Share Email Print

Journal of Electronic Imaging

Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier
Author(s): Song Tang; Mao Ye; Ce Zhu; Yiguang Liu
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 11 February 2017
PDF: 9 pages
J. Electron. Imag. 26(1) 013012 doi: 10.1117/1.JEI.26.1.013012
Published in: Journal of Electronic Imaging Volume 26, Issue 1
Show Author Affiliations
Song Tang, Univ. of Electronic Science and Technology of China (China)
Mao Ye, Univ. of Electronic Science and Technology of China (China)
Ce Zhu, Univ. of Electronic Science and Technology of China (China)
Yiguang Liu, Sichuan Univ. (China)

© SPIE. Terms of Use
Back to Top