2022
DOI: 10.1109/access.2022.3150969
|View full text |Cite
|
Sign up to set email alerts
|

Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal

Abstract: Sea-ice identification is an essential process for safety critical navigation support of surface vessels in polar waters. Semantic segmentation has drawn much attention as an enabling technique for fast detection of objects in a scene including sea-ice conditions. Identifying sea-ice is a challenging problem, especially in the presence of raindrops. The raindrop alters the boundaries of the objects in the scene, and thus, degrades the identification performance. In this work, a raindrop removing framework is d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(2 citation statements)
references
References 29 publications
0
2
0
Order By: Relevance
“…In [131], an automated SIE algorithm was integrated into a mobile device. In [132], considering the impact of raindrops on the segmentation results of captured images, raindrop removal techniques were developed to improve the classification performance. In [133], a semantic segmentation model based on a conditional generative adversarial network (cGAN) was proposed.…”
Section: Supervised Learningmentioning
confidence: 99%
“…In [131], an automated SIE algorithm was integrated into a mobile device. In [132], considering the impact of raindrops on the segmentation results of captured images, raindrop removal techniques were developed to improve the classification performance. In [133], a semantic segmentation model based on a conditional generative adversarial network (cGAN) was proposed.…”
Section: Supervised Learningmentioning
confidence: 99%
“…For comparison, other classification models were trained using the training data of this paper, and the average accuracy of MSMN was found to be higher than that obtained from the model made using Convolutional Neural Networks (CNNs) and ResNet18 models. To improve classification performance, a framework for raindrop removal was introduced [123] . Images of sea ice are categorized into ice, water, ship and sky [86] , by training three deep learning semantic segmentation networks, they are VGG-16, FCN, and pyramid scene parsing network.…”
Section: Oceanography and Sea Ice Mappingmentioning
confidence: 99%