Skip to main content
Journal cover image

Siamese network ensemble for visual tracking

Publication ,  Journal Article
Jiang, C; Xiao, J; Xie, Y; Tillo, T; Huang, K
Published in: Neurocomputing
January 31, 2018

Visual object tracking is a challenging task considering illumination variation, occlusion, rotation, deformation and other problems. In this paper, we extend a Siamese INstance search Tracker (SINT) with model updating mechanism to improve its tracking robustness. SINT uses convolutional neural network (CNN) features, and compares the new frame features with the target features in the first frame. The candidate region with the highest similarity score is considered as the tracking result. However, SINT is not robust against large target variation because the matching model is not updated during the whole tracking process. To combat this defect, we propose an Ensemble Siamese Tracker (EST), where the final similarity score is also affected by the similarity with tracking results in recent frames instead of solely considering the first frame. Tracking results in recent frames are used to adjust the model for continuous target change. Meanwhile, we combine large displacement optical flow method with EST to further improve the performance (called EST+). We test the proposed EST and EST+ on a standard tracking benchmark OTB. It turns out the average overlap ratio of EST and EST+ increase 2.72% and 3.55% respectively compared with SINT on OTB 2013, which contains 51 video sequences. For the OTB 100, the average overlap ratio gain is 4.2%.

Duke Scholars

Published In

Neurocomputing

DOI

EISSN

1872-8286

ISSN

0925-2312

Publication Date

January 31, 2018

Volume

275

Start / End Page

2892 / 2903

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 52 Psychology
  • 46 Information and computing sciences
  • 40 Engineering
  • 17 Psychology and Cognitive Sciences
  • 09 Engineering
  • 08 Information and Computing Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Jiang, C., Xiao, J., Xie, Y., Tillo, T., & Huang, K. (2018). Siamese network ensemble for visual tracking. Neurocomputing, 275, 2892–2903. https://doi.org/10.1016/j.neucom.2017.10.043
Jiang, C., J. Xiao, Y. Xie, T. Tillo, and K. Huang. “Siamese network ensemble for visual tracking.” Neurocomputing 275 (January 31, 2018): 2892–2903. https://doi.org/10.1016/j.neucom.2017.10.043.
Jiang C, Xiao J, Xie Y, Tillo T, Huang K. Siamese network ensemble for visual tracking. Neurocomputing. 2018 Jan 31;275:2892–903.
Jiang, C., et al. “Siamese network ensemble for visual tracking.” Neurocomputing, vol. 275, Jan. 2018, pp. 2892–903. Scopus, doi:10.1016/j.neucom.2017.10.043.
Jiang C, Xiao J, Xie Y, Tillo T, Huang K. Siamese network ensemble for visual tracking. Neurocomputing. 2018 Jan 31;275:2892–2903.
Journal cover image

Published In

Neurocomputing

DOI

EISSN

1872-8286

ISSN

0925-2312

Publication Date

January 31, 2018

Volume

275

Start / End Page

2892 / 2903

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 52 Psychology
  • 46 Information and computing sciences
  • 40 Engineering
  • 17 Psychology and Cognitive Sciences
  • 09 Engineering
  • 08 Information and Computing Sciences