SAR image segmentation for land cover change detection
Authors:
- 1 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1-6
Abstract
Synthetic aperture radar is used for land cover change detection which can either be mounted on a drone or an aircraft, spacecraft. It can be used for land cover change detection by comparing two images which are taken at different intervals of time. For this we are using differencing methods. The operators used in differencing methods are log ratio and mean ratio. For obtaining a better difference in image. The image fusion technique is applied using complementary information obtained from log ratio and mean ratio differenced image then the image is segmented using k means clustering algorithms in which k centroids are placed as one for each cluster such that they are at maximum distance away from each other. The image obtained is compared with the ground truth, which has been already implemented. Now if the image is normal there is no change, and if the image is abnormal then the change has occurred during that time interval.Keywords
This publication has 22 references indexed in Scilit:
- Multitemporal Spaceborne SAR Data for Urban Change Detection in ChinaIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Multitemporal Image Change Detection Using a Detail-Enhancing Approach With Nonsubsampled Contourlet TransformIEEE Geoscience and Remote Sensing Letters, 2012
- A Context-Sensitive Technique Robust to Registration Noise for Change Detection in VHR Multispectral ImagesIEEE Transactions on Image Processing, 2010
- Change Detection in Satellite Images Using a Genetic Algorithm ApproachIEEE Geoscience and Remote Sensing Letters, 2010
- Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means ClusteringIEEE Geoscience and Remote Sensing Letters, 2009
- The Nonsubsampled Contourlet Transform: Theory, Design, and ApplicationsIEEE Transactions on Image Processing, 2006
- The contourlet transform: an efficient directional multiresolution image representationIEEE Transactions on Image Processing, 2005
- Survey over image thresholding techniques and quantitative performance evaluationJournal of Electronic Imaging, 2004
- Spatially adaptive wavelet thresholding with context modeling for image denoisingIEEE Transactions on Image Processing, 2000
- Change detection techniques for ERS-1 SAR dataIEEE Transactions on Geoscience and Remote Sensing, 1993