Water Across Synthetic Aperture Radar Data (WASARD): SAR Water Body Classification for the Open Data Cube

Kreiser, Zachary; Killough, Brian; Rizvi, S. R. H.

doi:10.1109/igarss.2018.8517447

Cited by 9 publications

(6 citation statements)

References 6 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Currently, the majority of known Data Cube implementations rely on optical imagery [9,12,13] and only a few of them offer access to SAR ARD products. One example of the use of SAR data in a Data Cube framework is the Water Across Synthetic Aperture Radar Data (WASARD) for water body classification [14]. Having SAR data in an Earth Observation Data Cube (EODC) can be an excellent complement to optical imagery and can overcome limitations such as cloud coverage.…”

Section: Introductionmentioning

confidence: 99%

Towards Sentinel-1 SAR Analysis-Ready Data: A Best Practices Assessment on Preparing Backscatter Data for the Cube

Truckenbrodt

Freemantle

Williams

et al. 2019

Data

View full text Add to dashboard Cite

This study aims at assessing the feasibility of automatically producing analysis-ready radiometrically terrain-corrected (RTC) Synthetic Aperture Radar (SAR) gamma nought backscatter data for ingestion into a data cube for use in a large spatio-temporal data environment. As such, this study investigates the analysis readiness of different openly available digital elevation models (DEMs) and the capability of the software solutions SNAP and GAMMA in terms of overall usability as well as backscatter data quality. To achieve this, the study builds on the Python library pyroSAR for providing the workflow implementation test bed and provides a Jupyter notebook for transparency and future reproducibility of performed analyses. Two test sites were selected, over the Alps and Fiji, to be able to assess regional differences and support the establishment of the Swiss and Common Sensing Open Data cubes respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Sentinel-1 SAR Analysis-Ready Data: A Best Practices Assessment on Preparing Backscatter Data for the Cube

Truckenbrodt

Freemantle

Williams

et al. 2019

Data

View full text Add to dashboard Cite

show abstract

“…In the same year, Klemenjak, S. et al [70] adapted and extended the method in their research [71], proposing a classification strategy that considers SVM as an unsupervised method, of which the premise is that the training samples are generated automatically. In 2018, Kreiser, Z. et al [72] described water across synthetic aperture radar data (WASARD), which utilized SVM to segment the water bodies automatically in Australia. In the end, WASARD has the ability to segment water bodies of interest with an accuracy of 97% with Geoscience Australia's Water Observations from Space (WOFS).…”

Section: Support Vector Machinementioning

confidence: 99%

Water-Body Segmentation for SAR Images: Past, Current, and Future

Guo

Huang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR), as a microwave sensor that can sense a target all day or night under all-weather conditions, is of great significance for detecting water resources, such as coastlines, lakes and rivers. This paper reviews literature published in the past 30 years in the field of water body extraction in SAR images, and makes some proposals that the community working with SAR image waterbody extraction should consider. Firstly, this review focuses on the main ideas and characteristics of traditional water body extraction on SAR images, mainly focusing on traditional Machine Learning (ML) methods. Secondly, how Deep Learning (DL) methods are applied and optimized in the task of water-body segmentation for SAR images is summarized from the two levels of pixel and image. We also pay more attention to the most popular networks, such as U-Net and its modified models, and novel networks, such as the Cascaded Fully-Convolutional Network (CFCN) and River-Net. In the end, an in-depth discussion is presented, along with conclusions and future trends, on the limitations and challenges of DL for water-body segmentation.

show abstract

“…SAR 위성영상에서 수체를 추출한 선행연구에는 1) 후방산란계수의 임계값에 근거해 수체와 비수체를 구분 한 연구가 대부분이었다 (Otsu, 1979;Matgen et al, 2011;Twele et al, 2016;Ahmad and Kim, 2019). 이 외에 2) 군집화 알고리즘에 근거한 방법 (Gan et al, 2012;Buono et al, 2017); 3) 다중 이미지 중첩 방법 (Brivio et al, 2002;Borah et al, 2018;Perrou et al, 2018); 그리고 4) 딥러닝에 기반한 방법 (Klemenjak et al, 2012;Kreiser et al, 2018;Lv et al, 2018;Pai et al, 2019) 등이 있었다.…”

Section: 서 론unclassified

Small- to Medium-Sized Stream Waterbody Extraction Using Sentinel-1 Images Based on Shortest Plane Distance

Kim¹,

Kim²

2022

J. Korean Soc. Hazard Mitig

View full text Add to dashboard Cite

In this study, a method for extracting the waterbody of small- to medium-sized streams is verified using SAR (Synthetic Aperture Radar) images based on the shortest plane distance (DST). The areas investigated are the Hantangang River and Jungnangcheon stream. To verify the waterbody extraction method, SAR satellite image data (Sentinel-1) and PlanetScope, which is a high-resolution optical satellite, are used simultaneously. After preprocessing the Sentinel-1 images, their brightness distribution is equalized via histogram matching. To realize an efficient stream extraction, a weight, which is the DST from the stream centerline, is added. After combining this weight value and Sentinel-1's VH and VV polarizations, the optimal parameter value is obtained using the k-means method. This value allows the waterbody to be extracted from Sentinel-1 images with maximum accuracy, depending on the resolution limit. Based on the correlation among the VV, VH, and DST, the waterbody extraction can be calculated using an elliptic equation. Results show that the average accuracy is 0.45-0.75, and the average Kappa coefficient is 0.60-0.85. This study shows that the waterbody area can be estimated using the DST. Additionally, the proposed method extracts the waterbody more simply and rapidly than the existing waterbody extraction method.

show abstract

Water Across Synthetic Aperture Radar Data (WASARD): SAR Water Body Classification for the Open Data Cube

Cited by 9 publications

References 6 publications

Towards Sentinel-1 SAR Analysis-Ready Data: A Best Practices Assessment on Preparing Backscatter Data for the Cube

Towards Sentinel-1 SAR Analysis-Ready Data: A Best Practices Assessment on Preparing Backscatter Data for the Cube

Water-Body Segmentation for SAR Images: Past, Current, and Future

Small- to Medium-Sized Stream Waterbody Extraction Using Sentinel-1 Images Based on Shortest Plane Distance

Contact Info

Product

Resources

About