Semantic Segmentation with High-Resolution Sentinel-1 SAR Data

Erten H., Bostanci E., Acici K., Guzel M. S., Asuroglu T., Aydin A.

APPLIED SCIENCES-BASEL, cilt.13, sa.10, 2023 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 13 Sayı: 10
  • Basım Tarihi: 2023
  • Doi Numarası: 10.3390/app13106025
  • Dergi Adı: APPLIED SCIENCES-BASEL
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Agricultural & Environmental Science Database, Applied Science & Technology Source, Communication Abstracts, INSPEC, Metadex, Directory of Open Access Journals, Civil Engineering Abstracts
  • Anahtar Kelimeler: SAR, SAR segmentation, deep learning, semantic segmentation, Sentinel-1, CONVOLUTIONAL NEURAL-NETWORK, LAND-COVER, CLASSIFICATION, IMAGE, FOREST
  • Ankara Üniversitesi Adresli: Evet

Özet

The world's high-resolution images are supplied by a radar system named Synthetic Aperture Radar (SAR). Semantic SAR image segmentation proposes a computer-based solution to make segmentation tasks easier. When conducting scientific research, accessing freely available datasets and images with low noise levels is rare. However, SAR images can be accessed for free. We propose a novel process for labeling Sentinel-1 SAR radar images, which the European Space Agency (ESA) provides free of charge. This process involves denoising the images and using an automatically created dataset with pioneering deep neural networks to augment the results of the semantic segmentation task. In order to exhibit the power of our denoising process, we match the results of our newly created dataset with speckled noise and noise-free versions. Thus, we attained a mean intersection over union (mIoU) of 70.60% and overall pixel accuracy (PA) of 92.23 with the HRNet model. These deep learning segmentation methods were also assessed with the McNemar test. Our experiments on the newly created Sentinel-1 dataset establish that combining our pipeline with deep neural networks results in recognizable improvements in challenging semantic segmentation accuracy and mIoU values.