OIL SPILL DETECTION TECHNIQUE WITH AUTOMATIC UPDATING USING DEEP LEARNING AND OIL SPILL INDEX
-
Title
- OIL SPILL DETECTION TECHNIQUE WITH AUTOMATIC UPDATING USING DEEP LEARNING AND OIL SPILL INDEX
-
Author(s)
- Shin, Dae Woon; Yang, Chan Su; Choi, Won Jun
- KIOST Author(s)
- Shin, Dae Woon(신대운); Yang, Chan Su(양찬수); Choi, Won Jun(최원준)
-
Alternative Author(s)
- 신대운; 양찬수; 최원준
-
Publication Year
- 2023-07-17
-
Abstract
- This paper presents a novel approach for detecting oil spills, employing two distinct methods.
The first method involves utilizing an Oil Spill Index (OSI) that analyzes spectral band information, while the second method utilizes a Deep Learning (DL) segmentation model.
The outcomes of both methods are then combined to generate training data, and this iterative process is repeated to update the oil spill DL model.
The training data used in this approach are obtained from multiple remote sensing platforms including optical and SAR satellite imagery.
By employing this proposed method, it is anticipated that high-quality and comprehensive training datasets will be generated, enabling the DL model to perform effectively.
-
ISSN
- 0000-0000
-
URI
- https://sciwatch.kiost.ac.kr/handle/2020.kiost/44443
-
Bibliographic Citation
- IGARSS 2023, pp.4019 - 4022, 2023
-
Publisher
- IEEE
-
Type
- Conference
-
Language
- English
- Files in This Item:
-
There are no files associated with this item.
Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.