Incrementally update CNN for visual tracking using active learning and artificial data

Yunqiu Lv; Kai Liu; Fei Cheng; Wei Li

doi:10.1117/12.2504317

29 October 2018 Incrementally update CNN for visual tracking using active learning and artificial data

Yunqiu Lv, Kai Liu, Fei Cheng, Wei Li

Proceedings Volume 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence; 1083610 (2018) https://doi.org/10.1117/12.2504317
Event: 2018 International Conference on Image, Video Processing and Artificial Intelligence, 2018, Shanghai, China

Abstract

Deep learning has been widely used in visual tracking due to strong feature extraction ability of convolutional neural network(CNN). Many trackers pre-train CNN primarily and fine-tune it during tracking, which could improve representation ability from off-line database and adjust to appearance variation of the interested object. However, since target information is limited, the network is likely to overfit to a single target state. In this paper, an update strategy composed of two modules is proposed. First, we fine-tune the pre-trained CNN using active learning that emphasizes the most discriminative data iteratively. Second, artificial convolutional features generated from empirical distribution are employed to train fully connected layers, which makes up the deficiency of training examples. Experiments evaluated on VOT2016 benchmark shows that our algorithm outperforms many state-of-the-art trackers.

Citation Download Citation

Yunqiu Lv, Kai Liu, Fei Cheng, and Wei Li "Incrementally update CNN for visual tracking using active learning and artificial data", Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 1083610 (29 October 2018); https://doi.org/10.1117/12.2504317

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Optical tracking

Detection and tracking algorithms

Convolution

Data modeling

Databases

Neural networks

Video

Show All Keywords

Keywords/Phrases

Search In:

Publication Years