High-dynamic-range imaging for cloud segmentation
Sky–cloud images obtained from ground-based sky cameras are usually captured using a fisheye lens with a wide field of view. However, the sky exhibits a large dynamic range in terms of luminance, more than a conventional camera can capture. It is thus difficult to capture the details of an entire sc...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/102675 http://hdl.handle.net/10220/50280 |
| _version_ | 1826109790618648576 |
|---|---|
| author | Dev, Soumyabrata Savoy, Florian M. Lee, Yee Hui Winkler, Stefan |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Dev, Soumyabrata Savoy, Florian M. Lee, Yee Hui Winkler, Stefan |
| author_sort | Dev, Soumyabrata |
| collection | NTU |
| description | Sky–cloud images obtained from ground-based sky cameras are usually captured using a fisheye lens with a wide field of view. However, the sky exhibits a large dynamic range in terms of luminance, more than a conventional camera can capture. It is thus difficult to capture the details of an entire scene with a regular camera in a single shot. In most cases, the circumsolar region is overexposed, and the regions near the horizon are underexposed. This renders cloud segmentation for such images difficult. In this paper, we propose HDRCloudSeg – an effective method for cloud segmentation using high-dynamic-range (HDR) imaging based on multi-exposure fusion. We describe the HDR image generation process and release a new database to the community for benchmarking. Our proposed approach is the first using HDR radiance maps for cloud segmentation and achieves very good results. |
| first_indexed | 2024-10-01T02:24:09Z |
| format | Journal Article |
| id | ntu-10356/102675 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:24:09Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/1026752020-03-07T14:00:34Z High-dynamic-range imaging for cloud segmentation Dev, Soumyabrata Savoy, Florian M. Lee, Yee Hui Winkler, Stefan School of Electrical and Electronic Engineering High-dynamic-range Imaging Cloud Segmentation Engineering::Electrical and electronic engineering Sky–cloud images obtained from ground-based sky cameras are usually captured using a fisheye lens with a wide field of view. However, the sky exhibits a large dynamic range in terms of luminance, more than a conventional camera can capture. It is thus difficult to capture the details of an entire scene with a regular camera in a single shot. In most cases, the circumsolar region is overexposed, and the regions near the horizon are underexposed. This renders cloud segmentation for such images difficult. In this paper, we propose HDRCloudSeg – an effective method for cloud segmentation using high-dynamic-range (HDR) imaging based on multi-exposure fusion. We describe the HDR image generation process and release a new database to the community for benchmarking. Our proposed approach is the first using HDR radiance maps for cloud segmentation and achieves very good results. Published version 2019-10-30T02:00:41Z 2019-12-06T20:58:52Z 2019-10-30T02:00:41Z 2019-12-06T20:58:52Z 2018 Journal Article Dev, S., Savoy, F. M., Lee, Y. H., & Winkler, S. (2018). High-dynamic-range imaging for cloud segmentation. Atmospheric Measurement Techniques, 11(4), 2041-2049. doi:10.5194/amt-11-2041-2018 1867-1381 https://hdl.handle.net/10356/102675 http://hdl.handle.net/10220/50280 10.5194/amt-11-2041-2018 en Atmospheric Measurement Techniques © 2018 The author(s). This work is distributed under the Creative Commons Attribution 3.0 License. 9 p. application/pdf |
| spellingShingle | High-dynamic-range Imaging Cloud Segmentation Engineering::Electrical and electronic engineering Dev, Soumyabrata Savoy, Florian M. Lee, Yee Hui Winkler, Stefan High-dynamic-range imaging for cloud segmentation |
| title | High-dynamic-range imaging for cloud segmentation |
| title_full | High-dynamic-range imaging for cloud segmentation |
| title_fullStr | High-dynamic-range imaging for cloud segmentation |
| title_full_unstemmed | High-dynamic-range imaging for cloud segmentation |
| title_short | High-dynamic-range imaging for cloud segmentation |
| title_sort | high dynamic range imaging for cloud segmentation |
| topic | High-dynamic-range Imaging Cloud Segmentation Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/102675 http://hdl.handle.net/10220/50280 |
| work_keys_str_mv | AT devsoumyabrata highdynamicrangeimagingforcloudsegmentation AT savoyflorianm highdynamicrangeimagingforcloudsegmentation AT leeyeehui highdynamicrangeimagingforcloudsegmentation AT winklerstefan highdynamicrangeimagingforcloudsegmentation |