View in EDS

Forest Change Detection Using an Optimized Convolution Neural Network.

Saved in:
Bibliographic Details
Title: Forest Change Detection Using an Optimized Convolution Neural Network.
Authors: Senthilkumar, Radha1 (AUTHOR) radhasenthil@annauniv.edu, Srinidhi, V.1 (AUTHOR) srinidhi.venky97@gmail.com, Neelavathi, S.1 (AUTHOR) neelas479@gmail.com, Renuga Devi, S.1 (AUTHOR) renugadevi22111997@gmail.com
Source: IETE Technical Review. Jan/Feb2022, Vol. 39 Issue 1, p135-142. 8p.
Subjects: Convolutional neural networks, Remote-sensing images, Forest degradation, Remote sensing, Forest monitoring
Abstract: Forest plays a pivotal role in maintaining the ecological balance. It is necessary to detect the changes in forest cover as the forests have a significant role in promoting carbon cycle. Remote sensing domain has shown a promising potential for monitoring forest degradation. However, the problem arising due to missing satellite images in temporal domain and problems due to artefacts such as clouds need to be addressed. To detect the changes in the forest area, an index for mapping forest cover known as Normalized Difference Fraction Index (NDFI) has been used. NDFI is calculated for three satellite images (Landsat7, Landsat8, and Sentinal2) and for the fusion of all these satellite images. Following this, the missing image is predicted by applying regression methods and the best regression method was identified. For change detection problem, optimal values for Convolution Neural Network (CNN) parameters were obtained using the Genetic Algorithm (GA). Later, various filters were applied for the optimal CNN and best filter was identified. [ABSTRACT FROM AUTHOR]
Copyright of IETE Technical Review is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Forest plays a pivotal role in maintaining the ecological balance. It is necessary to detect the changes in forest cover as the forests have a significant role in promoting carbon cycle. Remote sensing domain has shown a promising potential for monitoring forest degradation. However, the problem arising due to missing satellite images in temporal domain and problems due to artefacts such as clouds need to be addressed. To detect the changes in the forest area, an index for mapping forest cover known as Normalized Difference Fraction Index (NDFI) has been used. NDFI is calculated for three satellite images (Landsat7, Landsat8, and Sentinal2) and for the fusion of all these satellite images. Following this, the missing image is predicted by applying regression methods and the best regression method was identified. For change detection problem, optimal values for Convolution Neural Network (CNN) parameters were obtained using the Genetic Algorithm (GA). Later, various filters were applied for the optimal CNN and best filter was identified. [ABSTRACT FROM AUTHOR]
ISSN:02564602
DOI:10.1080/02564602.2020.1827987