EGAFNet: An Edge Guidance and Scale-aware Adaptive Fusion Network for Building Extraction from Remote Sensing Images

Accurately extracting buildings from high-resolution remote sensing images is crucial for urban planning, smart city construction, map updating, and other fields. However, the buildings extracted from remote sensing images still have deficiencies such as fuzzy boundaries and poor integrity due to the occlusion of trees and shadows, the interference of redundant information, and the characteristics of buildings with different shapes and scales. In this paper, a novel building extraction model EGAFNet is proposed for remote sensing images, which utilizes EfficientNetV2 as the encoder and multiscale feature enhancement module as the decoder to improve the accuracy and efficiency. To address the issue of missing boundary information, a branch for extract boundary features and an edge guidance module are constructed to enhance the network's ability to express the boundary. In addition, a scale-aware adaptive fusion module is designed to adaptively aggregate the multi-scale features to enhance the network's ability to capture the different scale features. We also adopt a multi-layer supervision strategy that predict the outputs for each layer of the decoding phase and impose multi-level loss constraints to achieve fast fitting of the model. Experiments are conducted on the WHU building dataset and a dataset of building instances of typical cities in China. The experimental results demonstrate that the EGAFNet achieves the best F1-score and IoU compared with other typical building extraction methods. It suggests that EGAFNet can effectively improve the learning ability of the boundary information and enhance the multi-scale building feature representation, thus realizing more accurate building extraction. The code will be available at https://github.com/Mwyang/EGAFNet.