Structural feature learning-based unsupervised semantic segmentation of synthetic aperture radar image

Fang Liu; Puhua Chen; Yuanjie Li; Licheng Jiao; Dashen Cui; Yuanhao Cui; Jing Gu

doi:10.1117/1.JRS.13.014501

11 January 2019 Structural feature learning-based unsupervised semantic segmentation of synthetic aperture radar image

Fang Liu, Puhua Chen, Yuanjie Li, Licheng Jiao, Dashen Cui, Yuanhao Cui, Jing Gu

Author Affiliations +

Funded by: National Natural Science Foundation of China (NSFC), National Natural Science Foundation of China, Natural Science Foundation of China, Program for Cheung Kong Scholars and Innovative Research Team in University, Program for Cheung Kong Scholars Innovative Research Team in University, University Research Teaching Programs (the 111 Project), University Research Teaching Programs, 111 project, Found for Foreign Scholars in University Research and Teaching programs (The 111 Project), Fund for Foreign Scholars in University Research and Teaching Programs, University Research and Teaching Programs, Fund for Foreign Scholars in University Research and Teaching Programs (the 111 Project), Foreign Scholars in University Research and Teaching Programs, Major Research Plan of the National Natural Science Foundation of China, China Postdoctoral Science Foundation Funded Project, China Post-Doctoral Science Foundation funded project, Fundamental Research Funds for the Central Universities, State Key Program of National Natural Science of China, Equipment Pre Research Field Foundation of China, Shaanxi Natural Science Foundation

Journal of Applied Remote Sensing, Vol. 13, Issue 1, 014501 (January 2019). https://doi.org/10.1117/1.JRS.13.014501

Abstract

Region map is the sparse representation of a high-resolution synthetic aperture radar (SAR) image on the middle-level semantic layer in its semantic space. Based on the semantic information of the region map, the high-resolution SAR image is divided into hybrid, structural, and homogeneous pixel subspaces. The segmentation of SAR images can be divided into these three subspaces segmentation, of which the segmentation of hybrid subspace has more challenge because of complex structures. There are often many extremely inhomogeneous areas in the hybrid pixel subspace. Are these nonconnected areas in the same or different classes? To solve this problem, a Bayesian learning model with the constraint of sketch characteristic and an initialization method is proposed to construct a structural vector that can reflect the essential features of each extremely inhomogeneous area. Then, the unsupervised segmentation of the hybrid pixel subspace can be realized by using the structural vectors of these areas in this paper. Theoretical analysis and experimental results show that the performance of the hybrid pixel subspace segmentation realized by the structural vectors based on the Bayesian learning model proposed in the paper is better than that only used by hand designing features.

Citation Download Citation

Fang Liu, Puhua Chen, Yuanjie Li, Licheng Jiao, Dashen Cui, Yuanhao Cui, and Jing Gu "Structural feature learning-based unsupervised semantic segmentation of synthetic aperture radar image," Journal of Applied Remote Sensing 13(1), 014501 (11 January 2019). https://doi.org/10.1117/1.JRS.13.014501

Received: 31 August 2018; Accepted: 10 December 2018; Published: 11 January 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE