Nested Hyper-Rectangle Learning Model for Remote Sensing

Abstract

Listen

Translate article

This study presents an exemplar-based nested hyper-rectangle learning model (NHLM) which is an efficient and accurate supervised classification model. The proposed model is based on the concept of seeding training data in the Euclidean m-space (where m denotes the number of features) as hyper-rectangles. To express the exceptions, these hyper-rectangles may be nested inside one another to an arbitrary depth. The fast and one-shot learning procedures can adjust weights dynamically when new examples are added. Furthermore, the second chance heuristic is introduced in NHLM to avoid creating more memory objects than necessary. NHLM is applied to solving the land cover classification problem in Taiwan using remote sensed imagery. The study investigated five land cover classes and clouds. These six classes were chosen from field investigation of the study area according to previous study. Therefore, this paper aims to produce a land cover classification based on SPOT HRV spectral data. Compared with a standard back-propagation neural network (BPN), the experimental results indicate that NHLM provides a powerful tool for categorizing remote sensing data.