Minimum barrier distance based tracking via spatio-temporal context learning

Abstract

We propose an efficient and robust tracking method based on minimum barrier distance (MBD) and spatio-temporal context (STC) learning. It is robust to noise and blur, and can be evaluated approximately through a Dijkstra-like algorithm, leading to fast computation. We adopt the MBD transform to measure the weights of context pixels, and formulate the spatio-temporal relationship between the object and its surrounding region based on a Bayesian framework to estimate the most likely location of the target. A bounded scale update model is proposed to estimate the size of the object. The whole proposed method runs at nearly 160 frames per second (FPS) on an i5 machine. Extensive experimental results show it has comparable or better comprehensive performance than the original STC and some other leading methods.

References

[1] PapanikolopoulosN., KhoslaP., KanadeT.. IEEE Trans. Robot. Automat., 1993, 9: 14

[2] ChangC., WijayaL. H.. IEEE Trans. Ind. Electron., 2012, 59: 1640

[3] SongH., ChoiW., KimH.. IEEE Trans. Ind. Elec tron., 2016, 63: 3725

[4] RossD., LimJ., LinR., YangM.. International Journal of Computer Vision, 2007, 77: 125

[5] BiresawT., CavallaroA., RegazzoniC.. IEEE Trans. Circuits Syst. Video Technol., 2015, 25: 776

[6] YuanW., SunJ., CaoZ., TianJ., YangM.. Optoelectronics Letters, 2010, 6: 137

[7] SunX., YaoH., ZhangS., LiD.. IEEE Transactions on Image Processing, 2015, 24: 3386

[8] ZhaoL., ZhaoQ., ChenY., LvP.. J. Electron. Imaging, 2016, 25: 023005

[9] DinhT., YuQ., MedioniG.. Computer Vision and Image Understanding, 2014, 119: 41

[10] HuQ., GuoY., LinZ., DengX., AnW.. IEEE Access, 2017, 5: 8568

[11] XiaoJ., QiaoL., StolkinR., LeonardisA.. Distractor-supported Single Target Tracking in Extremely Cluttered Scenes, in Proc. Eur. Conf. Comput. Vis., 2016,

[12] BolmeD. S., BeveridgeJ. R., DraperB. A., LuiY. M.. Visual Object Tracking Using Adaptive Correlation Filters, Proc. IEEE Conf. Comput. Vis. Pattern Reco. (CVPR), 2544, 2010,

[13] HenriquesF., CaseiroR., MartinsP., BatistaJ.. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels, Euro, 2012, Berlin, 702, Conf. on Computer Vision (ECCV)

[14] HenriquesJ., CaseiroR., MartinsP., BatistaJ.. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37: 583

[15] DanelljanM., FahadS. K., MichaelF., JoostVand W.. Adaptive Color Attributes for Real-time Visual Tracking, Proc. IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), 2014,

[16] ZhangK., ZhangL., LiuQ., ZhangD., YangM.H.. Fast Visual Tracking via Dense Spatio-temporal Context Learning, Euro, 2014, Berlin,127, Conf. on Computer Vision (ECCV)

[17] ChenD. B., ZhuM., WangH. L.. Optoelectronics Letters, 2017, 13: 392

[18] ChenG., MiaoL., WangH.. Robust Tracking via Color Names and Spatial Context Learning, 2015 International Conference on Virtual Reality and Visualization (ICVRV), Xiamen, 2015,

[19] StrandR., CiesielskiK., MalmbergF., SahaP.. Computer Vision and Image Understanding, 2013, 117: 429

[20] CiesielskiK., StrandR., MalmbergF., SahaP.. Computer Vision and Image Understanding, 2014, 123: 53

[21] ZhangJ., SclaroffS., LinZ., ShenX., PriceB., MechR.. Minimum Barrier Salient Object Detection at 80 FPS, 2015 IEEE International Conference on Computer Vision (ICCV), 2015,

[22] WuY., LimJ., YangM.. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37: 1834

[23] ZhangK., ZhangL., YangM.H.. Real-time Compressive Tracking, Euro, 2012, Berlin, 864, Conf. on Computer Vision (ECCV)

[24] KalalZ., MikolajczykK., MatasJ.. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34: 1409

[25] Sevilla-LaraL., Learned-MillerE.. Distribution Fields for Tracking, Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012,

[26] RossD. A., LimJ., LinR.S., YangM.H.. Int. J. Comput. Vis., 2008, 77: 125

[27] ZhangT., GhanemB., LiuS., AhujaN.. Int. J. Comput. Vis., 2013, 101: 367

[28] DinhT. B., VoN., MedioniG.. Context Tracker: Exploring Supporters and Distracters in Unconstrained Environments, Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1177, 2011,

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.