer visual model for robust visual tracking . . 2011 . . IEEE Int. Conf. on Computer Vision . . 1363 - - 1370 . . DOI: 10.1109/ICCV.2011.6126390 http://doi.org/10.1109/ICCV.2011.6126390 . .

K Chen , , , Y Lai , , , Y Wu , , , 等 . . Automatic semantic modeling of indoor scenes from low-quality RGB-D data using contextual information . . ACM Trans. Graph. , , 2014 . . 33 ( ( 6 ): ): 208 - - 219 . . DOI: 10.1145/2661229.2661239 http://doi.org/10.1145/2661229.2661239 . .

C Choi , , , HI Christensen . . RGB-D object tracking: a particle filter approach on GPU . . 2013 . . IEEE/RSJ Int. Conf. on Intelligent Robots and Systems . . 1084 - - 1091 . . DOI: 10.1109/IROS.2013.6696485 http://doi.org/10.1109/IROS.2013.6696485 . .

M Danelljan , , , G Häger , , , FS Khan , , , 等 . . Accurate scale estimation for robust visual tracking . . 2014a . . British Machine Vision Conf. . . 1 - - 11 . . . .

M Danelljan , , , FS Khan , , , M Felsberg , , , 等 . . Adaptive color attributes for real-time visual tracking . . 2014b . . IEEE Conf. on Computer Vision and Pattern Recognition . . 1090 - - 1097 . . DOI: 10.1109/CVPR.2014.143 http://doi.org/10.1109/CVPR.2014.143 . .

TB Dinh , , , N Vo , , , GG Medioni . . Context tracker: exploring supporters and distracters in unconstrained environments . . 2011 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 1177 - - 1184 . . DOI: 10.1109/CVPR.2011.5995733 http://doi.org/10.1109/CVPR.2011.5995733 . .

M Everingham , , , LV Gool , , , CK Williams , , , 等 . . The Pascal Visual Object Classes (VOC) challenge . . Int. J. Comput. Vis. , , 2010 . . 88 ( ( 2 ): ): 303 - - 338 . . DOI: 10.1007/s11263-009-0275-4 http://doi.org/10.1007/s11263-009-0275-4 . .

H Grabner , , , J Matas , , , LV Gool , , , 等 . . Tracking the invisible: learning where the object might be . . 2010 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 1285 - - 1292 . . DOI: 10.1109/CVPR.2010.5539819 http://doi.org/10.1109/CVPR.2010.5539819 . .

S Gupta , , , RB Girshick , , , P Arbelaez , , , 等 . . Learning rich features from RGB-D images for object detection and segmentation . . 2014 . . ECCV . . 345 - - 360 . . DOI: 10.1007/978-3-319-10584-0_23 http://doi.org/10.1007/978-3-319-10584-0_23 . .

S Hare , , , A Saffari , , , P Torr , , , 等 . . Struck: structured output tracking with kernels . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2011 . . 38 ( ( 10 ): ): 263 - - 270 . . DOI: 10.1109/TPAMI.2015.2509974 http://doi.org/10.1109/TPAMI.2015.2509974 . .

JF Henriques , , , R Caseiro , , , P Martins , , , 等 . . Exploiting the circulant structure of tracking-by-detection with kernels . . 2012 . . ECCV . . 702 - - 715 . . DOI: 10.1007/978-3-642-33765-9_50 http://doi.org/10.1007/978-3-642-33765-9_50 . .

JF Henriques , , , R Caseiro , , , P Martins , , , 等 . . Highspeed tracking with kernelized correlation filters . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2015 . . 37 ( ( 3 ): ): 583 - - 596 . . DOI: 10.1109/TPAMI.2014.2345390 http://doi.org/10.1109/TPAMI.2014.2345390 . .

S Hickson , , , S Birchfield , , , IA Essa , , , 等 . . Efficient hierarchical graph-based segmentation of RGBD videos . . 2014 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 344 - - 351 . . . .

H Izadinia , , , I Saleemi , , , W Li , , , 等 . . (MP) 2T: multiple people multiple parts tracker . . 2012 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 100 - - 114 . . DOI: 10.1007/978-3-642-33783-3_8 http://doi.org/10.1007/978-3-642-33783-3_8 . .

Z Kalal , , , K Mikolajczyk , , , J Matas . . Trackinglearning-detection . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2012 . . 34 ( ( 7 ): ): 1409 - - 1422 . . DOI: 10.1109/TPAMI.2011.239 http://doi.org/10.1109/TPAMI.2011.239 . .

M Kristan , , , R Pflugfelder , , , A Leonardis , , , 等 . . The visual object tracking VOT2014 challenge results . . 2015 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 191 - - 217 . . . .

BV Kumar , , , A Mahalanobis , , , RD Juday . . Correlation Pattern Recognition , , 2010 . . : Cambridge : Cambridge University Press , , . .

D Lee , , , J Sim , , , C Kim . . Visual tracking using pertinent patch selection and masking . . 2014 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 3486 - - 3493 . . . .

