Share Email Print

Proceedings Paper

Infrared image synthesis for railway scene
Author(s): Zhaoyi Jiang; Xun Wang; Yun Ling
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Imaging guiding and machine vision in the infrared (IR) of military targets on land backgrounds are an extensively studied subject. The railway scene as an important traffic infrastructure usually plays a decisive role in land wars. Real IR images are expensive to obtain, and many researchers cannot afford them. The solution to this problem is generating realistic images at various conditions in computer. In this paper, a physics based model of infrared image synthesis for railway scene is proposed. A method for generating a thermal image of railway scene obtained by a forward-looking infrared (FLIR) sensor is described here. It consists of an integrated process based on thermal model of railway, atmospheric transmission and IR sensor effect. At first, a simple numeric model is proposed to calculate the temperature distribution of railway scene based on theoretical analysis of heat transfer. The typical structure of a railway can be divided into two main components. To simplify the thermal model, two parts of railway are processed independent. The distribution of track section temperature is considered in detail and not considered conduction along the track line. The ballast base is discretized into one-dimension multiple layers. Then we focus on the emissivtiy of steel track, which is a dominant factor in railway IR simulation. The value of emissivtiy is mainly determined by surface status of track. So the infrared radiation from track surface is calculated by Stephan-Boltzmann Law. Some results of synthesis image of railway scene in atmospheric window are shown finally. The generating images of railway are in good accordance with real images.

Paper Details

Date Published: 30 October 2009
PDF: 6 pages
Proc. SPIE 7494, MIPPR 2009: Multispectral Image Acquisition and Processing, 74940K (30 October 2009); doi: 10.1117/12.833161
Show Author Affiliations
Zhaoyi Jiang, Zhejiang Gongshang Univ. (China)
Xun Wang, Zhejiang Gongshang Univ. (China)
Yun Ling, Zhejiang Gongshang Univ. (China)

Published in SPIE Proceedings Vol. 7494:
MIPPR 2009: Multispectral Image Acquisition and Processing
Faxiong Zhang; Faxiong Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?