A fuzzy logic approach to detect hotspots with NOAA/AVHRR image using multi-channel information fusion technique |
| |
Authors: | R S Gautam D Singh A Mittal |
| |
Affiliation: | (1) Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee, 247 667, India |
| |
Abstract: | This paper proposes a novel approach to detect hotspots using NOAA advanced very high resolution radiometer (AVHRR) for the
Jharia, Jharkhand (India) region. Jharia coalfield in Jharkhand is the richest coal bearing area in India that contains a
large number of mine fires which have been burning for several decades. In this paper, a fuzzy based methodology has been
applied for the determination of hotspots to Jharia AVHRR images based on a theoretical model that establishes relationship
among AVHRR channel 4, channel 5 and different vegetation indices. The algorithm consists of four stages: data preprocessing,
multi-channel information fusion, hotspot detection using fuzzy logic approach and validation of result. The most commonly
used existing algorithms like contextual algorithms, multi-thresholding, entropy based thresholding, and genetic algorithms
have limitation that they need some mathematical model for training in order to get the required result. The employed fuzzy
logic approach overcomes this requirement and in addition, it is flexible, tolerant of imprecise data and is based on natural
language. The results were compared with the results obtained by ground survey and a good agreement has been obtained between
observed and predicted hotspots. |
| |
Keywords: | Remote sensing Fuzzy logic Hotspot detection Multi-channel Fuzzy inference system Fuzzification NOAA advanced very high resolution radiometer (AVHRR) |
本文献已被 SpringerLink 等数据库收录! |
|