2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017
DOI: 10.1109/igarss.2017.8127520
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning for semantic segmentation of remote sensing images with rich spectral content

Abstract: With the rapid development of Remote Sensing acquisition techniques, there is a need to scale and improve processing tools to cope with the observed increase of both data volume and richness. Among popular techniques in remote sensing, Deep Learning gains increasing interest but depends on the quality of the training data. Therefore, this paper presents recent Deep Learning approaches for fine or coarse land cover semantic segmentation estimation. Various 2D architectures are tested and a new 3D model is intro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
12
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 19 publications
(12 citation statements)
references
References 13 publications
0
12
0
Order By: Relevance
“…Regarding the work on CNNs, several modifications have been proposed to increase their classification performance. A detailed overview of recent improvements to CNNs can be found in [25,26,27]. Next, we present and focus on the improvements that are relevant to our work.…”
Section: Related Workmentioning
confidence: 99%
“…Regarding the work on CNNs, several modifications have been proposed to increase their classification performance. A detailed overview of recent improvements to CNNs can be found in [25,26,27]. Next, we present and focus on the improvements that are relevant to our work.…”
Section: Related Workmentioning
confidence: 99%
“…In recent years, spectral data for earth surface classification has been a very active research area. Methods proposed by Kemker et al [11,20], Hamida et al [21], and López et al [18] use CNNs for RS-CNNMSI pixel-wise classification. Nevertheless, processing raw spectral data with deep learning (DL) algorithms is computationally very expensive.…”
Section: Related Workmentioning
confidence: 99%
“…However, it is difficult to classify the detail information accurately in RSIs since they contain a large amount of information. In this context, Deep Neural Network (DNN) appears as an appealing alternative to traditional shallow classification approaches to deal with such a massive amount of data [13]. The popular DNN models for semantic segmentation include SegNet, U-Net, DeepLab, FCN, etc.…”
Section: A Dnn-based Rsi Segmentationmentioning
confidence: 99%