| Autor: |
Chatziantoniou Andromachi, Topouzelis Konstantinos |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
IGARSS |
| DOI: |
10.1109/igarss47720.2021.9553174 |
| Popis: |
Biogenic oil films detected near aquaculture farms are thin surface films derived from organic substances. Similarly to oil spills, they are visible from SAR images due to the differentiation in sea surface roughness which affects the retractable radar signal. The algorithms used for the detection of oil slicks are based on adaptive thresholding methods to identify dark formations in the image. Two important parameters are responsible for the size of the dark spots that will be detected: the moving window size (w) and the threshold shift (k). Any alteration to the values of these parameters will lead to different results. The purpose of this study was to examine how different parameters affect the performance of the dark spot detection algorithm in SAR images. We used one Sentinel-1 image and examined 9 different combinations. Results exemplified the importance of choosing the appropriate parameters for the better performance of the algorithm. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
