SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion
Optical image sequences of spacecraft acquired by space-based monocular cameras are typically imaged through exposure bracketing. The spacecraft feature deformable alignment network for multi-exposure image fusion (SFDA-MEF) aims to synthesize a High Dynamic Range (HDR) spacecraft image from a set o...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/199 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587594985111552 |
|---|---|
| author | Qianwen Xiong Xiaoyuan Ren Huanyu Yin Libing Jiang Canyu Wang Zhuang Wang |
| author_facet | Qianwen Xiong Xiaoyuan Ren Huanyu Yin Libing Jiang Canyu Wang Zhuang Wang |
| author_sort | Qianwen Xiong |
| collection | DOAJ |
| description | Optical image sequences of spacecraft acquired by space-based monocular cameras are typically imaged through exposure bracketing. The spacecraft feature deformable alignment network for multi-exposure image fusion (SFDA-MEF) aims to synthesize a High Dynamic Range (HDR) spacecraft image from a set of Low Dynamic Range (LDR) images with varying exposures. The HDR image contains details of the observed target in LDR images captured within a specific luminance range. The relative attitude of the spacecraft in the camera coordinate system undergoes continuous changes during the orbital rendezvous, which leads to a large proportion of moving pixels between adjacent frames. Concurrently, subsequent tasks of the In-Orbit Servicing (IOS) system, such as attitude estimation, are highly sensitive to variations in multi-view geometric relationships, which means that the fusion result should preserve the shape of the spacecraft with minimal distortion. However, traditional methods and unsupervised deep-learning methods always exhibit inherent limitations in dealing with complex overlapping regions. In addition, supervised methods are not suitable when ground truth data are scarce. Therefore, we propose an unsupervised learning framework for the multi-exposure fusion of optical spacecraft image sequences. We introduce a deformable convolution in the feature deformable alignment module and construct an alignment loss function to preserve its shape with minimal distortion. We also design a feature point extraction loss function to render our output more conducive to subsequent IOS tasks. Finally, we present a multi-exposure spacecraft image dataset. Subjective and objective experimental results validate the effectiveness of SFDA-MEF, especially in retaining the shape of the spacecraft. |
| format | Article |
| id | doaj-art-bd25a5fb37644ad183b5e66c469e3198 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-bd25a5fb37644ad183b5e66c469e31982025-01-24T13:47:42ZengMDPI AGRemote Sensing2072-42922025-01-0117219910.3390/rs17020199SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image FusionQianwen Xiong0Xiaoyuan Ren1Huanyu Yin2Libing Jiang3Canyu Wang4Zhuang Wang5College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaOptical image sequences of spacecraft acquired by space-based monocular cameras are typically imaged through exposure bracketing. The spacecraft feature deformable alignment network for multi-exposure image fusion (SFDA-MEF) aims to synthesize a High Dynamic Range (HDR) spacecraft image from a set of Low Dynamic Range (LDR) images with varying exposures. The HDR image contains details of the observed target in LDR images captured within a specific luminance range. The relative attitude of the spacecraft in the camera coordinate system undergoes continuous changes during the orbital rendezvous, which leads to a large proportion of moving pixels between adjacent frames. Concurrently, subsequent tasks of the In-Orbit Servicing (IOS) system, such as attitude estimation, are highly sensitive to variations in multi-view geometric relationships, which means that the fusion result should preserve the shape of the spacecraft with minimal distortion. However, traditional methods and unsupervised deep-learning methods always exhibit inherent limitations in dealing with complex overlapping regions. In addition, supervised methods are not suitable when ground truth data are scarce. Therefore, we propose an unsupervised learning framework for the multi-exposure fusion of optical spacecraft image sequences. We introduce a deformable convolution in the feature deformable alignment module and construct an alignment loss function to preserve its shape with minimal distortion. We also design a feature point extraction loss function to render our output more conducive to subsequent IOS tasks. Finally, we present a multi-exposure spacecraft image dataset. Subjective and objective experimental results validate the effectiveness of SFDA-MEF, especially in retaining the shape of the spacecraft.https://www.mdpi.com/2072-4292/17/2/199multi-exposure image fusionspacecraft optical imageunsupervised learningdynamic scenes |
| spellingShingle | Qianwen Xiong Xiaoyuan Ren Huanyu Yin Libing Jiang Canyu Wang Zhuang Wang SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion Remote Sensing multi-exposure image fusion spacecraft optical image unsupervised learning dynamic scenes |
| title | SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion |
| title_full | SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion |
| title_fullStr | SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion |
| title_full_unstemmed | SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion |
| title_short | SFDA-MEF: An Unsupervised Spacecraft Feature Deformable Alignment Network for Multi-Exposure Image Fusion |
| title_sort | sfda mef an unsupervised spacecraft feature deformable alignment network for multi exposure image fusion |
| topic | multi-exposure image fusion spacecraft optical image unsupervised learning dynamic scenes |
| url | https://www.mdpi.com/2072-4292/17/2/199 |
| work_keys_str_mv | AT qianwenxiong sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion AT xiaoyuanren sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion AT huanyuyin sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion AT libingjiang sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion AT canyuwang sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion AT zhuangwang sfdamefanunsupervisedspacecraftfeaturedeformablealignmentnetworkformultiexposureimagefusion |