By Topic

An effective technique to detect forest fire region through ANFIS with spatial data

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

2 Author(s)
Angayarkkani, K. ; Dept. of Comput. Applic., D.G. Vaishnav Coll., Chennai, India ; Radhakrishnan, N.

Recently, spatial data mining plays a vital role because of its pressing need in the real world applications. Among the wide range of applications the nature disaster diagnosis is the most imperative and besides the other forest fire region mining through the spatial data is most imponderable. Forest fires are an increasing threat to the environment in both the tropical and boreal regions of the world. Hence the detection of fire regions of forest fires through the remote sensing images is most important. In this work, the forest fire region is detected through the spatial data in three phases, preprocessing phase, training phase and detection phase. Initially in the preprocessing phase, the remote sensing forest fire images are filtered through the unsharp filtering and then the image is converted to the CIEXYZ color space. Then the XYZ color spaced image is segmented through the anisotropic diffusion technique. After that the segmented regions are trained the Adaptive Neuro Fuzzy Inference System (ANFIS) in training phase. In the detection phase, the test image is tested in the trained ANFIS after the completion of preprocessing process and consequently the fire regions of the forest fire are detected. Hence the fire regions of forest image are identified and detected in an effective manner.

Published in:

Electronics Computer Technology (ICECT), 2011 3rd International Conference on  (Volume:3 )

Date of Conference:

8-10 April 2011