SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model
Recently, Siamese network based trackers have been greatly developed and achieved state-of-the-art performance on multiple benchmarks. However, the decision-making mechanism needs to be studied more deeply in order to obtain higher accuracy. In this paper, we propose a novel Siamese network based vi...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8863912/ |
id |
doaj-1733486382eb4ec0863f18134806e5dc |
---|---|
record_format |
Article |
spelling |
doaj-1733486382eb4ec0863f18134806e5dc2021-03-30T00:56:10ZengIEEEIEEE Access2169-35362019-01-01714433914435310.1109/ACCESS.2019.29458468863912SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context ModelBo Huang0https://orcid.org/0000-0001-6734-5247Tingfa Xu1Shenwang Jiang2https://orcid.org/0000-0002-0914-4954Yu Bai3https://orcid.org/0000-0002-4100-8223Yiwen Chen4Image Engineering and Video Technology Lab, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaImage Engineering and Video Technology Lab, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaImage Engineering and Video Technology Lab, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaImage Engineering and Video Technology Lab, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaImage Engineering and Video Technology Lab, School of Optics and Photonics, Beijing Institute of Technology, Beijing, ChinaRecently, Siamese network based trackers have been greatly developed and achieved state-of-the-art performance on multiple benchmarks. However, the decision-making mechanism needs to be studied more deeply in order to obtain higher accuracy. In this paper, we propose a novel Siamese network based visual tracking method, which enhances decision-making ability by Spatially Constrained Correlation Filter (SCCF) and Saliency Prior Context (SPC) model. We use the deep features extracted from Siamese networks to train the SCCF via the efficient Alternating Direction Method of Multipliers (ADMM), and our SCCF applies a penalizing matrix to suppress the boundary effect well. Meanwhile, we regard the end-to-end output of Siamese networks as a priori probability and utilize the spatio-temporal relationship to establish the SPC model. The SPC model can handle the various cases of feature distributions generated from different targets and their contexts. Further, we also take measures to solve some challenging problems in visual tracking, such as target scale change and target occlusion. We conduct extensive experiments to demonstrate the effectiveness of the proposed method, which obtains currently the best results on three large tracking benchmarks, including OTB-2013, OTB-2015, and VOT-2016.https://ieeexplore.ieee.org/document/8863912/Siamese networkspatially constrained correlation filter (SCCF)saliency prior context (SPC) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bo Huang Tingfa Xu Shenwang Jiang Yu Bai Yiwen Chen |
spellingShingle |
Bo Huang Tingfa Xu Shenwang Jiang Yu Bai Yiwen Chen SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model IEEE Access Siamese network spatially constrained correlation filter (SCCF) saliency prior context (SPC) |
author_facet |
Bo Huang Tingfa Xu Shenwang Jiang Yu Bai Yiwen Chen |
author_sort |
Bo Huang |
title |
SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model |
title_short |
SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model |
title_full |
SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model |
title_fullStr |
SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model |
title_full_unstemmed |
SVTN: Siamese Visual Tracking Networks With Spatially Constrained Correlation Filter and Saliency Prior Context Model |
title_sort |
svtn: siamese visual tracking networks with spatially constrained correlation filter and saliency prior context model |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Recently, Siamese network based trackers have been greatly developed and achieved state-of-the-art performance on multiple benchmarks. However, the decision-making mechanism needs to be studied more deeply in order to obtain higher accuracy. In this paper, we propose a novel Siamese network based visual tracking method, which enhances decision-making ability by Spatially Constrained Correlation Filter (SCCF) and Saliency Prior Context (SPC) model. We use the deep features extracted from Siamese networks to train the SCCF via the efficient Alternating Direction Method of Multipliers (ADMM), and our SCCF applies a penalizing matrix to suppress the boundary effect well. Meanwhile, we regard the end-to-end output of Siamese networks as a priori probability and utilize the spatio-temporal relationship to establish the SPC model. The SPC model can handle the various cases of feature distributions generated from different targets and their contexts. Further, we also take measures to solve some challenging problems in visual tracking, such as target scale change and target occlusion. We conduct extensive experiments to demonstrate the effectiveness of the proposed method, which obtains currently the best results on three large tracking benchmarks, including OTB-2013, OTB-2015, and VOT-2016. |
topic |
Siamese network spatially constrained correlation filter (SCCF) saliency prior context (SPC) |
url |
https://ieeexplore.ieee.org/document/8863912/ |
work_keys_str_mv |
AT bohuang svtnsiamesevisualtrackingnetworkswithspatiallyconstrainedcorrelationfilterandsaliencypriorcontextmodel AT tingfaxu svtnsiamesevisualtrackingnetworkswithspatiallyconstrainedcorrelationfilterandsaliencypriorcontextmodel AT shenwangjiang svtnsiamesevisualtrackingnetworkswithspatiallyconstrainedcorrelationfilterandsaliencypriorcontextmodel AT yubai svtnsiamesevisualtrackingnetworkswithspatiallyconstrainedcorrelationfilterandsaliencypriorcontextmodel AT yiwenchen svtnsiamesevisualtrackingnetworkswithspatiallyconstrainedcorrelationfilterandsaliencypriorcontextmodel |
_version_ |
1724187557977128960 |