Multiscale Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows

IF 1.3 4区 工程技术 Q2 ENGINEERING, AEROSPACE Journal of Aerospace Information Systems Pub Date : 2023-08-01 DOI:10.2514/1.i011089
Aneesh M. Heintz, Mason Peck, Ian Mackey
{"title":"Multiscale Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows","authors":"Aneesh M. Heintz, Mason Peck, Ian Mackey","doi":"10.2514/1.i011089","DOIUrl":null,"url":null,"abstract":"Many onboard vision tasks for spacecraft navigation require high-quality remote-sensing images with clearly decipherable features. However, design constraints and the operational and environmental conditions limit their quality. Enhancing images through postprocessing is a cost-efficient solution. Current deep learning methods that enhance low-resolution images through super-resolution do not quantify network uncertainty of predictions and are trained at a single scale, which hinders practical integration in image-acquisition pipelines. This work proposes performing multiscale super-resolution using a deep normalizing flow network for uncertainty-quantified and Monte Carlo estimates so that image enhancement for spacecraft vision tasks may be more robust and predictable. The proposed network architecture outperforms state-of-the-art super-resolution models on in-orbit lunar imagery data. Simulations demonstrate its viability on task-based evaluations for landmark identification.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"41 1","pages":"0"},"PeriodicalIF":1.3000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Aerospace Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2514/1.i011089","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}
引用次数: 0

Abstract

Many onboard vision tasks for spacecraft navigation require high-quality remote-sensing images with clearly decipherable features. However, design constraints and the operational and environmental conditions limit their quality. Enhancing images through postprocessing is a cost-efficient solution. Current deep learning methods that enhance low-resolution images through super-resolution do not quantify network uncertainty of predictions and are trained at a single scale, which hinders practical integration in image-acquisition pipelines. This work proposes performing multiscale super-resolution using a deep normalizing flow network for uncertainty-quantified and Monte Carlo estimates so that image enhancement for spacecraft vision tasks may be more robust and predictable. The proposed network architecture outperforms state-of-the-art super-resolution models on in-orbit lunar imagery data. Simulations demonstrate its viability on task-based evaluations for landmark identification.
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
基于深度条件归一化流的多尺度超分辨率远程成像
许多航天器导航的机载视觉任务需要具有清晰可解码特征的高质量遥感图像。然而,设计约束、操作条件和环境条件限制了它们的质量。通过后处理增强图像是一种经济有效的解决方案。目前通过超分辨率增强低分辨率图像的深度学习方法没有量化预测的网络不确定性,并且在单一尺度上进行训练,这阻碍了图像采集管道的实际集成。这项工作提出了使用深度归一化流网络进行不确定性量化和蒙特卡罗估计的多尺度超分辨率,以便航天器视觉任务的图像增强可能更加鲁棒和可预测。所提出的网络架构在在轨月球图像数据上优于最先进的超分辨率模型。仿真结果证明了该方法在基于任务的地标识别评价中的可行性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
3.70
自引率
13.30%
发文量
58
审稿时长
>12 weeks
期刊介绍: This Journal is devoted to the dissemination of original archival research papers describing new theoretical developments, novel applications, and case studies regarding advances in aerospace computing, information, and networks and communication systems that address aerospace-specific issues. Issues related to signal processing, electromagnetics, antenna theory, and the basic networking hardware transmission technologies of a network are not within the scope of this journal. Topics include aerospace systems and software engineering; verification and validation of embedded systems; the field known as ‘big data,’ data analytics, machine learning, and knowledge management for aerospace systems; human-automation interaction and systems health management for aerospace systems. Applications of autonomous systems, systems engineering principles, and safety and mission assurance are of particular interest. The Journal also features Technical Notes that discuss particular technical innovations or applications in the topics described above. Papers are also sought that rigorously review the results of recent research developments. In addition to original research papers and reviews, the journal publishes articles that review books, conferences, social media, and new educational modes applicable to the scope of the Journal.
期刊最新文献
New Type-2-Fuzzy-Logic-Based Control System for the Cessna Citation X Basic Engagement Zones Advanced Wavelet Transform-Based Automated System for Drone State Identification Using Radio-Frequency Signal Integration of the Functional Hazard Assessment Within a Model-Based Systems Engineering Framework Safe Spacecraft Inspection via Deep Reinforcement Learning and Discrete Control Barrier Functions
×
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