Loading…
Impact of data augmentation on identifying water bodies in satellite images
Recognizing surface water is helpful in an assortment of remote sensing applications, the applications such as assessing the accessibility of water, estimating its adjustment of time, and anticipating dry seasons and floods. However, identifying surface water with old-style techniques is certainly n...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Recognizing surface water is helpful in an assortment of remote sensing applications, the applications such as assessing the accessibility of water, estimating its adjustment of time, and anticipating dry seasons and floods. However, identifying surface water with old-style techniques is certainly not an essential endeavour. Instead, distant identifying with expansive consideration and distinctive passing noticing is the most intelligent response for surface water checking. To Identify surface water efficiently, we developed a deep learning model that can process full Landsat Image inside a single shot without separating the contribution to tiles and increasing the model accuracy by applying data augmentation resulting in the model coming over a modified version of the original data in every case by using the data augmentation to the images and their identical masks. |
---|---|
ISSN: | 0094-243X 1551-7616 |
DOI: | 10.1063/5.0105731 |