|
|
Visual tracking using discriminative representation with ℓ2 regularization |
Haijun WANG1,2( ), Hongjuan GE1 |
1. College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China 2. Aviation Information Technology Research and Development Center, Binzhou University, Binzhou 256603, China |
|
|
Abstract In this paper, we propose a novel visual tracking method using a discriminative representation under a Bayesian framework. First, we exploit the histogram of gradient (HOG) to generate the texture features of the target templates and candidates. Second, we introduce a novel discriminative representation and ℓ2-regularized least squares method to solve the proposed representation model. The proposed model has a closed-form solution and very high computational efficiency. Third, a novel likelihood function and an update scheme considering the occlusion factor are adopted to improve the tracking performance of our proposed method. Both qualitative and quantitative evaluations on 15 challenging video sequences demonstrate that our method can achieve more robust tracking results in terms of the overlap rate and center location error.
|
Keywords
visual tracking
discriminative representation
Bayesian framework
closed-form solution
|
Corresponding Author(s):
Haijun WANG
|
Just Accepted Date: 20 January 2017
Online First Date: 06 March 2018
Issue Date: 31 January 2019
|
|
1 |
ALi, MLin, YWu, M HYang, S CYan. NUS-PRO: a new visual tracking challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 335–349
https://doi.org/10.1109/TPAMI.2015.2417577
|
2 |
YWu, JLim, M HYang. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834–1848
https://doi.org/10.1109/TPAMI.2014.2388226
|
3 |
K HZhang, LZhang, M HYang. Fast compressive tracking. IEEE Transations on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002–2015
https://doi.org/10.1109/TPAMI.2014.2315808
|
4 |
XLi, C HShen, ADick, A Hengel. Learning compact binary codes for visual tracking. In: Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2419–2426
https://doi.org/10.1109/CVPR.2013.313
|
5 |
K HZhang, LZhang, M HYang, Q H Hu. Robust object tracking via active feature selection. IEEE Transactions Circuits and Systems for Video Technology, 2013, 23(11): 1957–1967
https://doi.org/10.1109/TCSVT.2013.2269772
|
6 |
H HSong. Robust visual tracking via online informative feature selection. Electronics Letters, 2014, 50(25): 1931–1933.
https://doi.org/10.1049/el.2014.1911
|
7 |
BBabenko, M HYang, SBelongie. Visual tracking with online multiple instance learning. In: Proceedings of the 22nd IEEE Conference on Computer Vision and Pattern Recognition. 2009, 983–990
|
8 |
K HZhang, Q SLiu, YWu, M HYang. Robust visual tracking via convolutional networks without training. IEEE Transations on Image Processing, 2016, 25(4): 1779–1792
https://doi.org/10.1109/TIP.2016.2531283
|
9 |
JYan, XChen, D XDeng, Q P Zhu. Visual object tracking via online sparse instance learning. Journal of Visual Communication and Image Representation, 2015, 26: 231–246
https://doi.org/10.1016/j.jvcir.2014.11.013
|
10 |
K HZhang, LZhang, M HYang. Real-time object tracking via online discriminative feature selection. IEEE Transactions on Image Processing, 2013, 22(12): 4664–4677
https://doi.org/10.1109/TIP.2013.2277800
|
11 |
H HSong, Y HZheng, K HZhang. Robust visual tracking via selfsimilarity learning. Electronics Letters, 2017, 53(1): 20–22
https://doi.org/10.1049/el.2016.3011
|
12 |
XYang, MWang, L MZhang, F M Sun, R CHong, M BQi. An efficient tracking system by orthogonalized templates. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3187–3197
https://doi.org/10.1109/TIE.2016.2515559
|
13 |
DWang, H CLu, Z YXiao, M H Yang. Inverse sparse tracker with a locally weighted distance metric. IEEE Transactions on Image Processing, 2015, 24(9): 2646–2657
https://doi.org/10.1109/TIP.2015.2427518
|
14 |
DWang, H CLu. Online visual tracking via two view sparse representation. IEEE Signal Processing Letters, 2014, 21(9): 1031–1034
https://doi.org/10.1109/LSP.2014.2322389
|
15 |
Y HHan, YYang, YYan, Z G Ma, NSebe, X FZhou. Semisupervised feature selection via spline regression for video semantic recognition. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(2): 252–264
https://doi.org/10.1109/TNNLS.2014.2314123
|
16 |
Y HHan, FWu, QTian, Y T Zhuang. Image annotation by input-output structural grouping sparsity. IEEE Transactions on Image Processing, 2012, 21(6): 3066–3079
https://doi.org/10.1109/TIP.2012.2183880
|
17 |
JYang, D LChu, LZhang, Y Xu, J YYang. Sparse representation classifier steered discriminative projection with applications to face recognition. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(7): 1023–1035
https://doi.org/10.1109/TNNLS.2013.2249088
|
18 |
JWright, A YYang, AGanesh, S Sastry, YMa. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210–227
https://doi.org/10.1109/TPAMI.2008.79
|
19 |
