Content-Adaptive Multi-Region Deep Network for Polarimetric SAR Image Classification | IEEE Journals & Magazine | IEEE Xplore

Content-Adaptive Multi-Region Deep Network for Polarimetric SAR Image Classification


Abstract:

Deep learning methods excel in Polarimetric SAR (PolSAR) image classification. However, existing methods typically sample an image block for each pixel with a fixed-size ...Show More

Abstract:

Deep learning methods excel in Polarimetric SAR (PolSAR) image classification. However, existing methods typically sample an image block for each pixel with a fixed-size square window, which always contains inconsistent/incomplete content with the central pixel, resulting in many misclassifications especially in boundary and heterogeneous regions. So, a size-fixed square window is not enough for representing various terrain objects. To address this issue, we develop a content-adaptive multi-region deep network to obtain contextual consistent sampling windows for diverse terrain objects. Firstly, a complex scene of PolSAR image is partitioned into homogeneous, heterogeneous and boundary regions. Then, sampling windows with adaptive direction and scale are designed for three distinct regions. Besides, windows with central and global regions are proposed to provide additional local and global information. Finally, a fusion network is designed to adaptively combine different sampling windows to enhance classification performance. Experimental results on three real data sets demonstrate that the proposed method can achieve superior performance in both edge details and heterogeneous terrain objects compared with the state-of-the-art methods.
Page(s): 617 - 631
Date of Publication: 09 September 2024

ISSN Information:

Funding Agency:


I. Introduction

Polarimetric Synthetic Aperture Radar (PolSAR) is an active microwave imaging sensor capable of operating at day or night, and in all weather conditions. It acquires multidimensional measurements for continuous earth surface monitoring by transmitting microwave pulses with two different orthogonal polarization. Compared to traditional SAR, the PolSAR system can extract more extensive polarimetric information, encompassing horizontal polarization (H), vertical polarization (V), and oblique polarization (±45°). A wealth of multi-polarization data enhances the comprehensiveness of information sources for image interpretation. With these advantages, PolSAR images have found widespread applications in ground object classification [1], target recognition [2], change detection, and other fields. PolSAR image classification, which means to assign the certain class label to each pixel, is one of the most primary and essential task for further image interpretation. To exploit the benefits of PolSAR images effectively, researchers have devised numerous methods for PolSAR image classification.

References

References is not available for this document.