Abstract
Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF coefficients, which, inevitably, improves the tracking performance at the price of increasing complexity. To tackle online updating, SRDCF formulates its model on multiple training images, further adding difficulties in improving efficiency. In this work, by introducing temporal regularization to SRDCF with single sample, we present our spatial-temporal regularized correlation filters (STRCF). The STRCF formulation can not only serve as a reasonable approximation to SRDCF with multiple training samples, but also provide a more robust appearance model than SRDCF in the case of large appearance variations. Besides, it can be efficiently solved via the alternating direction method of multipliers (ADMM). By incorporating both temporal and spatial regularization, our STRCF can handle boundary effects without much loss in efficiency and achieve superior performance over SRDCF in terms of accuracy and speed. Compared with SRDCF, STRCF with hand-crafted features provides a 5Ã - speedup and achieves a gain of 5.4% and 3.6% AUC score on OTB-2015 and Temple-Color, respectively. Moreover, STRCF with deep features also performs favorably against state-of-the-art trackers and achieves an AUC score of 68.3% on OTB-2015.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 |
| Publisher | IEEE Computer Society |
| Pages | 4904-4913 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781538664209 |
| DOIs | |
| Publication status | Published - 2018 Dec 14 |
| Event | 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States Duration: 2018 Jun 18 → 2018 Jun 22 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Conference
| Conference | 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 |
|---|---|
| Country | United States |
| City | Salt Lake City |
| Period | 18/6/18 → 18/6/22 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
Cite this
}
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking. / Li, Feng; Tian, Cheng; Zuo, Wangmeng; Zhang, Lei; Yang, Ming Hsuan.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 4904-4913 8578613 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
AU - Li, Feng
AU - Tian, Cheng
AU - Zuo, Wangmeng
AU - Zhang, Lei
AU - Yang, Ming Hsuan
PY - 2018/12/14
Y1 - 2018/12/14
N2 - Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF coefficients, which, inevitably, improves the tracking performance at the price of increasing complexity. To tackle online updating, SRDCF formulates its model on multiple training images, further adding difficulties in improving efficiency. In this work, by introducing temporal regularization to SRDCF with single sample, we present our spatial-temporal regularized correlation filters (STRCF). The STRCF formulation can not only serve as a reasonable approximation to SRDCF with multiple training samples, but also provide a more robust appearance model than SRDCF in the case of large appearance variations. Besides, it can be efficiently solved via the alternating direction method of multipliers (ADMM). By incorporating both temporal and spatial regularization, our STRCF can handle boundary effects without much loss in efficiency and achieve superior performance over SRDCF in terms of accuracy and speed. Compared with SRDCF, STRCF with hand-crafted features provides a 5Ã - speedup and achieves a gain of 5.4% and 3.6% AUC score on OTB-2015 and Temple-Color, respectively. Moreover, STRCF with deep features also performs favorably against state-of-the-art trackers and achieves an AUC score of 68.3% on OTB-2015.
AB - Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF coefficients, which, inevitably, improves the tracking performance at the price of increasing complexity. To tackle online updating, SRDCF formulates its model on multiple training images, further adding difficulties in improving efficiency. In this work, by introducing temporal regularization to SRDCF with single sample, we present our spatial-temporal regularized correlation filters (STRCF). The STRCF formulation can not only serve as a reasonable approximation to SRDCF with multiple training samples, but also provide a more robust appearance model than SRDCF in the case of large appearance variations. Besides, it can be efficiently solved via the alternating direction method of multipliers (ADMM). By incorporating both temporal and spatial regularization, our STRCF can handle boundary effects without much loss in efficiency and achieve superior performance over SRDCF in terms of accuracy and speed. Compared with SRDCF, STRCF with hand-crafted features provides a 5Ã - speedup and achieves a gain of 5.4% and 3.6% AUC score on OTB-2015 and Temple-Color, respectively. Moreover, STRCF with deep features also performs favorably against state-of-the-art trackers and achieves an AUC score of 68.3% on OTB-2015.
UR - http://www.scopus.com/inward/record.url?scp=85056125315&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056125315&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00515
DO - 10.1109/CVPR.2018.00515
M3 - Conference contribution
AN - SCOPUS:85056125315
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 4904
EP - 4913
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
ER -