Share Email Print
cover

Proceedings Paper

Ice flood detection based on pulse coupled neural network
Author(s): Xian-hong Liu; Zhi-bin Chen; Wei-ming Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

When ice run in the river course blocks the waterway severely, swelling will be speeded and of large scope, which will usually cause disasters. To judge the trend of ice flood and its disaster in the future, some data of ice flood, such as area, velocity and density, must be obtained timely. The velocity of ice flood can be got by analyzing the displacement and time interval of a same object in each image. The density of ice flood can be calculated from the ice area in a certain region. A precise area statistic of ice is the most important and difficult thing. In this paper, an edge extraction approach based on pulse coupled neural network is proposed to locate the edge of ice. Then, the area of ice can be obtained by the relativity between the ice and the region. The experimental results indicate that the method based on pulse coupled neural network is feasible. The extracted edge of the ice is distinct and continuous and the influence of noise on the infrared image is effectively eliminated.

Paper Details

Date Published: 11 September 2013
PDF: 6 pages
Proc. SPIE 8907, International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications, 89075E (11 September 2013); doi: 10.1117/12.2035006
Show Author Affiliations
Xian-hong Liu, Mechanical Engineering College (China)
Zhi-bin Chen, Mechanical Engineering College (China)
Wei-ming Wang, Mechanical Engineering College (China)


Published in SPIE Proceedings Vol. 8907:
International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications
Haimei Gong; Zelin Shi; Qian Chen; Jin Lu, Editor(s)

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