Abstract
Remote sensing (RS) technology plays a critical role in monitoring our constantly changing world, with building change detection (BCD) being a pivotal application that contributes to urban planning, disaster management, and environmental monitoring. In tasks of BCD in high-resolution RS images, it is faced with challenges such as complex backgrounds, redundancy in feature fusion information, and imbalance of positive and negative samples. Utilizing high-resolution RS images for BCD tasks remains challenging. Therefore, a new BCD network named Meta-SGNet with siamese architecture is proposed. Firstly, a self-calibrating cross module (SCCM) algorithm is proposed to extract the morphological characteristics of buildings in RS images effectively. Subsequently, the gated feature fusion module (GFFM) is proposed to fuse the features of bi-temporal buildings dynamically. Finally, a self-learning meta-encoder (Meta-E) is proposed, which uses a meta-learning algorithm to guide the encoder to encode the bi-temporal RS image to better pay attention to the learning of positive samples of building changes to improve the accuracy of building change detection. Experimental results show that Meta-SGNet outperforms seven state-of-the-art (SOTA) BCD methods on three datasets (Google-CD, WHU-CD, and LEVIR-CD). In the practical application, we acquired 40 pairs of high-resolution image pairs via Google Earth API for a real building change detection task. The application results show that Meta-SGNet can accurately capture the range of building changes and shows high adaptability and the ability to quickly detect building changes in different scenarios.