Building Footprint Extraction in Dense Areas using Super Resolution and Frame Field Learning

TL;DR

This paper introduces a novel framework combining super resolution and frame field learning to improve building footprint extraction in dense areas from aerial imagery, addressing challenges of data quality and complex structures.

Contribution

The proposed method integrates super resolution with multitask learning and adaptive loss weighting to enhance accuracy in dense, complex urban environments.

Findings

Significantly outperforms existing methods on dense area datasets.

Effectively captures fine-grained building details and irregular structures.

Improves building footprint extraction in low-quality, dense imagery.

Abstract

Despite notable results on standard aerial datasets, current state-of-the-arts fail to produce accurate building footprints in dense areas due to challenging properties posed by these areas and limited data availability. In this paper, we propose a framework to address such issues in polygonal building extraction. First, super resolution is employed to enhance the spatial resolution of aerial image, allowing for finer details to be captured. This enhanced imagery serves as input to a multitask learning module, which consists of a segmentation head and a frame field learning head to effectively handle the irregular building structures. Our model is supervised by adaptive loss weighting, enabling extraction of sharp edges and fine-grained polygons which is difficult due to overlapping buildings and low data quality. Extensive experiments on a slum area in India that mimics a dense area demonstrate that our proposed approach significantly outperforms the current state-of-the-art methods by a large margin.