High-Order Multiple Kernelized Correlation Filter in Tensor for Visual Tracking
Article No.: 13, Pages 1 - 5
Abstract
Kernelized Correlation Filter has shown the unprecedented powerful discriminability of non-linear kernels. However, most of state-of-the-art methods ignore the interaction between channels and multi-kernel. Furthermore, the compressed kernel with simple summation operation may damage the feature information and degrade the online learning for visual tracking. Hence, we try to employ a novel method motivated by multivariate analysis via low rank tensor learning to enforce the local and global range interaction. We simplify our model and propose a high-order multi-kernel correlation filter (HOMKCF). Furthermore, the alternating direction method of multipliers (ADMM) algorithm is applied to implement the iteration and update of the model algorithm. Our novel tracker outperforms most state-of-the-art methods for precision and success rate in OTB and UAV benchmarks.
References
[1]
A.Bibi and B.Ghanem. 2017. High Order Tensor Formulation for Convolutional Sparse Coding. IEEE International Conference on Computer Vision (2017).
[2]
A.Mian. 2008. Realtime Visual Tracking of Aircrafts. Digital Image Computing: Techniques and Applications (2008).
[3]
A. Bibi and B. Ghanem. 2017. High Order Tensor Formulation for Convolutional Sparse Coding. 2017 IEEE International Conference on Computer Vision (ICCV) (2017).
[4]
D.Bolme, R.Beveridge, B.Draper, and Y.Lui. 2010. Visual object tracking using adaptive correlation filters. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2010).
[5]
G.Bleser and D.Strieker. 2009. Advanced tracking through efficient image processing and visual-inertial sensor fusion. 2008 IEEE Virtual Reality Conference (2009).
[6]
Chunming He, Kai Li, Guoxia Xu, Yulun Zhang, Runze Hu, Zhenhua Guo, and Xiu Li. 2023. Degradation-resistant unfolding network for heterogeneous image fusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 12611–12621.
[7]
Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. 2023. Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping. arXiv preprint arXiv:2305.11003 (2023).
[8]
H.Nam and B.Han. 2015. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).
[9]
J.F.Henriques, C.Rui, P.Martins, and J.Batista. 2012. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. in Computer Vision ECCV 2012 (2012).
[10]
J.F.Henriques, R.Caseiro, P.Martins, and J.Batista. 2015. High-Speed Tracking with Kernelized Correlation Filters. IEEE Transactions on Pattern Analysis and Machine Intelligence (2015).
[11]
J.Gao, J.Xing, W.Hu, and S.Maybank. 2013. Discriminant Tracking Using Tensor Representation with Semi-supervised Improvement. 2013 IEEE International Conference on Computer Vision (2013).
[12]
J.Pantrigo, J.Hernández, and A.Sánchez. 2009. Multiple and variable target visual tracking for video-surveillance applications. Pattern Recognition Letters (2009).
[13]
J.Zhang, S.Ma, and S.Sclaroff. 2014. MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization. European Conference on Computer Vision (2014).
[14]
K.Simonyan and A.Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science (2014).
[15]
L.Bertinetto, J.Valmadre, and J.F.Henriques. 2016. Fully-Convolutional Siamese Networks for Object Tracking. European Conference on Computer Vision (2016).
[16]
L.Bertinetto, J.Valmadre, and J.F.Henriques. 2016. Fully-Convolutional Siamese Networks for Object Tracking. European Conference on Computer Vision (2016).
[17]
L.Bertinetto, J.Valmadre, and S.Golodetz. 2016. Staple: Complementary Learners for Real-Time Tracking. Computer Vision and Pattern Recognition (2016).
[18]
Lianghua Huang and Bo Ma. 2015. Tensor pooling for online visual tracking. 2015 IEEE International Conference on Multimedia and Expo (ICME) (2015).
[19]
M.Danelljan, A.Robinson, and F.S.Khan. 2016. Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking. European Conference on Computer Vision (2016).
[20]
M.Danelljan, G.Bhat, F.Khan, and M.Felsberg. 2016. ECO: Efficient Convolution Operators for Tracking. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016).
[21]
M.Danelljan, G.Hager, F.Khan, and M.Felsberg. 2014. Accurate Scale Estimation for Robust Visual Tracking. British Machine Vision Conference (2014).
[22]
M.Danelljan, G.Häger, F.S.Khan, and M.Felsberg. 2015. Learning Spatially Regularized Correlation Filters for Visual Tracking. 2015 IEEE International Conference on Computer Vision (ICCV) (2015).
[23]
M.Danelljan, G.Häger, F.S.Khan, and M.Felsberg. 2016. Convolutional Features for Correlation Filter Based Visual Tracking. 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) (2016).
