Hierarchical land cover information retrieval in object-oriented remote sensing image databases with native queries

Abstract

Classification and change detection of land cover types in the remotely sensed images is one of the major applications in remote sensing. This paper presents a hierarchical framework for land cover information storage and retrieval from object-oriented (OO) remote sensing image databases. Multi-spectral (band) remotely sensed images are classified by an optimized k-means clustering algorithm. The land cover maps are then decomposed and indexed with region quad-tree data structure stored in an OO database. Native queries (NQs), which use the semantics of the OO programming language for query composition, are developed to retrieve land cover distribution information and detect the changes of each land cover type at multi levels. A prototype system was implemented and the experiments were conducted on a time series Landsat Thematic Mapper (TM) images. The results show the effectiveness of the framework and the potentials in other remote sensing applications like urban planning and drought monitoring.

CIELab Color Moments: Alternative Descriptors for LANDSAT Images Classification System

“…The success value of image classification process is influenced by the suitability of the used features and the domain of images to be classified. In remote sensing images, spectral values are widely used for remote sensing images _______________ classification systems [1], [2], [3], [4], [5], [6], [7]. This is because the spectral values of different materials reflect and absorb differently at different wave lengths.…”