ABSTRACT
Accurate and robust visual object tracking is one of the most challenging computer vision problems. Recently, discriminative correlation filter trackers have shown promising results on benchmark datasets with continuous performance improvements in tracking accuracy and robustness. Still, these algorithms fail to track as the target object and background conditions undergo drastic changes over time. They are also incapable to resume tracking once the target is lost, limiting the ability to track long term. The proposed BoVW-CFT is a classifier-based generic technique to handle tracking uncertainties in correlation filter trackers. Tracking failures in correlation trackers are automatically identified and an image classifier with training, testing and online update stages is proposed as detector in the tracking scenario using Bag of Visual Words (BoVW) features. The proposed detector falls under the parts based model and is quite well suited in the tracking framework. Further, the online training stage in the proposed framework with updated model or training samples, incorporates temporal information, helping to detect rotated, blurred and scaled versions of the target. On detecting a target loss in the correlation tracker, the trained classifier, referred to as detector, is invoked to re-initialize the tracker with the actual target location. Therefore, for each tracking uncertainty, two output patches are obtained, one each from the base tracker and the classifier. The final target location is estimated using the normalized cross-correlation with the initial target patch. The method has the advantages of mitigating the model drift in correlation trackers and learns a robust model that tracks long term. Extensive experimental results demonstrate an improvement of 4.1% in the expected overlap, 1.86% in accuracy and 15.46% in robustness on VOT2016 and 1.82% in overlap precision, 2.32% in AUC and 2.87% in success rates on OTB100.
- Vasileios Belagiannis, Falk Schubert, Nassir Navab, and Slobodan Ilic. 2012. Segmentation based particle filtering for real-time 2d object tracking. (2012), 842--855. In European Conference on Computer Vision, Springer.Google Scholar
- Luca Bertinetto, Valmadre Jack, Joao F. Henriques, Vedaldi Andrea, and Philip HS Torr. 2016. Fully-convolutional siamese networks for object tracking. (2016), 850--865. In European Conference on Computer Vision, Springer.Google Scholar
- Luca Bertinetto, Valmadre Jack, Golodetz Stuart, Miksik Ondrej, and Philip HS Torr. 2016. Staple: Complementary learners for real-time tracking. (2016), 1401--1409. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
- David S. Bolme, J. Ross Beveridge, Bruce A. Draper, and Yui Man Lui. 2010. Visual object tracking using adaptive correlation filters. (2010), 2544--2550. In Computer Vision and Pattern Recognition (CVPR), IEEE Conference.Google Scholar
- Andreas Robinson Fahad Shahbaz Khan Danelljan, Martin and Michael Felsberg. 2016. Beyond correlation filters: Learning continuous convolution operators for visual tracking. (2016), 472--488. In European Conference on Computer Vision.Google Scholar
- M. Danelljan, G. Bhat, F. S. Khan, and M. Felsberg. 2017. Eco: Efficient convolution operators for tracking. (2017), 21--26. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.Google Scholar
- Martin Danelljan, Hager Gustav, Fahad Shahbaz Khan, and Michael Felsberg. 2015. Learning spatially regularized correlation filters for visual tracking. (2015), 4310--4318. In Proceedings of the IEEE International Conference on Computer Vision.Google Scholar
- Martin Danelljan, Gustav Hager, Fahad Khan, and Michael Felsberg. 2014. Accurate scale estimation for robust visual tracking. (2014). In British Machine Vision Conference.Google ScholarCross Ref
- Martin Danelljan, Gustav Hager, Fahad Shahbaz Khan, and Michael Felsberg. 2015. Convolutional features for correlation filter based visual tracking. (2015), 58--66. In Proceedings of the IEEE International Conference on Computer Vision Workshops.Google ScholarDigital Library
- Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg, and Joost Van de Weijer. 2014. Adaptive color attributes for real-time visual tracking. (2014), 1090--1097. In Computer vision and pattern recognition (CVPR), IEEE Conference.Google Scholar
- Sam Hare, Golodetz Stuart, Saffari Amir, Vineet Vibhav, Cheng Ming-Ming, L. Hicks Stephen, and Philip HS Torr. 2016. truck: Structured output tracking with kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 10 (2016), 2096--2109.Google ScholarDigital Library
- JoÃčo F. Henriques, Rui Caseiro, Pedro Martins, and Jorge Batista. 2015. Highspeed tracking with kernelized correlation filters. IEEE Transactions on Circuits and Systems for Video Technology 37, 3 (2015), 583--596.Google Scholar
- Rui Caseiro Pedro Martins Henriques, JoÃčo F. and Jorge Batista. 2012. Exploiting the circulant structure of tracking-by-detection with kernels. (2012), 702--715. In European conference on computer vision, Springer.Google Scholar
