For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Faster-ADNet for Visual Tracking
Tiansa ZHANG Chunlei HUO Zhiqiang ZHOU Bo WANG
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/03/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
visual tracking, deep learning, status re-identification,
Full Text: PDF(1.7MB)
>>Buy this Article
By taking advantages of deep learning and reinforcement learning, ADNet (Action Decision Network) outperforms other approaches. However, its speed and performance are still limited by factors such as unreliable confidence score estimation and redundant historical actions. To address the above limitations, a faster and more accurate approach named Faster-ADNet is proposed in this paper. By optimizing the tracking process via a status re-identification network, the proposed approach is more efficient and 6 times faster than ADNet. At the same time, the accuracy and stability are enhanced by historical actions removal. Experiments demonstrate the advantages of Faster-ADNet.