By Topic

A Segmentation Method of Smoke in Forest-Fire Image Based on FBM and Region Growing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Xiaoli Wang ; Sch. of Electron. Eng., Heilongjiang Univ., Harbin, China ; Aiping Jiang ; Yingli Wang

A segmentation method of smoke in forest-fire image based on FBM and Region Growing is outlined in this paper. When segmenting forest fire images, some edges can't be segmented accurately. This method which will be introduced then can solve the foregoing problems. The specific practices include the following two steps. Firstly, threshold of Hurst parameter should be selected properly so as to get binary image after estimating the value of Hurst parameter. Secondly, the regions which are useful are extracted by using region growing method. Image segmentation based on fractal theory has good noise immunity, and detects various details of image. It is more significant for some images whose boundaries are irregular and complex. Traditional method is helpless for analyzing these images, while image segmentation method based on fractal can describe these images accurately. Therefore, this method based on FBM and Region Growing offers reliable data to the further image analysis and target recognition. It may achieve magnificent result.

Published in:

Chaos-Fractals Theories and Applications (IWCFTA), 2011 Fourth International Workshop on

Date of Conference:

19-22 Oct. 2011