An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images
Nowadays, real-time monitoring of highway operation by unmanned aerial vehicle (UAV) technology is one of the research frontiers for urban remote sensing. In general, the existing stitching algorithms can meet the basic requirements in terms of accuracy, but their splicing speed cannot meet the real...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10538363/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850219380245266432 |
|---|---|
| author | Haoxin Zheng Zhanqiang Chang Yakai Li Jie Zhu Wei Wang Qing Yang Chou Xie Jingfa Zhang Jiaxi Liu |
| author_facet | Haoxin Zheng Zhanqiang Chang Yakai Li Jie Zhu Wei Wang Qing Yang Chou Xie Jingfa Zhang Jiaxi Liu |
| author_sort | Haoxin Zheng |
| collection | DOAJ |
| description | Nowadays, real-time monitoring of highway operation by unmanned aerial vehicle (UAV) technology is one of the research frontiers for urban remote sensing. In general, the existing stitching algorithms can meet the basic requirements in terms of accuracy, but their splicing speed cannot meet the real-time stitching requirements of UAV. The cause is that the time consumption sharply increases when stitching plenty of UAV images—this is the bottleneck problem. Herein, we proposed a novel splicing method based on the Superpoint network and a self-designed algorithm of matrix iteration. In this method, we take advantage of an advanced deep learning algorithm—Superpoint to efficiently extract image feature points for calculating the geometric transformation matrix, and make the Superpoint model more suitable for highway. More importantly, for the purpose of further improving the stitching speed and realizing real-time stitching for a large number of UAV images, we specially designed an algorithm of matrix iteration to accurately represent the image transformation relationships, i.e., a matrix is iterated through each adjacent transformation matrix relationship. It is the first time that an algorithm of transformation matrix iteration has been designed to address the bottleneck problem in stitching plenty of UAV images. As a result, the experiments indicate that the proposed method has remarkably enhanced the stitching speed and accuracy for plenty of UAV images. Notably, even in the condition of no air triangulation parameters, it can realize real-time stitching. |
| format | Article |
| id | doaj-art-e9ea44badfda4f55862f0b54b33678e3 |
| institution | OA Journals |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-e9ea44badfda4f55862f0b54b33678e32025-08-20T02:07:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117104541046710.1109/JSTARS.2024.340322810538363An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV ImagesHaoxin Zheng0https://orcid.org/0009-0006-3978-5492Zhanqiang Chang1https://orcid.org/0000-0001-6820-4622Yakai Li2https://orcid.org/0009-0007-5160-8920Jie Zhu3https://orcid.org/0000-0002-4320-5503Wei Wang4https://orcid.org/0000-0002-8618-866XQing Yang5https://orcid.org/0009-0003-2139-6542Chou Xie6https://orcid.org/0000-0003-4788-1530Jingfa Zhang7https://orcid.org/0000-0002-1927-4672Jiaxi Liu8https://orcid.org/0009-0001-5591-2475College of Resource, Environment and Tourism, Capital Normal University, Beijing, ChinaCollege of Resource, Environment and Tourism, Capital Normal University, Beijing, ChinaCollege of Resource, Environment and Tourism, Capital Normal University, Beijing, ChinaChina Earthquake Networks Center, Beijing, ChinaHenan Institute of Remote Sensing and Surveying, Zhengzhou, ChinaChina Siwei Surveying and Mapping Technology Company, Ltd., Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaNational Institute of Natural Hazards, Beijing, ChinaCollege of Resource, Environment and Tourism, Capital Normal University, Beijing, ChinaNowadays, real-time monitoring of highway operation by unmanned aerial vehicle (UAV) technology is one of the research frontiers for urban remote sensing. In general, the existing stitching algorithms can meet the basic requirements in terms of accuracy, but their splicing speed cannot meet the real-time stitching requirements of UAV. The cause is that the time consumption sharply increases when stitching plenty of UAV images—this is the bottleneck problem. Herein, we proposed a novel splicing method based on the Superpoint network and a self-designed algorithm of matrix iteration. In this method, we take advantage of an advanced deep learning algorithm—Superpoint to efficiently extract image feature points for calculating the geometric transformation matrix, and make the Superpoint model more suitable for highway. More importantly, for the purpose of further improving the stitching speed and realizing real-time stitching for a large number of UAV images, we specially designed an algorithm of matrix iteration to accurately represent the image transformation relationships, i.e., a matrix is iterated through each adjacent transformation matrix relationship. It is the first time that an algorithm of transformation matrix iteration has been designed to address the bottleneck problem in stitching plenty of UAV images. As a result, the experiments indicate that the proposed method has remarkably enhanced the stitching speed and accuracy for plenty of UAV images. Notably, even in the condition of no air triangulation parameters, it can realize real-time stitching.https://ieeexplore.ieee.org/document/10538363/Image mosaicmatrix iterationreal-time stitchingunmanned aerial vehicle (UAV) |
| spellingShingle | Haoxin Zheng Zhanqiang Chang Yakai Li Jie Zhu Wei Wang Qing Yang Chou Xie Jingfa Zhang Jiaxi Liu An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Image mosaic matrix iteration real-time stitching unmanned aerial vehicle (UAV) |
| title | An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images |
| title_full | An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images |
| title_fullStr | An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images |
| title_full_unstemmed | An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images |
| title_short | An Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images |
| title_sort | efficient and fast image mosaic approach for highway panoramic uav images |
| topic | Image mosaic matrix iteration real-time stitching unmanned aerial vehicle (UAV) |
| url | https://ieeexplore.ieee.org/document/10538363/ |
| work_keys_str_mv | AT haoxinzheng anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT zhanqiangchang anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT yakaili anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jiezhu anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT weiwang anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT qingyang anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT chouxie anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jingfazhang anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jiaxiliu anefficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT haoxinzheng efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT zhanqiangchang efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT yakaili efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jiezhu efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT weiwang efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT qingyang efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT chouxie efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jingfazhang efficientandfastimagemosaicapproachforhighwaypanoramicuavimages AT jiaxiliu efficientandfastimagemosaicapproachforhighwaypanoramicuavimages |