Abstract

The research provides a method for improving change detection in SAR images using a fusion object and a supervised classification system. To remove noise from the input image, we use the DnCNN denoising approach. The data from the first image is then processed with the mean ratio operator. The log ratio operator is used to process the second image. These two images are fused together using SWT-based image fusion, and the output is sent to a supervise classifier for change detection.

Highlights

  • Remote sensing-technology's most important application is identification of changes occurring on the surface of earth using multi-temporal remote sensing images

  • Change detection usually involves examining two co-registered remote sensing images that were collected at different time instances over the same geographic area

  • For a low-frequency band and a high-frequency band, SWT (Stationary Wavelet transform) fusion criteria based on an average operator and minimum local area

Read more

Summary

INTRODUCTION

Remote sensing-technology's most important application is identification of changes occurring on the surface of earth using multi-temporal remote sensing images. For categorising modified and unchanged regions in the fused difference image, an artificial neural network type multi layer perceptron or back propagation with feed forward network will be proposed This classifier belongs to the supervised segmentation category, and it operates on the basis of training cum classification. SWT (Stationary Wavelet transform)[20][21] fusion based on an average operator and minimum local area energy is performed in the third step, To restrict background information and improve the information of changed regions in the fused difference picture. The reference image is usually retrieved from a database and the second image processing is planed after a mark-able change[15]

PROPOSED TECHNIQUE
Findings
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call