Feature Extraction Strategies Based on Mathematical Morphology for The Analysis Of Remotely Sensed Imagery

Abstract

The thesis evolves on the development of novel feature extraction methods for the newlineanalysis of remotely sensed images which are enabled to enhance the robustness and newlinethe generalization properties of the feature extraction system. Recent developments in newlineoptical data sensors mounted on-board of both space-borne and airborne earth newlineobservation platforms have led to increasing volume, acquisition speed and a variety of newlinesensed images. Therefore the feature extraction from remotely sensed imageries is a newlinemajor concern and challenge for the photogrammetry, remote sensing, and GIS newlinecommunities. The extensive survey of literatures expose the shortcomings overlooked newlinefor the existing approaches utilized in the feature extraction of remote sensing images. newlineThe automated extraction of features from the remotely sensed images has been an newlineactive area of research for over a decade due to its substantial role in several application newlineareas viz. urban planning, transportation navigation, traffic management, emergency newlinehandling, etc. Although the concept of feature extraction is relatively simple, the newlinereliability and accuracy remains a major challenge. newlineWith advanced imaging technologies, there is an augmented demand for developing newlinenew approaches which can exhaustively explore the information embedded in remote newlinesensing images. The past studies evidenced mathematical morphological tools as best newlinesuited for the potential exploitation of the spatial information in the remote sensing newlineimageries. Priorly, mathematical morphology was applied only for the interpretation of newlinebinary images. However, it was extended to analyze grey scale and colour images. The newlinethesis presents different spatial feature extraction methods which are developed based newlineon mathematical morphology for the analysis of remote sensing optical images newlineaddressing to different applications such as urban feature detection, waterbody newlineextraction, crop field boundary extraction and shoreline extraction.