A new computer vision algorithm for classification of POLSAR images

Abstract

Extracting good representations from POLSAR images is essential for many computer vision tasks. In this paper, we propose hierarchical matching pursuit (HMP), which builds a feature hierarchy layer-by-layer using an efficient matching pursuit encoder. The algorithm proposed in this paper, was applied on a POLSAR image and the result demonstrates that the extracted features using the proposed computer vision algorithm is an effective and useful method for classification of POLSAR images.