Paper Info
Title
Densely connected Siamese network visual tracking
Abstract
Purpose - Visual object tracking plays a significant role in intelligent robot systems. This study aims to focus on unlocking the tracking performance potential of the deep network and presenting a dynamic template update strategy for the Siamese trackers. Design/methodology/approach - This paper presents a novel and efficient Siamese architecture for visual object tracking which introduces densely connected convolutional layers and a dynamic template update strategy into Siamese tracker. Findings - The most advanced performance can be achieved by introducing densely connected convolutional neural networks that have not yet been applied to the tracking task into SiamRPN. By using the proposed architecture, the experimental results demonstrate that the performance of the proposed tracker is 5.8% (area under curve), 5.4% expected average overlap (EAO) and 3.5% (EAO) higher than the baseline on the OTB100, VOT2016 and VOT2018 data sets and achieves an excellent EAO score of 0.292 on the VOT2019 data set. Originality/value - This study explores a deeper backbone network with each convolutional network layer densely connected. In response to tracking errors caused by templates that are not updated, this study proposes a dynamic template update strategy.
Year
DOI
Venue
2021
10.1108/IR-01-2021-0010
INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION
Keywords
DocType
Volume
Robot vision, Artificial intelligence, Image processing, Object tracking, Siamese network, Dynamic template
Journal
48
Issue
ISSN
Citations 
5
0143-991X
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Xiaolong Zhou100.34
Pinghao Wang200.34
Sixian Chan3127.69
Kai Fang400.34
Jianwen Fang500.34