Feature Aggregation Network for Building Extraction from High-resolution Remote Sensing Images

TL;DR

This paper introduces FANet, a novel neural network architecture that effectively combines global and local features for precise building extraction from high-resolution satellite imagery, addressing the challenge of intraclass variability.

Contribution

The paper presents FANet, which integrates Pyramid Vision Transformer, Feature Aggregation, Difference Elimination, Receptive Field Block, and Dual Attention modules for enhanced feature extraction in remote sensing images.

Findings

FANet outperforms existing methods on multiple datasets.

The model achieves high accuracy in boundary recognition.

Extensive experiments validate the effectiveness of the proposed architecture.

Abstract

The rapid advancement in high-resolution satellite remote sensing data acquisition, particularly those achieving submeter precision, has uncovered the potential for detailed extraction of surface architectural features. However, the diversity and complexity of surface distributions frequently lead to current methods focusing exclusively on localized information of surface features. This often results in significant intraclass variability in boundary recognition and between buildings. Therefore, the task of fine-grained extraction of surface features from high-resolution satellite imagery has emerged as a critical challenge in remote sensing image processing. In this work, we propose the Feature Aggregation Network (FANet), concentrating on extracting both global and local features, thereby enabling the refined extraction of landmark buildings from high-resolution satellite remote sensing imagery. The Pyramid Vision Transformer captures these global features, which are subsequently refined by the Feature Aggregation Module and merged into a cohesive representation by the Difference Elimination Module. In addition, to ensure a comprehensive feature map, we have incorporated the Receptive Field Block and Dual Attention Module, expanding the receptive field and intensifying attention across spatial and channel dimensions. Extensive experiments on multiple datasets have validated the outstanding capability of FANet in extracting features from high-resolution satellite images. This signifies a major breakthrough in the field of remote sensing image processing. We will release our code soon.