Journal Article

TENet: A Texture-Enhanced Network for Intertidal Sediment and Habitat Classification in Multiband PolSAR Images

Wang, Wensheng, Gade, Martin, Zhou, Huihui, Zhang, Di

2024

Overview

This paper proposes a texture-enhanced network (TENet) for intertidal sediment and habitat classification using multiband multipolarization synthetic aperture radar (SAR) images. The architecture introduces the texture enhancement module (TEM) into the UNet framework to explicitly learn global texture information from SAR images. The study sites are chosen from the northern part of the intertidal zones in the German Wadden Sea. Results show that the presented TENet model is able to detail the intertidal surface types, including land, seagrass, bivalves, bright sands/beach, water, sediments, and thin coverage of vegetation or bivalves. To further assess its performance, we quantitatively compared our results from the TENet model with different instance segmentation models for the same areas of interest. The TENet model gives finer classification accuracies and shows great potential in providing more precise locations.

• Publisher: MDPI AG
• Subject: Algorithms / Artificial satellites in remote sensing / Bivalvia / Classification / Classification (sedimentation) / Coastal ecosystems / Decomposition / Deep learning / Environmental aspects / Habitats / Image enhancement / Instance segmentation / Intertidal zone / intertidal zones / littoral zone / Machine learning / Mollusks / multiband / multipolarization / Neural networks / North Sea / Radar imaging / Remote sensing / SAR / seagrasses / Sediments / Sediments (Geology) / Semantics / Sensors / Synthetic aperture radar / Texture / texture enhancement / Tide pool ecology / vegetation