[24]
M.E.Kilmer and C.D.Martin. 2011. Factorization strategies for third-order tensors. Linear Algebra and Its Applications (2011).
[25]
M.E.Kilmer, K.Braman, N.Hao, and R.C.Hoover. 2013. Third-Order Tensors as Operators on Matrices: A Theoretical and Computational Framework with Applications in Imaging. Siam Journal on Matrix Analysis and Applications (2013).
[26]
S.Gladh, M.Danelljan, and F.S.Khan. 2016. Deep Motion Features for Visual Tracking. 23rd International Conference on Pattern Recognition (2016).
[27]
S.Hare, A.Saffari, and P.H.STorr. 2015. Struck: Structured Output Tracking with Kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence (2015).
[28]
T.Zhang, A.Bibi, and B.Ghanem. 2016. In Defense of Sparse Tracking: Circulant Sparse Tracker. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016).
[29]
W.Hu, J.Gao, J.Xing, C.Zhang, and S.Maybank. 2017. Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence (2017).
[30]
X.Jia, H.Lu, and M.Yang. 2012. Visual tracking via adaptive structural local sparse appearance model. 2012 IEEE Conference on Computer Vision and Pattern Recognition (2012).
[31]
X.Li, W.Hu, Z.Zhang, X.Zhang, and G.Luo. 2007. Robust Visual Tracking Based on Incremental Tensor Subspace Learning. 2007 IEEE 11th International Conference on Computer Vision (2007).
[32]
X.Mei and H.Ling. 2011. Robust Visual Tracking and Vehicle Classification via Sparse Representation. Pattern Analysis and Machine Intelligence, IEEE Transactions on (2011).
[33]
Guoxia Xu, Chunming He, Hao Wang, Hu Zhu, and Weiping Ding. 2023. DM-Fusion: Deep Model-Driven Network for Heterogeneous Image Fusion. IEEE Transactions on Neural Networks and Learning Systems (2023).
[34]
Guoxia Xu, Hao Wang, Meng Zhao, Marius Pedersen, and Hu Zhu. 2022. Learning the distribution-based temporal knowledge with low rank response reasoning for uav visual tracking. IEEE Transactions on Intelligent Transportation Systems (2022).
[35]
Y.Li and J.Zhu. 2014. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration. Computer Vision ECCV 2014 Workshops (2014).
[36]
Z.Hong, X.Mei, D.Prokhorov, and D.Tao. 2013. Tracking via Robust Multi-task Multi-view Joint Sparse Representation. 2013 IEEE International Conference on Computer Vision (2013).
[37]
Hu Zhu, Haopeng Ni, Shiming Liu, Guoxia Xu, and Lizhen Deng. 2020. Tnlrs: Target-aware non-local low-rank modeling with saliency filtering regularization for infrared small target detection. IEEE Transactions on Image Processing 29 (2020), 9546–9558.
[38]
Hu Zhu, Hao Peng, Guoxia Xu, Lizhen Deng, Yueying Cheng, and Aiguo Song. 2021. Bilateral weighted regression ranking model with spatial-temporal correlation filter for visual tracking. IEEE Transactions on Multimedia 24 (2021), 2098–2111.
Index Terms
- High-Order Multiple Kernelized Correlation Filter in Tensor for Visual Tracking
Recommendations
Learning spatial-channel regularization jointly with correlation filter for visual tracking
AbstractThe boundary effect of correlation filters is one key issue to limit the performance of visual tracking. Most existing methods focus on using regularization to constrain filters in the spatial domain, but less attention is paid to the ...
Improved kernelized correlation filter tracking by using spatial regularization
Highlights- We propose an efficient way to solve the spatial regularized regression formula.
- We propose a real-time tracking algorithm base on the correlation filter.
- The new algorithm achieves comparable performance and higher speed with ...
AbstractThe correlation filter based trackers have drawn much attention due to their encouraging performance on precision, robustness and speed. In this paper, we introduce the spatial regularization component into the ridge regression model used by ...
Robust visual tracking via co-trained Kernelized correlation filters
We train a pool of discriminative classifiers jointly in a closed-form fashion for visual tracking.We propose analytic model for datasets of thousands of translated patches.It is able to outperform the baseline by a larger margin. Recent advances in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
January 2024
506 pages
ISBN:9798400718199
DOI:10.1145/3653804
Copyright © 2024 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 the author(s) 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: 01 June 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
Conference
CVDL 2024
CVDL 2024: The International Conference on Computer Vision and Deep Learning
January 19 - 21, 2024
Changsha, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 12Total Downloads
- Downloads (Last 12 months)12
- Downloads (Last 6 weeks)4
Reflects downloads up to 14 Dec 2024
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 inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format