基于生成对抗网络的SAR图像水体和陆地的改进语义分割

M. Pai, Vaibhav Mehrotra, Ujjwal Verma, R. Pai
{"title":"基于生成对抗网络的SAR图像水体和陆地的改进语义分割","authors":"M. Pai, Vaibhav Mehrotra, Ujjwal Verma, R. Pai","doi":"10.1142/s1793351x20400036","DOIUrl":null,"url":null,"abstract":"The availability of computationally efficient and powerful Deep Learning frameworks and high-resolution satellite imagery has created new approach for developing complex applications in the field of remote sensing. The easy access to abundant image data repository made available by different 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 identification 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 effort of manual labeling. Further, the research also proposes the use of deep-learning approaches such as U-Net and FCN-8 to perform an efficient 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 of 0.98 and F1 score of 0.9923. However, when augmented with GANs, the results saw a rise in these metrics with PA of 0.99 and F1 score of 0.9954.","PeriodicalId":217956,"journal":{"name":"Int. J. Semantic Comput.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"22","resultStr":"{\"title\":\"Improved Semantic Segmentation of Water Bodies and Land in SAR Images Using Generative Adversarial Networks\",\"authors\":\"M. Pai, Vaibhav Mehrotra, Ujjwal Verma, R. Pai\",\"doi\":\"10.1142/s1793351x20400036\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The availability of computationally efficient and powerful Deep Learning frameworks and high-resolution satellite imagery has created new approach for developing complex applications in the field of remote sensing. The easy access to abundant image data repository made available by different 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 identification 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 effort of manual labeling. Further, the research also proposes the use of deep-learning approaches such as U-Net and FCN-8 to perform an efficient 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 of 0.98 and F1 score of 0.9923. However, when augmented with GANs, the results saw a rise in these metrics with PA of 0.99 and F1 score of 0.9954.\",\"PeriodicalId\":217956,\"journal\":{\"name\":\"Int. J. Semantic Comput.\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"22\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Int. J. Semantic Comput.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1142/s1793351x20400036\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Semantic Comput.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/s1793351x20400036","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 22

摘要

计算效率高且功能强大的深度学习框架和高分辨率卫星图像的可用性为开发遥感领域的复杂应用创造了新的方法。哥白尼、陆地卫星等空间机构的不同卫星提供了丰富的图像数据储存库,这为监测世界海洋、陆地、河流等开辟了各种研究途径。微波波谱图像中地表水的准确识别和后续分割是该方向研究的难点。近年来,由于深度学习方法具有较高的准确性和易用性,因此成为语义分割的首选方法。语义分割管道的一个主要瓶颈是数据的手工标注。本文提出了基于训练数据(图像及其相应标签)的生成对抗网络(GANs),以创建一个增强的数据集,从而可以在该数据集上训练网络,从而减少人工标记的工作量。此外,该研究还提出了使用U-Net和FCN-8等深度学习方法对水体和土地的自动注释增强数据进行有效分割。实验结果表明,不含GAN的U-Net模型在SAR图像上的像素精度为0.98,F1分数为0.9923,具有较好的性能。然而,当添加gan时,结果显示这些指标的PA值为0.99,F1值为0.9954。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Improved Semantic Segmentation of Water Bodies and Land in SAR Images Using Generative Adversarial Networks
The availability of computationally efficient and powerful Deep Learning frameworks and high-resolution satellite imagery has created new approach for developing complex applications in the field of remote sensing. The easy access to abundant image data repository made available by different 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 identification 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 effort of manual labeling. Further, the research also proposes the use of deep-learning approaches such as U-Net and FCN-8 to perform an efficient 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 of 0.98 and F1 score of 0.9923. However, when augmented with GANs, the results saw a rise in these metrics with PA of 0.99 and F1 score of 0.9954.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Guest Editorial - Special Issue on IEEE AIKE 2022 TemporalDedup: Domain-Independent Deduplication of Redundant and Errant Temporal Data Knowledge Graph-Based Explainable Artificial Intelligence for Business Process Analysis Knowledge Graph-Based Integration of Autonomous Driving Datasets Confidence-Based Cheat Detection Through Constrained Order Inference of Temporal Sequences
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1