Robust visual track using an ensemble cascade of convolutional neural networks

Dan Hu; Xingshe Zhou; Xiaohao Yu; Zhiqiang Hou

doi:10.1117/12.2228001

9 December 2015 Robust visual track using an ensemble cascade of convolutional neural networks

Dan Hu, Xingshe Zhou, Xiaohao Yu, Zhiqiang Hou

Proceedings Volume 9817, Seventh International Conference on Graphic and Image Processing (ICGIP 2015); 98170W (2015) https://doi.org/10.1117/12.2228001
Event: Seventh International Conference on Graphic and Image Processing, 2015, Singapore, Singapore

Abstract

Convolutional Neural Networks (CNN) have dramatically boosted the performance of various computer vision tasks except visual tracking due to the lack of training data. In this paper, we pre-train a deep CNN offline to classify the 1 million images from 256 classes with very leaky non-saturating neurons for training acceleration, which is transformed to a discriminative classifier by adding an additional classification layer. In addition, we propose a novel approach for combining increasingly our CNN classifiers in a “cascade” structure through a modification of the AdaBoost framework, and then transfer the selected discriminative features from the ensemble of CNN classifiers to the robust visual tracking task, by updating online to robustly discard the background regions from promising object-like region to cope with appearance changes of the target. Extensive experimental evaluations on an open tracker benchmark demonstrate outstanding performance of our tracker by improving tracking success rate and tracking precision on an average of 9.2% and 13.9% at least over other state-of-the-art trackers.

Citation Download Citation

Dan Hu, Xingshe Zhou, Xiaohao Yu, and Zhiqiang Hou "Robust visual track using an ensemble cascade of convolutional neural networks", Proc. SPIE 9817, Seventh International Conference on Graphic and Image Processing (ICGIP 2015), 98170W (9 December 2015); https://doi.org/10.1117/12.2228001

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
11 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Optical tracking

Video

Convolutional neural networks

Neurons

Visualization

Performance modeling

Detection and tracking algorithms

Show All Keywords

Keywords/Phrases

Search In:

Publication Years