{"title":"基于深度条件归一化流的多尺度超分辨率远程成像","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":"{\"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}","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}
Multiscale Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows
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.
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.