Open AccessDynamic Update Siamese Networks with Deeper Features
Author(s) -
Jianhao Tan,
Shanshan Tan,
Wang Yin,
Liming Li,
Siyuan Zhang,
Yaonan Wang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/790/1/012037
Subject(s) - fuse (electrical) , computer science , smoothing , feature (linguistics) , bittorrent tracker , artificial intelligence , computer vision , video tracking , field (mathematics) , tracking (education) , pattern recognition (psychology) , object (grammar) , eye tracking , engineering , mathematics , psychology , pedagogy , linguistics , philosophy , pure mathematics , electrical engineering
Visual object tracking has been a concern topic these years, and many trackers have achieved good results in various fields. These researches and breakthroughs have made many improvements to solve problems such as drift, lighting, deformation and occlusion. In this paper, we improve the structure of the AlexNet [1] network by designing the three important influencing factors of the receptive field size, total network step size, and feature filling of the twin network. Apart from this, we add a smoothing matrices and a background suppression matrices to effectively learn the features of the first few frames as much as possible. Fuse multilayer feature elements can learn online about target appearance changes and background suppression, and we train them by using continuous video sequences.