English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Offshore wind farms represent a renewable energy source with a significantglobal growth trend, and their monitoring is strategic for territorial andenvironmental planning. This study's primary objective is to detect offshorewind plants at an instance level using semantic segmentation models andSentinel-1 time series. The secondary objectives are: (a) to develop a databaseconsisting of labeled data and S-1 time series; (b) to compare the performanceof five deep semantic segmentation architectures (U-Net, U-Net++, FeaturePyramid Network - FPN, DeepLabv3+, and LinkNet); (c) develop a novelaugmentation strategy that shuffles the positions of the images within the timeseries; (d) investigate different dimensions of time series intervals (1, 5,10, and 15 images); and (e) evaluate the semantic-to-instance conversionprocedure. LinkNet was the top-performing model, followed by U-Net++ and U-Net,while FPN and DeepLabv3+ presented the worst results. The evaluation ofsemantic segmentation models reveals enhanced Intersection over Union (IoU)(25%) and F-score metrics (18%) with the augmentation of time series images.The study showcases the augmentation strategy's capability to mitigate biasesand precisely detect invariant targets. Furthermore, the conversion fromsemantic to instance segmentation demonstrates its efficacy in accuratelyisolating individual instances within classified regions - simplifying trainingdata and reducing annotation effort and complexity.

Offshore Wind Plant Instance Segmentation Using Sentinel-1 Time Series, GIS, and Semantic Segmentation Models