الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 157 |  |  |
| | | from | 157 | | |
Abstract
Remote sensing satellite imagery plays an important role in extracting information, earth observation and knowledge of our environment with the help of various sensors. There are different types of sensors: passive, e.g. infrared and active, e.g. radars. This thesis focuses on passive sensors covering the visible and infrared bands, which are having different spectral and spatial resolutions. Therefore, image fusion, which merges images of different spatial and spectral resolutions, plays an important role in information extraction. Remote sensing image fusion is used to improve the quantitative analysis and facilitate image interpretation due to complementary information of different spectral and spatial resolution of data characteristics. There are major technical constraints like minimum data storage from a satellite platform in space, fewer bandwidth for communication with earth station etc. limits the satellite sensors from capturing images with high spatial and high spectral resolutions simultaneously. To overcome this limitation, image fusion has demonstrated to be a solution in remote sensing applications, which combine the information from panchromatic and multispectral images; propose to a single image which has higher spatial and multispectral resolutions. This thesis proposed only one image registration approach based on particle swarm optimization and mutual information. The proposed image registration approach was concluded that the image fusion accuracy depended on the image registration quality. Then, this thesis proposed five different remote sensing image fusion approaches, which covered different image fusion levels. First, remote sensing image fusion approach based on Brovey and wavelets transform. This approach reduced the spectral distortion in the Brovey transform and spatial distortion in the wavelet transform. The obtained results show that the proposed approach achieves less deflection and reduces the distortion. Second, the fusion of multispectral and panchromatic satellite images using principal component analysis and fuzzy logic approach, which provides trade-off solution between the spectral and spatial fidelity with preserves more detail in terms of spectral and spatial information. Third, region-based image fusion of panchromatic and multi-spectral images using stationary wavelet transform and marker controlled watershed segmentation. That is based on the stationary wavelet transform (SWT) in conjunction with marker-controlled watershed segmentation technique. The SWT is redundant, linear and shift invariant, and these properties allow SWT to be realized exploiting a recursive algorithm and give a better approximation than the DWT. Fourth, an adaptive image fusion rules for remote sensing images based on the particle swarm optimization. This approach proposes an adaptive remote sensing image fusion approach based on the particle swarm optimization (PSO) to get the optimum fused image. Finally, the flower pollination algorithm for multispectral (MS) and panchromatic (Pan) image fusion. This approach proposes MS and Pan image fusion based on the flower pollination algorithm optimization (FPA) approach. The FPA is a nature-inspired algorithm, based on the characteristics of flower pollination process. The proposed approach got more than 80% accuracy in spatial content.