A Fast Scale Adaptive Kernel Correlation Filter Tracker via Reliable Key Points
Article No.: 53, Pages 1 - 6
Abstract
Recently1, a class of method with correlation filtering for target tracking is one of the hottest methods in the tracking field. However, the performance of visual tracking still needs to be improved. Consequently, a scheme employing a key-point-based strategy to solve the multi-scale problem is proposed. An explicit scale filter is learned online using fore-and-backwards optical flow method which matches the reserved reliable points pairs at different scales. Moreover, these sparse pairs of tracked points are still adopted to discriminate occlusion. An extensive evaluation on OTB-2013 with 50 public test sequences was conducted. Experimental data and analysis indicate that our approach exceeds some other advanced tracking methods; there is a considerable improvement in speed. Additionally, our method can achieve more competitive performance even in the case where scale variation or partial occlusion occurs.
References
[1]
Hare, S., Saffari, A., and Torr, P. H. S. 2011. Struck: Structured output tracking with kernels. IEEE Transactions on Pattern Analysis & Machine Intelligence, 38(10), 2096--2109.
[2]
Henriques, J. F., Caseiro, R., Martins, P., and Batista, J. 2012. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. European Conference on Computer Vision. Springer, Berlin, Heidelberg, 702--715.
[3]
Henriques, J. F., Caseiro, R., Martins, P., and Batista, J. 2015. High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis & Machine Intelligence, 37(3), 583--596.
[4]
Kalal, Z., Mikolajczyk, K., and Matas, J. 2012. Tracking-Learning-Detection. IEEE Trans Pattern Anal Mach Intell, 34(7), 1409--1422.
[5]
Nebehay, G., and Pflugfelder, R. 2014. Consensus-based matching and tracking of keypoints for object tracking. IEEE, 2014, 862--869.
[6]
Leutenegger, S., Chli, M., and Siegwart, R. Y. 2012. BRISK: Binary Robust invariant scalable keypoints. IEEE International Conference on Computer Vision, 2548--2555.
[7]
Zhong, W., Lu, H., and Yang, M. H. 2012. Robust object tracking via sparsity-based collaborative model. IEEE Conference on Computer Vision and Pattern Recognition, 1838--1845.
[8]
Wu, Y., Lim, J., and Yang, M. H. 2013. Online Object Tracking: A Benchmark. IEEE Conference on Computer Vision and Pattern Recognition, 2411--2418.
[9]
Bolme, D. S., Beveridge, J. R., Draper, B. A., and Lui, Y. M. 2010. Visual object tracking using adaptive correlation filters. IEEE Computer Vision and Pattern Recognition, 2544--2550.
[10]
Li, Y. and Zhu, J. 2014. A scale adaptive kernel correlation filter tracker with feature integration{J}. 8926, 254--265.
[11]
Danelljan, M., Häger, G., Shahbaz Khan, F., and Felsberg, M. 2014. Accurate scale estimation for robust visual tracking. British Machine Vision Conference. 2014, 65.1--65.11.
[12]
Danelljan, M., Robinson, A., Khan, F. S., and Felsberg, M. 2016. Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking. European Conference on Computer Vision, Springer, Cham., 472--488.
[13]
Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., and Torr, P. H. S. 2016. Fully-convolutional siamese networks for object tracking{J}. 850--865.
Index Terms
- A Fast Scale Adaptive Kernel Correlation Filter Tracker via Reliable Key Points
Recommendations
A Kernel Correlation Filter Tracker with Fast Scale Prediction
ICMLC '20: Proceedings of the 2020 12th International Conference on Machine Learning and ComputingMost existing scale solutions of Correlation Filter-based trackers fail to consider the priority of target scale calculation. Their high complexity destroys the high speed performance of the tracking method. To tackle this problem, an optimization ...
Scale-adaptive tracking based on perceptual hash and correlation filter
In the research on computer vision, object tracking has encountered various challenges, such as occlusion and scale variation. In recent years, tracking-by-detection methods have performed competitively. Some of these methods have focused on solving the ...
Kernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues
Although the correlation filter-based trackers have achieved competitive results both on accuracy and robustness, the performance of trackers can still be improved because the most existing trackers either use a fixed scale or a sole filtering template ...
Comments
Information & Contributors
Information
Published In
October 2018
1083 pages
Copyright © 2018 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 22 October 2018
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CSAE '18
CSAE '18: The 2nd International Conference on Computer Science and Application Engineering
October 22 - 24, 2018
Hohhot, China
Acceptance Rates
CSAE '18 Paper Acceptance Rate 189 of 383 submissions, 49%;
Overall Acceptance Rate 368 of 770 submissions, 48%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 66Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in