Gaussian-Based Swap Operator for Context-Aware Extraction of Building Boundary Vectors

Abstract

Accurate extraction of building vector boundaries holds paramount importance within the domains of urban planning and geographic information systems (GISs), providing indispensable support for urban construction endeavors and resource management initiatives. CNNs, while proficient in local feature extraction, often falter in capturing holistic, global image characteristics. Transformers excel in contextual feature comprehension but demand substantial computational resources and parameterization, impeding practical deployment. To address these challenges, this article introduces an innovative computational operator known as G-Swap, which integrates Gaussian-distance-based feature correlation considerations, thereby significantly augmenting contextual comprehension within the computational framework. In addition, a universal architecture for boundary vector extraction is proposed in this article, comprising three primary components: 1) an enhanced backbone, integrating the G-Swap operator to enhance the backbone while bolstering model expressiveness; 2) a decoder module, tasked with discriminating corner and edge features; and 3) a two-branch detection head. Empirical experiments conducted on the vectorizing world building (VWB) dataset underscore the model’s superior performance. Our G-Swap achieved ${F}1$ scores of 91.2% for vertices and 80.1% for edges, surpassing the previous state-of-the-art (SOTA) by 2.1% and 2.0%, respectively.