Land-Use Classification of High-Resolution Remote Sensing Imagery Incorporating Global–Local Interactive Features Across Optical Domain and Land Cover Primitives

The Land Use (LU) classification of remote sensing (RS) images has broad applications in various fields. In recent years, hybrid CNN-Transformer models have been widely applied to the LU classification task. These methods combine the advantages of CNN and transformer to mine information within RS images fully for LU classification. However, due to rich content and complex backgrounds in RS images, existing methods often overlook the deep semantic information and spatial structural relationships hidden within optical domain, resulting in limited classification accuracy. To address these challenges, we propose a novel LU classification model: the Global-Local Interactive Feature Fusion Model (GLIFFM). The GLIFFM utilizes a CNN-Transformer architecture and simultaneously integrates Land Cover (LC) primitives to fully exploit both semantic content within the RS images and the spatial structural information. First, a Mutual Feature Extraction module is designed to extract correlated and complementary features between optical and LC primitives. Next, we introduce a Local and Global Feature Enhancement Module to enhance deep features containing both LC and optical information. Finally, a Gated Information Fusion Block is proposed to perform gated fusion of the local and global features. The experimental results conducted on the WHDLD, EuroSAT, and LCZGBA datasets demonstrate that our GLIFFM can achieve superior classification performance and outperform many state-of-the-art methods. Our source codes are available at https://github.com/Fimwu7/The-GLIFFM-for-Land-Use-Classifcation.