Preparing a new set of Data Using Synergy of PolSAR and Optical Derived Products for Map Updating
ISBN 978-85-88783-11-9
Authors
1Nasr, A.; 2Helmy, A.
1National Authority for Remote Sensing and Space Sciences Email: aymanasr@hotmail.com
2National Authority for Remote Sensing and Space Sciences Email: ashraf_khaled@hotmail.com
Abstract
A new approach to improve the feature extraction and map updating of part of Halayib area located in south eastern desert of Egypt, using multi-source data sets, is proposed in this paper. It investigates the potential of the joint use of the PolSAR and Optical derived data. Due to the different appearance of objects in PolSAR and Optical imagery, adapted methods have been developed. The approach is consisted of combining Radarsat-2 Pauli decomposition data, with ETM-8 principal component transformation based on a multichannel model of Pulse Coupled Neural Network (m-PCNN). We used bandlet bases to decompose the original images into a series of frequency, and then employed the m-PCNN to make the fusion decision. Bandlet transform takes advantage of the geometrical regularity of the image structure and represents sharp image transitions such as edges efficiently in the output image. The new results were evaluated using qualitative and quantitative measures. They demonstrate accurate spectral preservation, where PolSAR texture information enhances the fusion product. The proposed approach clearly state that, the combination of PolSAR and Optical derived data has potential to improve feature extraction and map updating in desert area.
Keywords
Map updating; Data Fusion; RADARSAT-2 and ETM-8 Data