A template consensus method for visual tracking

Abstract

Visual tracking is a challenging problem in computer vision. Recently, correlation filter-based trackers have shown to provide excellent tracking performance. Inspired by a sample consensus approach proposed for foreground detection, which classifies a given pixel as foreground or background based on its similarity to recently observed samples, we present a template consensus tracker based on the kernelized correlation filter (KCF). Instead of keeping only one target appearance model in the KCF, we make a feature pool to keep several target appearance models in our method and predict the new target position by searching for the location of the maximal value of the response maps. Both quantitative and qualitative evaluations are performed on the CVPR2013 tracking benchmark dataset. The results show that our proposed method improves the original KCF tracker by 8.17% in the success plot and 8.11% in the precision plot.

References

[1] AlperY.. Omar Javed and Mubarak Shah, ACM Computing Surveys, 2006, 38: 4

[2] Yi Wu, Jongwoo Lim and Ming Hsuan Yang, Online Object Tracking: A Benchmark, IEEE Conference on Computer Vision and Pattern Recognition, 2411 (2013).

[3] ArnoldW. M.. Smeulders, Dung M. Chu, Rita Cucchiara, Simone Calderara, Afshin Dehghan and Mubarak Shah, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36: 1442

[4] DavidS., BolmeJ.. Ross Beveridge, Bruce A. Draper and Yui Man Lui, Computer Vision and Pattern Recognition, 2010, 119: 2544

[5] Martin Danelljan, Gustav Hager, Fahad Shahbaz Khan and Michael Felsberg, Accurate Scale Estimation for Robust Visual Tracking, British Machine Vision Conference, 223 (2014).

[6] Jo. F. Henriques, Rui Caseiro, Pedro Martins and Jorge Batista, Exploiting the circulant structure of tracking-by-detection with kernels, European Conference on Computer Vison, 702 (2012).

[7] DanelljanM., KhanF. S., FelsbergM., Van de WeijerJ.. Adaptive Color Attributes for Real-Time Visual Tracking, IEEE Conference on Computer Vision and Pattern Recognition, 1090, 2014,

[8] JoaoF. H.. Caseiro Rui, Pedro Martins and Jorge Batista, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37: 583

[9] Yang Li and Jianke Zhu, A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration, European Conference on Computer Vision, 254 (2015).

[10] MonteroA. S., LangJ., LaganiReR.. Scalable Kernel Correlation Filter with Sparse Feature Integration, IEEE International Conference on Computer Vision Workshop, 587, 2015,

[11] AshaC. S., NarasimhadhanA. V.. Procedia Computer Science, 2016, 89: 614

[12] ZhangjianJ., WeiqiangW.. Journal of Visual Communication & Image Representation, 2018, 55: 354

[13] Xu F, Wang H, Song Y and Liu J, A Multi-Scale Kernel Correlation Filter Tracker with Feature Integration and Robust Model Updater, 29th Chinese Control and Decision Conference, 1934 (2017).

[14] PanZ., ZhuY.. Computer Engineering & Applications, 2017, 53: 196

[15] Bibi A and Ghanem B, Multi-template Scale-Adaptive Kernelized Correlation Filters, IEEE International Conference on Computer Vision Workshop, 613 (2016).

[16] HanziW., DavidS.. Pattern Recognition, 2007, 40: 1091

[17] Sam Hare, Amir Saffari and Philip H. S Torr, Struck: Structured Output Tracking with Kernels, IEEE International Conference on Computer Vision, 263 (2011).

[18] ZdenekK.. Krystian Mikolajczyk and Jiri Matas, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34: 1409

[19] Thang Ba Dinh, Nam Vo and G Medioni, Context Tracker: Exploring Supporters and Distracters in Unconstrained Environments, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, 1177 (2011).

[20] BorisB.. Ming Hsuan Yang and Serge Belongie, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33: 1619

This work has been supported by the National Natural Science Foundation of China (No.61401425).