Paper
31 July 2019 PolSAR image classification based on complex-valued convolutional neural network and Markov random field
Author Affiliations +
Proceedings Volume 11198, Fourth International Workshop on Pattern Recognition; 111980B (2019) https://doi.org/10.1117/12.2540913
Event: Fourth International Workshop on Pattern Recognition, 2019, Nanjing, China
Abstract
Recently, a complex-valued convolutional neural network (CV-CNN) has been used for the classification of polarimetric synthetic aperture radar (PolSAR) images, and has shown superior performance to most traditional algorithms. However, it usually yields unreliable results for the pixels distributing within heterogeneous regions or the edge areas. To solve this problem, in this paper, an edge reassigning scheme based on Markov random field (MRF) is considered to combine with the CV-CNN. In this scheme,both the polarimetric statistical property and label context information are employed. The experiments performed on a benchmark PolSAR image of Flevoland has demonstrated the superior performance of the proposed algorithm.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xianxiang Qin, Wangsheng Yu, Peng Wang, Tianping Chen, and Huanxin Zou "PolSAR image classification based on complex-valued convolutional neural network and Markov random field", Proc. SPIE 11198, Fourth International Workshop on Pattern Recognition, 111980B (31 July 2019); https://doi.org/10.1117/12.2540913
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

Polarimetry

Convolutional neural networks

Magnetorheological finishing

Synthetic aperture radar

Buildings

Algorithm development

Back to Top