2020
DOI: 10.1109/jstars.2019.2954850
|View full text |Cite
|
Sign up to set email alerts
|

OpenSARUrban: A Sentinel-1 SAR Image Dataset for Urban Interpretation

Abstract: The Sentinel-1 mission provides a freely accessible opportunity for urban image interpretation based on synthetic aperture radar (SAR) data with a specific resolution, which is of paramount importance for Earth observation. In parallel, with the rapid development of advanced technologies, especially deep learning, we urgently need a large-scale SAR dataset supporting urban image interpretation. This article presents OpenSARUrban: a Sentinel-1 dataset dedicated to the content-related interpretation of urban SAR… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
44
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
7
1

Relationship

2
6

Authors

Journals

citations
Cited by 43 publications
(44 citation statements)
references
References 59 publications
0
44
0
Order By: Relevance
“…Performance is, however, partially higher for Sentinel-1 HH+HV and Sentinel-2 combinations (>0.9; Table 4). It should be noted that previous studies (including [23,26,41,47,71]) have focused on VV+VH usage only in case of Sentinel-1 as this is the commonly available acquisition mode for IW over land.…”
Section: Target Classesmentioning
confidence: 99%
See 2 more Smart Citations
“…Performance is, however, partially higher for Sentinel-1 HH+HV and Sentinel-2 combinations (>0.9; Table 4). It should be noted that previous studies (including [23,26,41,47,71]) have focused on VV+VH usage only in case of Sentinel-1 as this is the commonly available acquisition mode for IW over land.…”
Section: Target Classesmentioning
confidence: 99%
“…Specifically, deep learning is expected to allow identification of human footprint-related features and to deal with ambiguities. A range of remote sensing studies, including in urban environments, exist for these approaches [40,41].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The Sentinel-1 dataset contains 33358 image patches of SAR urban targets, covering 21 major cities of China, with 10 categories, 2 polarization modes and 4 formats. [7] In this research, 300 patches are sampled from each class, regarding the 2 polarization mode, respectively.…”
Section: Datasetsmentioning
confidence: 99%
“…In the Sentinel-1 dataset, the number of classes varies from 5 to 10 specific to the image location and local urban structures. Zhao et al [3] presented the OpenSARUrban dataset for urban interpretation which covers areas of 21 major cities in China. There are 5 functional classes and a total of 10 classes in OpenSARUrban.…”
Section: Introductionmentioning
confidence: 99%