Attribute Learning for SAR Image Classification

Chu He,Mingsheng Liao,Xinlong Liu,Chenyao Kang,Dong Chen

doi:10.3390/ijgi6040111

Abstract

This paper presents a classification approach based on attribute learning for high spatial resolution Synthetic Aperture Radar (SAR) images. To explore the representative and discriminative attributes of SAR images, first, an iterative unsupervised algorithm is designed to cluster in the low-level feature space, where the maximum edge response and the ratio of mean-to-variance are included; a cross-validation step is applied to prevent overfitting. Second, the most discriminative clustering centers are sorted out to construct an attribute dictionary. By resorting to the attribute dictionary, a representation vector describing certain categories in the SAR image can be generated, which in turn is used to perform the classifying task. The experiments conducted on TerraSAR-X images indicate that those learned attributes have strong visual semantics, which are characterized by bright and dark spots, stripes, or their combinations. The classification method based on these learned attributes achieves better results.

Highlights

Synthetic Aperture Radar (SAR) is characterized by day-and-night and all-weather imaging ability in remote sensing; SAR images contain rich information on the imaged area, i.e., the dielectric and geometrical characteristics of the observed object are relevant to the backscattering [1]
The Bag-of-Word (BoW) model has been introduced for SAR image classification [14,15], which is inspired by the texton representation of an image, and this approach is based on the discriminative low-level features
High-level features extracted by the multi-layer model often lack semantics, and it is an intractable problem to directly establish a correspondence between the physical mechanisms of a SAR image and the semantics of the features at a high level

Summary

Introduction

Synthetic Aperture Radar (SAR) is characterized by day-and-night and all-weather imaging ability in remote sensing; SAR images contain rich information on the imaged area, i.e., the dielectric and geometrical characteristics of the observed object are relevant to the backscattering [1]. With improvements of SAR systems in terms of spatial resolution, high resolution SAR images can provide more detailed and precise information on an observed scene; for this reason, the application of SAR data is highly popular in earth observation [2]. It creates challenges in SAR image classification because of the more sophisticated shapes, structures and other details of the target. It would be highly desirable to interpret SAR images based on a multi-layer model with clear semantic attributes. High-level features extracted by the multi-layer model often lack semantics, and it is an intractable problem to directly establish a correspondence between the physical mechanisms of a SAR image and the semantics of the features at a high level

Objectives

Results

Conclusion