B HZhuang, H CLu, Z YXiao, D Wang. Visual tracking via discriminative sparse similarity map. IEEE Transactions on Image Processing, 2014, 23(4): 1872–1881
https://doi.org/10.1109/TIP.2014.2308414
|
20 |
H WHu, BMa, Y DJia. Multi-task L0 gradient minimization for visual tracking. Neurocomputing, 2015, 154(22): 41–49
https://doi.org/10.1016/j.neucom.2014.12.021
|
21 |
J HYoon, M HYang, K JYoon. Interacting multiview tracker. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(5): 903–917
https://doi.org/10.1109/TPAMI.2015.2473862
|
22 |
J SPan, JLim, Z XSu, M H Yang. L0-regularized object representation for visual tracking. In: Proceedings of the British Machine Vision Conference. 2014, 1–12
https://doi.org/10.5244/C.28.29
|
23 |
BMa, J BShen, Y BLiu, H W Hu, LShao, X LLi. Visual tracking using strong classifier and structural local sparse descriptors. IEEE Transactions on Multimedia, 2015, 17(10): 1818–1828
https://doi.org/10.1109/TMM.2015.2463221
|
24 |
XMei, H BLing. Robust visual tracking using l1 minimization. In: Proceedings of the 12th IEEE International Conference on Computer Vision. 2009, 1436–1443
|
25 |
C LBao, YWu, H BLing, H Ji. Real time robust l1 tracker using accelerated proximal gradient approach. In: Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1830–1837
|
26 |
XJia, H CLu, M HYang. Visual tracking via coarse and fine structural local sparse appearance models. IEEE Transactions on Image Processing, 2016, 25(10): 4555–4564
https://doi.org/10.1109/TIP.2016.2592701
|
27 |
WZhong, H CLu, M HYang. Robust object tracking via sparse collaborative appearance model. IEEE Transactions on Image Processing, 2014, 23(5): 2356–2368
https://doi.org/10.1109/TIP.2014.2313227
|
28 |
DWang, H CLu, M HYang. Least soft-threshold squares tracking. In: Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2371–2378
https://doi.org/10.1109/CVPR.2013.307
|
29 |
Y WWu, J SYuan, P YTan, Y D Jia, JZhang. Robust distracterresistive tracker via learning a multi-component discriminative dictionary. IEEE Transactions on Image Processing, submitted.
|
30 |
DWang, H CLu, M HYang. Kernel collaborative face recognition. Pattern Recognition, 2015, 48(10): 3025–3237
https://doi.org/10.1016/j.patcog.2015.01.012
|
31 |
LZhang, M HYang, X CFeng. Sparse representation or collaborative representation: Which helps face recognition? In: Proceedings of the 13th IEEE International Conference on Computer Vision. 2011, 471–478
https://doi.org/10.1109/ICCV.2011.6126277
|
32 |
S JCai, LZhang, W MZuo, X C Feng. A probabilistic collaborative representation based approach for pattern classification. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2950–2959
https://doi.org/10.1109/CVPR.2016.322
|
33 |
S FShi, A Eriksson, AHengel, C HShen. Is face recognition really a compressive sensing problem? In: Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. 2011, 553–560
https://doi.org/10.1109/CVPR.2011.5995556
|
34 |
Z YXiao, H CLu, DWang. L2-RLS based object tracking. IEEE Transaction on Circuits and Systems for Video Technology, 2014, 24(8): 1301–1308
https://doi.org/10.1109/TCSVT.2013.2291355
|
35 |
NDalal, BTriggs. Histograms of oriented gradients for human detection. In: Proceedings of the 18th IEEE Conference on Computer Vision and Pattern Recognition. 2005, 886–893
https://doi.org/10.1109/CVPR.2005.177
|
36 |
JHenriques, R Caseiro, PMartins, JBatista. Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of the 12th European Conference on Computer Vision. 2012, 702–715
https://doi.org/10.1007/978-3-642-33765-9_50
|
37 |
YXu, Z FZhong, JYang, J You, DZhang. A new discriminative sparse representation method for robust face recognition via l2 regularization. IEEE Transactions on Neural Networks and Learning Systems, 2016, PP(99): 1–10
|
38 |
XJia, H CLu, M HYang. Visual tracking via adaptive structural local sparse appearance model. In: Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. 2012, 1822–1829
|
39 |
DWang, H CLu. On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization. Signal Processing, 2013, 93(6): 1608–1623
https://doi.org/10.1016/j.sigpro.2012.07.015
|
40 |
DWang, H CLu, M HYang. Online object tracking with sparse prototypes. IEEE Transactions on Image Processing, 2013, 22(1): 314–325
https://doi.org/10.1109/TIP.2012.2202677
|
41 |
DWang, H CLu. Visual tracking via probability continuous outlier model. In: Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition. 2014, 3478–3485
https://doi.org/10.1109/CVPR.2014.445
|
42 |
AAdam, ERivlin, IShimshoni. Robust fragments-based tracking using the integral histogram. In: Proceedings of the 19th IEEE Conference on Computer Vision and Pattern Recognition. 2006, 798–805
https://doi.org/10.1109/CVPR.2006.256
|
43 |
J SKwon, K MLee. Visual tracking decomposition. In: Proceedings of the 23rd IEEE Conference on Computer Vision and Pattern Recognition. 2010, 1269–1276
https://doi.org/10.1109/CVPR.2010.5539821
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|