Deep Activation Feature Maps for Visual Object Tracking
Authors: 
Yang Li, Zhuang Miao, Jiabao WangAuthors Info & Claims
Yang Li, Zhuang Miao, Jiabao WangAuthors Info & ClaimsAbstract
Video object tracking is an important task with a broad range of applications. In this paper, we propose a novel visual tracking algorithm based on deep activation feature maps in correlation filter framework. Deep activation feature maps are generated from convolution neural network feature maps, which can discover the important part of the tracking target and overcome shape deformation and heavy occlusion. In addition, the scale variation is calculated by another correlation filter with histogram of oriented gradient (HoG) features. Moreover, we integrate the final tracking result in each frame based on the appearance model and scale model to further boost the overall tracking performance. We validate the effectiveness of our approach on a challenging benchmark, where the proposed method illustrates outstanding performance compared with the state-ofthe-art tracking algorithms
References
[1]
A. Geiger, M. Lauer, C. Wojek, C. Stiller, and R. Urtasun, "3D traffic scene understanding from movable platforms," IEEE Trans. Pattern Anal. Mach. Intell., vol.36, no.5, pp. 1012--1025, 2014.
[2]
Y. Wu, J. Lim, and M.-H. Yang, "Online object tracking: A benchmark," Proc. IEEE CVPR, Portland, Oregon, USA, pp. 2411--2418, Jun. 2013.
[3]
Y. Wu, J. Lim, and M.-H. Yang, "Object tracking benchmark," IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.9, pp. 1834--1848, 2015.
[4]
J. F. Henriques, R. Caseiro, P. Martins, and J. Batista, "High-speed tracking with kernelized correlation filters," IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.3, pp.583--596, Mar. 2015.
[5]
D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui, "Visual object tracking using adaptive correlation filters," Proc. IEEE CVPR, San Francisco, California, USA, pp.2544--2550, Jun. 2010.
[6]
N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," Proc. IEEE CVPR, San Diego, California, USA, pp. 886--893, Jun. 2005.
[7]
M. Danelljan, F. Shahbaz Khan, M. Felsberg, and J. van de Weijer, "Adaptive color attributes for real-time visual tracking," Proc. IEEE CVPR, Columbus, Ohio, USA, pp. 1090--1097, Jun. 2014.
[8]
Y. Li and J. Zhu, "A scale adaptive kernel correlation filter tracker with feature integration," Proc. ECCV, Zurich, Switzerland, pp. 254--265, Sept. 2014.
[9]
L. Wang, W. Ouyang, X. Wang, and H. Lu, "Visual tracking with fully convolutional networks," Proc. IEEE ICCV, Santiago, Chile, pp. 3119--3127, Dec. 2015.
[10]
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol.521, no.7553, pp. 436--444, May. 2015.
[11]
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," Proc. IEEE CVPR, Las Vegas, Nevada, USA, pp. 770--778, Jun. 2016.
[12]
J. Redmon, S.Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," Proc. IEEE CVPR, Las Vegas, Nevada, USA, pp. 779--788, Jun. 2016.
[13]
J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," Proc. IEEE CVPR, Boston, MA, USA, pp. 3431--3440, Jun. 2015.
[14]
C. Ma, J. Huang, X. Yang, and M.-H. Yang, "Hierarchical convolutional features for visual tracking," Proc. IEEE ICCV, Santiago, Chile, pp. 3074--3082, Dec. 2015.
[15]
M. Danelljan, G. Hager, F. Khan, and M. Felsberg, "Convolutional features for correlation filter based visual tracking," Proc. IEEE ICCV Workshop, Santiago, Chile, pp. 58--66, Dec. 2015.
[16]
M. Danelljan, G. Hager, F. Khan, and M. Felsberg, "Accurate scale estimation for robust visual tracking," Proc. BMVC, Nottingham, England, pp. 1--11, Sept. 2014.
[17]
Y. Xu, J. Wang, H. Li, Y. Li, Z. Miao, and Y. Zhang, "Patch-based scale calculation for real-time visual tracking," IEEE Signal Processing Letters, vol. 23, no. 1, pp. 40--44, Jan. 2016.
