A Comparative Analysis of Kernel-Based Methods for the Classification of Land Cover Maps in Satellite Imagery

摘要

This paper studies the impact of several learning issues in an image classification task with SVMs, such as rich feature-based representations, optimization and sensitivity to novelty in the test data sets. The employed imagery refers to the city of Rome, Italy and is acquired in different years and seasons by the European Remote Sensing Satellites ERS-1 and ERS-1/2 tandem mission. A comprehensive evaluation according to varying training conditions is reported, showing that SVMs provide robust and largely applicable tools.