Regular Articles

Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier

[+] Author Affiliations
Song Tang, Mao Ye, Ce Zhu

University of Electronic Science and Technology of China, School of Computer Science and Engineering, Center for Robotics, Key Laboratory for NeuroInformation of Ministry of Education, Chengdu, China

Yiguang Liu

Sichuan University, College of Computer Science, Chengdu, China

J. Electron. Imaging. 26(1), 013012 (Feb 11, 2017). doi:10.1117/1.JEI.26.1.013012
History: Received November 13, 2016; Accepted January 26, 2017
Text Size: A A A

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.

Figures in this Article
© 2017 SPIE and IS&T

Citation

Song Tang ; Mao Ye ; Ce Zhu and Yiguang Liu
"Adaptive pedestrian detection using convolutional neural network with dynamically adjusted classifier", J. Electron. Imaging. 26(1), 013012 (Feb 11, 2017). ; http://dx.doi.org/10.1117/1.JEI.26.1.013012


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.