[18]
M. Oquab, L. Bottou, I. Laptev, and J. Sivic, "Is object localization for free? weakly-supervised learning with convolutional neural networks," Proc. IEEE CVPR, Boston, MA, USA, pp. 685--694, Jun. 2015.
[19]
G. Li and Y. Yu, "Deep contrast learning for salient object detection," Proc. IEEE CVPR, LasVegas, Nevada, USA, pp. 478--487, Jun. 2016.
[20]
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," Proc. ICLR, pp. 1--13, Apr. 2015.
[21]
J. Yang, D. Zhang, A. F. Frangi and J. Y. Yang, "Two-dimensional PCA: A new approach to appearance-based face representation and recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 26, no. 1, pp. 131--137, 2004.
[22]
C. Ma, X. Yang, C. Zhang, and M.-H. Yang, "Long-term correlation tracking," Proc. IEEE CVPR, Boston, MA, USA, pp. 5388--5396, Jun. 2015.
[23]
J. Henriques, R. Caseiro, P. Martins, and J. Batista, "Exploiting the circulant structure of tracking-by-detection with kernels," Proc. ECCV, Frienze, Italy, pp. 702--715, Oct. 2012.
[24]
Y. Li, Y. Zhang, Y. Xu, J. Wang and Z. Miao, "Robust scale adaptive kernel correlation filter tracker with hierarchical convolutional features," IEEE Signal Processing Letters, vol. 23, no. 8, pp. 1136--1140, Aug. 2016.
[25]
A. Vedaldi and K. Lenc, "MatConvNet: Convolutional neural networks for MATLAB," Proc. 23th Int. Conf. Multimed., pp.689--692, Oct. 2015.
[26]
S. Hare, A. Saffari, and P. H. S. Torr, "Struck: Structured output tracking with kernels," Proc. IEEE ICCV, Barcelona, Spain, pp. 263--270, Nov. 2011.
[27]
M. Danelljan, H. Gustav, F. Khan, and M. Felsberg, "Learning spatially regularized correlation filters for visual tracking," Proc. IEEE ICCV, Santiago, Chile, pp. 4310--4318, Dec. 2015.
[28]
J. Gao, H. Ling, W. Hu, and J. Xing, "Transfer learning based visual tracking with Gaussian processes regression," Proc. ECCV, Zurich, Switzerland, pp. 188--203, Sept. 2014.
[29]
Y. Li, J. Zhu, and S. C. H. Hoi, "Reliable patch trackers: Robust visual tracking by exploiting reliable patches," Proc. IEEE CVPR, Boston, MA, USA, pp. 353--361, Jun. 2015.
[30]
D. Wang and H. Lu, "Visual tracking via probability continuous outlier model," Proc. IEEE CVPR, Columbus, Ohio, USA, pp. 3478--3485, Jun. 2014.
Index Terms
- Deep Activation Feature Maps for Visual Object Tracking
Recommendations
Deep visual tracking
The first comprehensive survey on deep-learning-based trackers.Review existing deep visual trackers from three different perspectives.Large-scale benchmark evaluations of deep visual trackers.Summarize cutting-edge research works and discuss future ...
Robust Correlation Filter Tracking with Shepherded Instance-Aware Proposals
MM '18: Proceedings of the 26th ACM international conference on MultimediaIn recent years, convolutional neural network (CNN) based correlation filter trackers have achieved state-of-the-art results on the benchmark datasets. However, the CNN based correlation filters cannot effectively handle large scale variation and ...
Deep Location-Specific Tracking
MM '17: Proceedings of the 25th ACM international conference on MultimediaConvolutional Neural Network (CNN) based methods have shown significant performance gains in the problem of visual tracking in recent years. Due to many uncertain changes of objects online, such as abrupt motion, background clutter and large deformation, ...
Comments
Information & Contributors
Information
Published In
November 2018
177 pages
ISBN:9781450366052
DOI:10.1145/3297067
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: 28 November 2018
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
SPML '18
SPML '18: 2018 International Conference on Signal Processing and Machine Learning
November 28 - 30, 2018
Shanghai, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 68Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 02 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