Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic
A low-altitude orthomosaic derived by an unmanned aerial vehicle (UAV) has been widely utilized for various purposes in large-scale infrastructure management. However, unwanted objects, such as cars and trucks, captured in the aerial images captured by the UAV have negative impacts on the quality of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843222002990 |
| _version_ | 1828293188933124096 |
|---|---|
| author | Jisoo Park Yong K. Cho Sungjin Kim |
| author_facet | Jisoo Park Yong K. Cho Sungjin Kim |
| author_sort | Jisoo Park |
| collection | DOAJ |
| description | A low-altitude orthomosaic derived by an unmanned aerial vehicle (UAV) has been widely utilized for various purposes in large-scale infrastructure management. However, unwanted objects, such as cars and trucks, captured in the aerial images captured by the UAV have negative impacts on the quality of orthomosaic. To this end, this study presented a novel method to remove the effect of unwanted objects on UAV-generated orthomosaic. The proposed method applied a deep learning-based image segmentation and inpainting algorithm to remove the vehicles from individual UAV images before processing structure from motion (SfM), and then it resulted in generateing an orthomosaic with the inpainted UAV images. To validate the proposed method, this study conducted a case study in actual highway environment and compared the performance of the proposed method with that of another method, which directly removes and inpaints vehicles from the final orthomosaic. Through comparison tests, it is shown that the proposed method is more effective than the other. The proposed automatic vehicle-free orthomosaic generation method can contribute to creating up-to-date immersive content for transportation infrastructure management. |
| first_indexed | 2024-04-13T11:19:13Z |
| format | Article |
| id | doaj.art-b9ae472fcb83403890ed6a2c4b9b2b7d |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-13T11:19:13Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-b9ae472fcb83403890ed6a2c4b9b2b7d2022-12-22T02:48:52ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322022-12-01115103111Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaicJisoo Park0Yong K. Cho1Sungjin Kim2Department of Built Environment, Indiana State University, Terre Haute, IN 47809, USASchool of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USADepartment of Architectural Engineering, Hanbat National University, 125 Dongseo-daero, S8-321, Yuseong-gu, Daejeon 34158, Republic of Korea; Corresponding author.A low-altitude orthomosaic derived by an unmanned aerial vehicle (UAV) has been widely utilized for various purposes in large-scale infrastructure management. However, unwanted objects, such as cars and trucks, captured in the aerial images captured by the UAV have negative impacts on the quality of orthomosaic. To this end, this study presented a novel method to remove the effect of unwanted objects on UAV-generated orthomosaic. The proposed method applied a deep learning-based image segmentation and inpainting algorithm to remove the vehicles from individual UAV images before processing structure from motion (SfM), and then it resulted in generateing an orthomosaic with the inpainted UAV images. To validate the proposed method, this study conducted a case study in actual highway environment and compared the performance of the proposed method with that of another method, which directly removes and inpaints vehicles from the final orthomosaic. Through comparison tests, it is shown that the proposed method is more effective than the other. The proposed automatic vehicle-free orthomosaic generation method can contribute to creating up-to-date immersive content for transportation infrastructure management.http://www.sciencedirect.com/science/article/pii/S1569843222002990Unmanned aerial vehicle (UAV)OrthomosaicImage segmentationImage inpaintingDeep learning |
| spellingShingle | Jisoo Park Yong K. Cho Sungjin Kim Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic International Journal of Applied Earth Observations and Geoinformation Unmanned aerial vehicle (UAV) Orthomosaic Image segmentation Image inpainting Deep learning |
| title | Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic |
| title_full | Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic |
| title_fullStr | Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic |
| title_full_unstemmed | Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic |
| title_short | Deep learning-based UAV image segmentation and inpainting for generating vehicle-free orthomosaic |
| title_sort | deep learning based uav image segmentation and inpainting for generating vehicle free orthomosaic |
| topic | Unmanned aerial vehicle (UAV) Orthomosaic Image segmentation Image inpainting Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843222002990 |
| work_keys_str_mv | AT jisoopark deeplearningbaseduavimagesegmentationandinpaintingforgeneratingvehiclefreeorthomosaic AT yongkcho deeplearningbaseduavimagesegmentationandinpaintingforgeneratingvehiclefreeorthomosaic AT sungjinkim deeplearningbaseduavimagesegmentationandinpaintingforgeneratingvehiclefreeorthomosaic |