Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries
Recently, analysis and decision-making based on spatiotemporal unmanned aerial vehicle (UAV) high-resolution imagery are gaining significant attention in smart agriculture. Constructing a spatiotemporal dataset requires multiple UAV image mosaics taken at different times. Because the weather or a UA...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/7/2/131 |
| _version_ | 1797621429371404288 |
|---|---|
| author | Hyeonseok Lee Semo Kim Dohun Lim Seoung-Hun Bae Lae-Hyong Kang Sungchan Kim |
| author_facet | Hyeonseok Lee Semo Kim Dohun Lim Seoung-Hun Bae Lae-Hyong Kang Sungchan Kim |
| author_sort | Hyeonseok Lee |
| collection | DOAJ |
| description | Recently, analysis and decision-making based on spatiotemporal unmanned aerial vehicle (UAV) high-resolution imagery are gaining significant attention in smart agriculture. Constructing a spatiotemporal dataset requires multiple UAV image mosaics taken at different times. Because the weather or a UAV flight trajectory is subject to change when the images are taken, the mosaics are typically unaligned. This paper proposes a two-step approach, composed of global and local alignments, for spatiotemporal alignment of two wide-area UAV mosaics of high resolution. The first step, global alignment, finds a projection matrix that initially maps keypoints in the source mosaic onto matched counterparts in the target mosaic. The next step, local alignment, refines the result of the global alignment. The proposed method splits input mosaics into patches and applies individual transformations to each patch to enhance the remaining local misalignments at patch level. Such independent local alignments may result in new artifacts at patch boundaries. The proposed method uses a simple yet effective technique to suppress those artifacts without harming the benefit of the local alignment. Extensive experiments validate the proposed method by using several datasets for highland fields and plains in South Korea. Compared with a recent work, the proposed method improves the accuracy of alignment by up to 13.21% over the datasets. |
| first_indexed | 2024-03-11T08:55:48Z |
| format | Article |
| id | doaj.art-481e58c2d3a245919474df763b9f684c |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-11T08:55:48Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-481e58c2d3a245919474df763b9f684c2023-11-16T20:07:03ZengMDPI AGDrones2504-446X2023-02-017213110.3390/drones7020131Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle ImageriesHyeonseok Lee0Semo Kim1Dohun Lim2Seoung-Hun Bae3Lae-Hyong Kang4Sungchan Kim5Department of Computer Science and Artificial Intelligence, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Mechatronics Engineering, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Computer Science and Artificial Intelligence, Jeonbuk National University, Jeonju 54896, Republic of KoreaSpatial Information Research Institute, Korea Land and Geospatial Informatix Corporation, Jeonju 54870, Republic of KoreaDepartment of Mechatronics Engineering, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Computer Science and Artificial Intelligence, Jeonbuk National University, Jeonju 54896, Republic of KoreaRecently, analysis and decision-making based on spatiotemporal unmanned aerial vehicle (UAV) high-resolution imagery are gaining significant attention in smart agriculture. Constructing a spatiotemporal dataset requires multiple UAV image mosaics taken at different times. Because the weather or a UAV flight trajectory is subject to change when the images are taken, the mosaics are typically unaligned. This paper proposes a two-step approach, composed of global and local alignments, for spatiotemporal alignment of two wide-area UAV mosaics of high resolution. The first step, global alignment, finds a projection matrix that initially maps keypoints in the source mosaic onto matched counterparts in the target mosaic. The next step, local alignment, refines the result of the global alignment. The proposed method splits input mosaics into patches and applies individual transformations to each patch to enhance the remaining local misalignments at patch level. Such independent local alignments may result in new artifacts at patch boundaries. The proposed method uses a simple yet effective technique to suppress those artifacts without harming the benefit of the local alignment. Extensive experiments validate the proposed method by using several datasets for highland fields and plains in South Korea. Compared with a recent work, the proposed method improves the accuracy of alignment by up to 13.21% over the datasets.https://www.mdpi.com/2504-446X/7/2/131unmanned aerial vehicle (UAV)spatiotemporal imageimage alignmentsmart agriculture |
| spellingShingle | Hyeonseok Lee Semo Kim Dohun Lim Seoung-Hun Bae Lae-Hyong Kang Sungchan Kim Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries Drones unmanned aerial vehicle (UAV) spatiotemporal image image alignment smart agriculture |
| title | Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries |
| title_full | Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries |
| title_fullStr | Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries |
| title_full_unstemmed | Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries |
| title_short | Two-Step Approach toward Alignment of Spatiotemporal Wide-Area Unmanned Aerial Vehicle Imageries |
| title_sort | two step approach toward alignment of spatiotemporal wide area unmanned aerial vehicle imageries |
| topic | unmanned aerial vehicle (UAV) spatiotemporal image image alignment smart agriculture |
| url | https://www.mdpi.com/2504-446X/7/2/131 |
| work_keys_str_mv | AT hyeonseoklee twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries AT semokim twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries AT dohunlim twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries AT seounghunbae twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries AT laehyongkang twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries AT sungchankim twostepapproachtowardalignmentofspatiotemporalwideareaunmannedaerialvehicleimageries |