- Dafei Huang, Luo Lei, Wen Mei, Chen Zhaoyun, and Zhang Chunyuan. 2015. Enable scale and aspect ratio adaptability in visual tracking with detection proposals. (2015), 185.1--185.12. Proceedings of the BMVC.Google Scholar
- Zdenek Kalal, Krystian Mikolajczyk, and Jiri Matas. 2012. Tracking-learning-detection. IEEE transactions on pattern analysis and machine intelligence 34, 7 (2012), 1409--1422.Google Scholar
- Matej Kristan, Matas Jiri, Leonardis Ales, Vojir Tomas, Pflugfelder Roman, Fernandez Gustavo, Nebehay Georg, Porikli Fatih, and Luka ÄŇehovin. 2016. A novel performance evaluation methodology for single-target trackers. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 11 (2016), 2137--2155.Google ScholarDigital Library
- Suha Kwak, Woonhyun Nam, Bohyung Han, and Joon Hee Han. 2011. Learning occlusion with likelihoods for visual tracking. (2011), 1551--1558. In Computer Vision (ICCV), IEEE International Conference.Google Scholar
- Junseok Kwon and Kyoung Mu Lee. 2011. Tracking by sampling trackers. (2011), 1195--1202. In Computer Vision (ICCV), IEEE International Conference.Google Scholar
- Ting Liu, Gang Wang, and Qingxiong Yang. 2015. Real-time part-based visual tracking via adaptive correlation filters. (2015). In Computer vision and pattern recognition (CVPR), IEEE Conference.Google Scholar
- Chao Ma, Yang Xiaokang, Zhang Chongyang, and Ming-Hsuan Yang. 2015. Long-term correlation tracking. (2015), 5388--5396. In Computer vision and pattern recognition (CVPR), IEEE Conference.Google Scholar
- Matthias Mueller, Smith Neil, and Bernard Ghanem. 2017. Context-aware correlation filter tracking. (2017), 1396--1404. In Proceedings of the IEEE International Conference on Computer Vision Workshops.Google Scholar
- Pedro Senna, Drummond Isabela, Neves, and Bastos Guilherme, Sousa. 2017. Realtime ensemble-based tracker with Kalman filter. (2017), 338--344. In Graphics, Patterns and Images (SIBGRAPI), 30th SIBGRAPI Conference.Google Scholar
- L. Sevilla-Lara and E Learned-Miller. 2012. Distribution fields for tracking. (2012), 1910--1917. In Computer Vision and Pattern Recognition (CVPR), IEEE Conference.Google Scholar
- Andres Solis, Montero, Lang Jochen, and Robert Laganiere. 2015. Scalable kernel correlation filter with sparse feature integration. (2015), 24--31. In Proceedings of the IEEE International Conference on Computer Vision Workshops.Google Scholar
- Chong Sun, Huchuan Lu, and Ming-Hsuan Yang. [n. d.]. Learning Spatial-Aware Regressions for Visual Tracking. ([n. d.]). arXiv preprint arXiv:1706.07457.Google Scholar
- Jack Valmadre, Bertinetto Luca, Henriques Joao, Vedaldi Andrea, and Philip HS Torr. 2017. End-to-end representation learning for correlation filter based tracking. (2017), 5000--5008. In Computer vision and pattern recognition (CVPR), IEEE Conference.Google Scholar
- Qing Wang, Feng Chen, Wenli Xu, and Ming-Hsuan Yang. 2015. Object tracking with joint optimization of representation and classification. IEEE Transactions on Circuits and Systems for Video Technology 25, 4 (2015), 638--650.Google ScholarDigital Library
- Xiaoyu Wang, Gang Hua, and Tony X. Han. 2010. Discriminative tracking by metric learning. (2010), 200--214. In European Conference on Computer Vision, Springer.Google Scholar
- Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. 2013. Online object tracking: A benchmark. (2013), 2411--2418. In Computer vision and pattern recognition (CVPR), IEEE Conference.Google Scholar
- Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. 2015. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 9 (2015), 1834--1848.Google ScholarDigital Library
Index Terms
- Bag of Visual Words based Correlation Filter Tracker (BoVW-CFT)
Recommendations
A visual tracker based on improved kernel correlation filter
ICIMCS '15: Proceedings of the 7th International Conference on Internet Multimedia Computing and ServiceRecently, Kernel Correlation Filter (KCF) is introduced into visual tracking, which has shown to provide the highest speed among the top ten trackers. However, the KCF tracker could not perfectly handle the occlusion during target's moving. Leading to ...
Correlation filter tracker with siamese: A robust and real-time object tracking framework
AbstractCorrelation filter (CF) based trackers have shown promising performance in object tracking. However, both the accuracy and efficiency of existing CF based trackers are limited. In this paper, we propose a robust and real-time object ...
Multipath Based Correlation Filter for Visual Object Tracking
Pattern Recognition and Machine IntelligenceAbstractThis paper presents a new correlation filter based visual object tracking method to improve the accuracy and robustness of trackers. Most of the current correlation filter based tracking methods often suffer in situations such as fast object ...
Comments