Fusion of Super‐Resolution and Semantic Segmentation Deep Models for Building Footprint Extraction From Aerial Images

ABSTRACT The spatial resolution of remotely sensed images has seen significant improvements; higher resolution facilitates the understanding of remote sensing images and improves the accuracy of building footprint extraction. Thus, this paper introduces a novel approach that combines super‐resolution reconstruction with semantic segmentation deep models for building footprint extraction. To begin, a super‐resolution reconstruction deep model is employed to enhance the resolution of the target images. Subsequently, training samples are generated using various data augmentation techniques based on the reconstructed images. Finally, a semantic segmentation deep model is trained to perform the final building footprint extraction. For validation, our proposed framework was tested on two publicly available aerial image datasets: the WHU building dataset and the Massachusetts building dataset. The results obtained from these datasets demonstrated the effectiveness of our method, achieving high Intersection over Union (IoU) scores of 90.57% and 75.02%, respectively. Furthermore, our approach outperformed seven other competing methods, showcasing its superior performance.