Improved Semantic Segmentation of Water Bodies and Land in SAR Images Using Generative Adversarial Networks

Pai, Manohara M.M. and Mehrotra, Vaibhav and Verma, Ujwal and Pai, Radhika M (2020) Improved Semantic Segmentation of Water Bodies and Land in SAR Images Using Generative Adversarial Networks. International Journal of Sematic Computing, 14 (1). pp. 55-69. ISSN 1793-351X

[img] PDF
9561.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

The availability of computationally e±cient and powerful Deep Learning frameworks and high-resolution satellite imagery has created new approach for developing complex applications in the ¯eld of remote sensing. The easy access to abundant image data repository made available by di®erent satellites of space agencies such as Copernicus, Landsat, etc. has opened various avenues of research in monitoring the world's oceans, land, rivers, etc. The challenging research problem in this direction is the accurate identi¯cation and subsequent segmentation of surface water in images in the microwave spectrum. In the recent years, deep learning methods for semantic segmentation are the preferred choice given its high accuracy and ease of use. One major bottleneck in semantic segmentation pipelines is the manual annotation of data. This paper proposes Generative Adversarial Networks (GANs) on the training data (images and their corresponding labels) to create an enhanced dataset on which the networks can be trained, therefore, reducing human e®ort of manual labeling. Further, the research also proposes the use of deep-learning approaches such as U-Net and FCN-8 to perform an e±cient segmentation of auto annotated, enhanced data of water body and land. The experimental results show that the U-Net model without GAN achieves superior performance on SAR images with pixel accuracy

Item Type: Article
Uncontrolled Keywords: GANs; SAR images; semantic segmentation; U-net; deep learning
Subjects: Engineering > MIT Manipal > Electronics and Communication
Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 06 Oct 2020 09:46
Last Modified: 06 Oct 2020 09:46
URI: http://eprints.manipal.edu/id/eprint/155741

Actions (login required)

View Item View Item