Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier

Song Tang; Mao Ye; Ce Zhu; Yiguang Liu

doi:10.1117/1.JEI.26.1.013012

11 February 2017 Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier

Song Tang, Mao Ye, Ce Zhu, Yiguang Liu

Author Affiliations +

Journal of Electronic Imaging, Vol. 26, Issue 1, 013012 (February 2017). https://doi.org/10.1117/1.JEI.26.1.013012

Abstract

How to transfer the trained detector into the target scenarios has been an important topic for a long time in the field of computer vision. Unfortunately, most of the existing transfer methods need to keep source samples or label target samples in the detection phase. Therefore, they are difficult to apply to real applications. For this problem, we propose a framework that consists of a controlled convolutional neural network (CCNN) and a modulating neural network (MNN). In a CCNN, the parameters of the last layer, i.e., the classifier, are dynamically adjusted by a MNN. For each target sample, the CCNN adaptively generates a proprietary classifier. Our contributions include (1) the first detector-based unsupervised transfer method that is very suitable for real applications and (2) a new scheme of a dynamically adjusting classifier in which a new object function is invented. Experimental results confirm that our method can achieve state-of-the-art results on two pedestrian datasets.

Citation Download Citation

Song Tang, Mao Ye, Ce Zhu, and Yiguang Liu "Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier," Journal of Electronic Imaging 26(1), 013012 (11 February 2017). https://doi.org/10.1117/1.JEI.26.1.013012

Received: 13 November 2016; Accepted: 26 January 2017; Published: 11 February 2017

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