High-speed railway clearance surveillance system based on convolutional neural networks

Yang Wang; Zujun Yu; Liqiang Zhu; Baoqing Guo

doi:10.1117/12.2245128

29 August 2016 High-speed railway clearance surveillance system based on convolutional neural networks

Yang Wang, Zujun Yu, Liqiang Zhu, Baoqing Guo

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100335S (2016) https://doi.org/10.1117/12.2245128
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

In this paper, the convolutional neural networks with the pre-trained kernels are applied to the video surveillance system, which has been built along the Shanghai-Hangzhou high-speed railway to monitor the railway clearance scene and will output the alarm images with the dangerous intruding objects in. The video surveillance system will firstly generate the images which are suspected of containing the dangerous objects intruding the clearance. The convolutional neural networks with the pre-trained kernels are applied to process these suspicious images to eliminating the false alarm images, only contain the trains and the empty clearance scene, from other suspicious images before the final output. Experimental result shows that, the process of each test image only takes 0.16 second and has a high accuracy.

Citation Download Citation

Yang Wang, Zujun Yu, Liqiang Zhu, and Baoqing Guo "High-speed railway clearance surveillance system based on convolutional neural networks", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335S (29 August 2016); https://doi.org/10.1117/12.2245128

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