Global-Local Detail Guided Transformer for Sea Ice Recognition in Optical Remote Sensing Images

TL;DR

This paper introduces GDGT, a transformer-based method that fuses global and local features with a detail-guided decoder to improve sea ice recognition in optical remote sensing images, addressing scale and edge detail challenges.

Contribution

The paper proposes a novel global-local feature fusion mechanism and a detail-guided decoder specifically designed for sea ice recognition in remote sensing images.

Findings

GDGT outperforms existing methods on the sea ice dataset.

The fusion mechanism effectively captures multi-scale features.

The detail-guided decoder enhances edge and detail recognition.

Abstract

The recognition of sea ice is of great significance for reflecting climate change and ensuring the safety of ship navigation. Recently, many deep learning based methods have been proposed and applied to segment and recognize sea ice regions. However, the diverse scales of sea ice areas, the zigzag and fine edge contours, and the difficulty in distinguishing different types of sea ice pose challenges to existing sea ice recognition models. In this paper, a Global-Local Detail Guided Transformer (GDGT) method is proposed for sea ice recognition in optical remote sensing images. In GDGT, a global-local feature fusiont mechanism is designed to fuse global structural correlation features and local spatial detail features. Furthermore, a detail-guided decoder is developed to retain more high-resolution detail information during feature reconstruction for improving the performance of sea ice recognition. Experiments on the produced sea ice dataset demonstrated the effectiveness and advancement of GDGT.