High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Iterative Technique for Image Change Detection Using SAR Images in Wsn


K.Gopalakrishnan , Nandha college of Technology,Erode; S.Hariprabha, Nandha college of Technology,Erode; C.kothainayaki, Nandha college of Technology,Erode; R.Lavanya, Nandha college of Technology,Erode; N.Nandhini, Nandha college of Technology,Erode


Satellite Images, Optical images, SAR Images, EM algorithm, Segmentation, EFCM algorithm


Satellite remote sensing imagery has been used to path changes on the Earth surface for applications including, plantation monitoring, and urban database updating. To achieve this, different sensors have been investigated including optical, synthetic aperture radars (SAR) or multi-spectral sensors. Optical sensors provide high resolution images due to the involved wavelengths. Remote sensing images are commonly used to monitor the earth surface evolution, this surveillance can be directed by perceiving changes between images acquired at different times and possibly by different kinds of sensors. A demonstrative case is when an optical image of a given area is available and a new image is acquired in an crisis situation (resulting from a natural disaster for instance) by a radar satellite. In such a case, images with heterogeneous properties have to be equated for change detection. This paper proposes a new approach for similarity measurement between images developed by heterogeneous sensors. The approach exploits the considered sensor physical properties and specially the associated measurement noise models and local joint distributions. These properties are inferred through manifold learning. The resulting similarity measure has been successfully applied to detect changes between many kinds of images, including pairs of optical images and pairs of optical-radar images. In addition, both low resolution and high resolution are taken for speckle noise removal with various thresholds and are taken for similarity measurement and image classification using Enhanced Fuzzy C-mean Clustering (EFCM) algorithm.

Other Details

Paper ID: IJSRDV4I10167
Published in: Volume : 4, Issue : 1
Publication Date: 01/04/2016
Page(s): 85-87

Article Preview

Download Article