Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Support vector correlation filter with long-term tracking

Support vector correlation filter with long-term tracking Boosted by the promising advancement of the correlation filter-based tracker, we propose an algorithm called the SLT (support vector correlation filter with long-term tracking) that is based on the new SCF (support vector correlation filter) framework to handle long-term tracking. To perform long-term tracking, we propose using a detector to refine the position that includes occlusion and deformation and is out-of-view. We used a new judgment criterion called the max response to the average response rate (MAR) to activate the re-detection procedure and then exploit the linear support vector machine (SVM) classifier to obtain a positive refinement. Moreover, we do not update the SVM classifier every frame to reduce the number of computations and obtain better samples to improve the accuracy of the classifier. We use the online passive–aggressive learning algorithm for online learning and use the same MAR criterion to active it. Extensive experimental results on the OTB50 benchmark dataset show its superior performance in terms of accuracy and robustness. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png "Signal, Image and Video Processing" Springer Journals

Support vector correlation filter with long-term tracking

Download PDF
9 pages

Loading next page...
 
/lp/springer_journal/support-vector-correlation-filter-with-long-term-tracking-9mAgCv3zHF
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer-Verlag London Ltd., part of Springer Nature
Subject
Computer Science; Image Processing and Computer Vision; Signal,Image and Speech Processing; Computer Imaging, Vision, Pattern Recognition and Graphics; Multimedia Information Systems
ISSN
1863-1703
eISSN
1863-1711
DOI
10.1007/s11760-018-1310-0
Publisher site
See Article on Publisher Site

Abstract

Boosted by the promising advancement of the correlation filter-based tracker, we propose an algorithm called the SLT (support vector correlation filter with long-term tracking) that is based on the new SCF (support vector correlation filter) framework to handle long-term tracking. To perform long-term tracking, we propose using a detector to refine the position that includes occlusion and deformation and is out-of-view. We used a new judgment criterion called the max response to the average response rate (MAR) to activate the re-detection procedure and then exploit the linear support vector machine (SVM) classifier to obtain a positive refinement. Moreover, we do not update the SVM classifier every frame to reduce the number of computations and obtain better samples to improve the accuracy of the classifier. We use the online passive–aggressive learning algorithm for online learning and use the same MAR criterion to active it. Extensive experimental results on the OTB50 benchmark dataset show its superior performance in terms of accuracy and robustness.

Journal

"Signal, Image and Video Processing" – Springer Journals

Published: May 31, 2018

References

  • Robust object tracking via online Principal Component-Canonical Correlation Analysis (P3CA)
    Wang, Y; Zhao, Q
  • Structural sparse coding seeds-active appearance model for object tracking
    Ouyang, Y
  • Visual tracking using IPCA and sparse representation
    Shan, D; Zhang, C
  • Robust object tracking with online multiple instance learning
    Babenko, B; Yang, M-H; Belongie, SJ
  • Tracking-learning-detection
    Kalal, Z; Mikolajczyk, K; Matas, J
  • Support vector tracking
    Avidan, S
  • High-speed tracking with kernelized correlation filters
    Henriques, JF; Caseiro, R; Martins, P; Batista, J
  • Improved object tracking via joint color-LPQ texture histogram based mean shift algorithm
    Medouakh, S; Boumehraz, M; Terki, N
  • Online passive-aggressive algorithms
    Crammer, K; Dekel, O; Keshet, J; Shalev-Shwartz, S; Singer, Y