Skip to main content

Research Repository

Advanced Search

Weakly Supervised Segmentation of SAR Imagery Using Superpixel and Hierarchically Adversarial CRF

Ma, Fei; Gao, Fei; Sun, Jinping; Zhou, Huiyu; Hussain, Amir

Authors

Fei Ma

Fei Gao

Jinping Sun

Huiyu Zhou



Abstract

Synthetic aperture radar (SAR) image segmentation aims at generating homogeneous regions from a pixel-based image and is the basis of image interpretation. However, most of the existing segmentation methods usually neglect the appearance and spatial consistency during feature extraction and also require a large number of training data. In addition, pixel-based processing cannot meet the real time requirement. We hereby present a weakly supervised algorithm to perform the task of segmentation for high-resolution SAR images. For effective segmentation, the input image is first over-segmented into a set of primitive superpixels. This algorithm combines hierarchical conditional generative adversarial nets (CGAN) and conditional random fields (CRF). The CGAN-based networks can leverage abundant unlabeled data learning parameters, reducing their reliance on the labeled samples. In order to preserve neighborhood consistency in the feature extraction stage, the hierarchical CGAN is composed of two sub-networks, which are employed to extract the information of the central superpixels and the corresponding background superpixels, respectively. Afterwards, CRF is utilized to perform label optimization using the concatenated features. Quantified experiments on an airborne SAR image dataset prove that the proposed method can effectively learn feature representations and achieve competitive accuracy to the state-of-the-art segmentation approaches. More specifically, our algorithm has a higher Cohen’s kappa coefficient and overall accuracy. Its computation time is less than the current mainstream pixel-level semantic segmentation networks.

Journal Article Type Article
Acceptance Date Feb 26, 2019
Online Publication Date Mar 2, 2019
Publication Date Mar 2, 2019
Deposit Date Jul 10, 2019
Publicly Available Date Jul 10, 2019
Journal Remote Sensing
Publisher MDPI
Peer Reviewed Peer Reviewed
Volume 11
Issue 5
Article Number 512
DOI https://doi.org/10.3390/rs11050512
Keywords synthetic aperture radar (SAR); segmentation; conditional random fields (CRF); conditional generative adversarial nets (CGAN); neighborhood consistency
Public URL http://researchrepository.napier.ac.uk/Output/1792052
Publisher URL http://doi.org/10.3390/rs11050512
Contract Date Jul 10, 2019

Files





You might also like



Downloadable Citations