2022
DOI: 10.3390/w14142234
|View full text |Cite
|
Sign up to set email alerts
|

ECDSA-Based Water Bodies Prediction from Satellite Images with UNet

Abstract: The detection of water bodies from satellite images plays a vital role in research development. It has a wide range of applications such as the prediction of natural disasters and detecting drought and flood conditions. There were few existing applications that focused on detecting water bodies that are becoming extinct in nature. The dataset to train this deep learning model is taken from Kaggle. It has two classes, namely water bodies and masks. There is a total of 2841 sentinel-2 satellite images with corre… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
12
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 32 publications
(12 citation statements)
references
References 36 publications
0
12
0
Order By: Relevance
“…For instance, based on the U-Net model, Ch et al [19] achieved high-precision detection while ensuring model robustness by incorporating a secure feature elliptical digital signature algorithm module to generate digital signatures for the predicted water regions. In [20], a framework based on Attention U-Net and LinkNet ingeniously combines prior knowledge generated by numerical simulators to predict the maximum water levels of floods and the terrain deformations caused by floods and debris flows.…”
Section: Detection Methods Based On Deep Learningmentioning
confidence: 99%
“…For instance, based on the U-Net model, Ch et al [19] achieved high-precision detection while ensuring model robustness by incorporating a secure feature elliptical digital signature algorithm module to generate digital signatures for the predicted water regions. In [20], a framework based on Attention U-Net and LinkNet ingeniously combines prior knowledge generated by numerical simulators to predict the maximum water levels of floods and the terrain deformations caused by floods and debris flows.…”
Section: Detection Methods Based On Deep Learningmentioning
confidence: 99%
“…For the implementation, the model is built within the TensorFlow-Keras framework with the binary cross-entropy loss function 27 (for describing the inconsistency between actual values and model-predicted values) and the Nadam optimizer 28 (for determining the direction of parameter optimization).…”
Section: Deep Learning Processmentioning
confidence: 99%
“…In order to enhance the integrity of the predicted mask in the proposed deep learning model [34], the Elliptic Curve Digital Signature Algorithm (ECDSA) is applied. ECDSA is a cryptographic algorithm that offers advantages in terms of power and scalability compared to other algorithms like RSA [35].ECDSA utilizes keys derived from elliptic curve cryptography, which allows for shorter key lengths while achieving the same level of security as other digital signature algorithms.…”
Section: Ecdsamentioning
confidence: 99%