Siamese Visual Tracking with Dual-Pipeline Correlated Fusion Network

Ying KANG  Cong LIU  Ning WANG  Dianxi SHI  Ning ZHOU  Mengmeng LI  Yunlong WU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E104-D    No.10    pp.1702-1711
Publication Date: 2021/10/01
Publicized: 2021/07/09
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2021EDP7060
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
visual tracking,  siamese network,  dual-pipeline correlation,  transient template,  fusion network,  adaptive selection,  

Full Text: PDF(2.6MB)>>
Buy this Article



Summary: 
Siamese visual tracking, viewed as a problem of max-similarity matching to the target template, has absorbed increasing attention in computer vision. However, it is a challenge for current Siamese trackers that the demands of balance between accuracy in real-time tracking and robustness in long-time tracking are hard to meet. This work proposes a new Siamese based tracker with a dual-pipeline correlated fusion network (named as ADF-SiamRPN), which consists of one initial template for robust correlation, and the other transient template with the ability of adaptive feature optimal selection for accurate correlation. By the promotion from the learnable correlation-response fusion network afterwards, we are in pursuit of the synthetical improvement of tracking performance. To compare the performance of ADF-SiamRPN with state-of-the-art trackers, we conduct lots of experiments on benchmarks like OTB100, UAV123, VOT2016, VOT2018, GOT-10k, LaSOT and TrackingNet. The experimental results of tracking demonstrate that ADF-SiamRPN outperforms all the compared trackers and achieves the best balance between accuracy and robustness.


open access publishing via