Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling
This paper proposes a robust feature-based mosaicking method that can handle images obtained by lightweight unmanned aerial vehicles (UAVs). The imaging geometry of small UAVs can be characterized by unstable flight attitudes and low flight altitudes. These can reduce mosaicking performance by causi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/6/1002 |
| _version_ | 1819290966670966784 |
|---|---|
| author | Jae-In Kim Hyun-cheol Kim Taejung Kim |
| author_facet | Jae-In Kim Hyun-cheol Kim Taejung Kim |
| author_sort | Jae-In Kim |
| collection | DOAJ |
| description | This paper proposes a robust feature-based mosaicking method that can handle images obtained by lightweight unmanned aerial vehicles (UAVs). The imaging geometry of small UAVs can be characterized by unstable flight attitudes and low flight altitudes. These can reduce mosaicking performance by causing insufficient overlaps, tilted images, and biased tiepoint distributions. To solve these problems in the mosaicking process, we introduce the tiepoint area ratio (TAR) as a geometric stability indicator and orthogonality as an image deformation indicator. The proposed method estimates pairwise transformations with optimal transformation models derived by geometric stability analysis between adjacent images. It then estimates global transformations from optimal pairwise transformations that maximize geometric stability between adjacent images and minimize mosaic deformation. The valid criterion for the TAR in selecting an optimal transformation model was found to be about 0.3 from experiments with two independent image datasets. The results of a performance evaluation showed that the problems caused by the imaging geometry characteristics of small UAVs could actually occur in image datasets and showed that the proposed method could reliably produce image mosaics for image datasets obtained in both general and extreme imaging environments. |
| first_indexed | 2024-12-24T03:31:08Z |
| format | Article |
| id | doaj.art-3ed19d3d3af14c999b67ac60f1712820 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T03:31:08Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3ed19d3d3af14c999b67ac60f17128202022-12-21T17:17:11ZengMDPI AGRemote Sensing2072-42922020-03-01126100210.3390/rs12061002rs12061002Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation ModelingJae-In Kim0Hyun-cheol Kim1Taejung Kim2Unit of Arctic Sea-Ice Prediction, Korea Polar Research Institute (KOPRI), Incheon 21990, KoreaUnit of Arctic Sea-Ice Prediction, Korea Polar Research Institute (KOPRI), Incheon 21990, KoreaDepartment of Geoinformatic Engineering, Inha University, Incheon 21990, KoreaThis paper proposes a robust feature-based mosaicking method that can handle images obtained by lightweight unmanned aerial vehicles (UAVs). The imaging geometry of small UAVs can be characterized by unstable flight attitudes and low flight altitudes. These can reduce mosaicking performance by causing insufficient overlaps, tilted images, and biased tiepoint distributions. To solve these problems in the mosaicking process, we introduce the tiepoint area ratio (TAR) as a geometric stability indicator and orthogonality as an image deformation indicator. The proposed method estimates pairwise transformations with optimal transformation models derived by geometric stability analysis between adjacent images. It then estimates global transformations from optimal pairwise transformations that maximize geometric stability between adjacent images and minimize mosaic deformation. The valid criterion for the TAR in selecting an optimal transformation model was found to be about 0.3 from experiments with two independent image datasets. The results of a performance evaluation showed that the problems caused by the imaging geometry characteristics of small UAVs could actually occur in image datasets and showed that the proposed method could reliably produce image mosaics for image datasets obtained in both general and extreme imaging environments.https://www.mdpi.com/2072-4292/12/6/1002lightweight uavimage mosaicimaging geometrytiepoint area ratio |
| spellingShingle | Jae-In Kim Hyun-cheol Kim Taejung Kim Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling Remote Sensing lightweight uav image mosaic imaging geometry tiepoint area ratio |
| title | Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling |
| title_full | Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling |
| title_fullStr | Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling |
| title_full_unstemmed | Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling |
| title_short | Robust Mosaicking of Lightweight UAV Images Using Hybrid Image Transformation Modeling |
| title_sort | robust mosaicking of lightweight uav images using hybrid image transformation modeling |
| topic | lightweight uav image mosaic imaging geometry tiepoint area ratio |
| url | https://www.mdpi.com/2072-4292/12/6/1002 |
| work_keys_str_mv | AT jaeinkim robustmosaickingoflightweightuavimagesusinghybridimagetransformationmodeling AT hyuncheolkim robustmosaickingoflightweightuavimagesusinghybridimagetransformationmodeling AT taejungkim robustmosaickingoflightweightuavimagesusinghybridimagetransformationmodeling |