Continuous Multi-Angle Remote Sensing and Its Application in Urban Land Cover Classification

Because of the limitations hardware devices, such as sensors, processing capacity, and high accuracy altitude control equipment, traditional optical remote sensing (RS) imageries capture information regarding same scene from mostly one single angle or a very small number angles. Nowadays, with video satellites coming into service, obtaining more-or-less continuous array angles has become reality. In this paper, we analyze differences between RS data multi-angle (CMARS) data, unravel characteristics CMARS data. We study advantages using for classification try to capitalize on complementarity and, at time, reduce embedded redundancy. Our arguments are substantiated by real-life experiments employment in order classify urban land covers while support vector machine (SVM) classifier. They show superiority over classification. The overall may increase up about 9% Furthermore, investigate disadvantages directly how can be better utilized through extraction key features that characterize variations spectral reflectance along entire angular array. This research lay foundation use future applications.