X Li , , , W Hu , , , C Shen , , , 等 . . A survey of appearance models in visual object tracking . . ACM Intell. Syst. Technol. , , 2013 . . 4 ( ( 4 ): ): 58 DOI: 10.1145/2508037.2508039 http://doi.org/10.1145/2508037.2508039 . .

Y Li , , , J Zhu . . A scale adaptive kernel correlation filter tracker with feature integration . . 2014 . . ECCV . . 254 - - 265 . . DOI: 10.1007/978-3-319-16181-5_18 http://doi.org/10.1007/978-3-319-16181-5_18 . .

Y Li , , , J Zhu , , , S Hoi , , , 等 . . Reliable patch trackers: robust visual tracking by exploiting reliable patches . . 2015 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 353 - - 361 . . . .

T Liu , , , G Wang , , , Q Yang . . Real-time part-based visual tracking via adaptive correlation filters . . 2015 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 4902 - - 4912 . . . .

M Luber , , , L Spinello , , , KO Arras . . People tracking in RGB-D data with on-line boosted target models . . 2011 . . IEEE/RSJ Int. Conf. on Intelligent Robots and Systems . . 3844 - - 3849 . . DOI: 10.1109/IROS.2011.6095075 http://doi.org/10.1109/IROS.2011.6095075 . .

C Ma , , , X Yang , , , C Zhang , , , 等 . . Long-term correlation tracking . . 2015 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 5388 - - 5396 . . . .

Y Park , , , V Lepetit , , , W Woo . . Texture-less object tracking with online training using an RGB-D camera . . 2011 . . 10th IEEE Int. Symp. on Mixed and Augmented Reality . . 121 - - 126 . . DOI: 10.1109/ISMAR.2011.6092377 http://doi.org/10.1109/ISMAR.2011.6092377 . .

DA Ross , , , J Lim , , , RS Lin , , , 等 . . Incremental learning for robust visual tracking . . Int. J. Comput. Vis. , , 2008 . . 77 ( ( 1-3 ): ): 125 - - 141 . . DOI: 10.1007/s11263-007-0075-7 http://doi.org/10.1007/s11263-007-0075-7 . .

G Shu , , , A Dehghan , , , O Oreifej , , , 等 . . Partbased multiple-person tracking with partial occlusion handling . . 2012 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 1815 - - 1821 . . DOI: 10.1109/CVPR.2012.6247879 http://doi.org/10.1109/CVPR.2012.6247879 . .

AW Smeulders , , , D Chu , , , R Cucchiara , , , 等 . . Visual tracking: an experimental survey . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2014 . . 36 ( ( 7 ): ): 1442 - - 1468 . . DOI: 10.1109/TPAMI.2013.230 http://doi.org/10.1109/TPAMI.2013.230 . .

S Song , , , J Xiao . . Tracking revisited using RGBD camera: unified benchmark and baselines . . 2013 . . IEEE Int. Conf. on Computer Vision . . 233 - - 240 . . . .

A Teichman , , , JT Lussier , , , S Thrun . . Learning to segment and track in RGBD . . IEEE Trans. Autom. Sci. Eng. , , 2013 . . 10 ( ( 4 ): ): 841 - - 852 . . DOI: 10.1109/TASE.2013.2264286 http://doi.org/10.1109/TASE.2013.2264286 . .

Y Wu , , , J Lim , , , M Yang . . Online object tracking: a benchmark . . 2013 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 2411 - - 2418 . . . .

B Yang , , , R Nevatia . . Online learned discriminative part-based appearance models for multi-human tracking . . 2012 . . ECCV . . 484 - - 498 . . DOI: 10.1007/978-3-642-33718-5_35 http://doi.org/10.1007/978-3-642-33718-5_35 . .

H Yang , , , L Shao , , , F Zheng , , , 等 . . Recent advances and trends in visual tracking: a review . . Neurocomputing , , 2011 . . 74 ( ( 18 ): ): 3823 - - 3831 . . DOI: 10.1016/j.neucom.2011.07.024 http://doi.org/10.1016/j.neucom.2011.07.024 . .

M Yang , , , Y Wu , , , G Hua . . Context-aware visual tracking . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2009 . . 31 ( ( 7 ): ): 1195 - - 1209 . . DOI: 10.1109/TPAMI.2008.146 http://doi.org/10.1109/TPAMI.2008.146 . .

A Yilmaz , , , O Javed , , , M Shah . . Object tracking: a survey . . ACM Comput. Surv. , , 2006 . . 38 ( ( 4 ): ): 13 DOI: 10.1145/1177352.1177355 http://doi.org/10.1145/1177352.1177355 . .

L Zhang , , , L Maaten . . Preserving structure in modelfree tracking . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2014 . . 36 ( ( 4 ): ): 756 - - 769 . . DOI: 10.1109/TPAMI.2013.221 http://doi.org/10.1109/TPAMI.2013.221 . .

K Zhang , , , L Zhang , , , Q Liu , , , 等 . . Fast visual tracking via dense spatio-temporal context learning . . 2014 . . ECCV . . 127 - - 141 . . DOI: 10.1007/978-3-319-10602-1_9 http://doi.org/10.1007/978-3-319-10602-1_9 . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

A quantitative attribute-based benchmark methodology for single-target visual tracking