2023 IEEE GRSS Data Fusion Contest: Large-Scale Fine-Grained Building Classification for Semantic Urban Reconstruction

Buildings are essential components of urban areas. While research on the extraction and 3D reconstruction of buildings is widely conducted, information on fine-grained roof types of buildings is usually ignored. This limits the potential of further analysis, e.g., in the context of urban planning applications. The fine-grained classification of building roof type from satellite images is a highly challenging task due to ambiguous visual features within the satellite imagery. The difficulty is further increased by the lack of corresponding fine-grained building classification datasets. The 2023 IEEE GRSS Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS), the Aerospace Information Research Institute under the Chinese Academy of Sciences, the Universität der Bundeswehr München, and GEOVIS Earth Technology Co., Ltd. aims to push current research on building extraction, classification, and 3D reconstruction towards urban reconstruction with fine-grained semantic information of roof types. To this aim, the DFC23 establishes a large-scale, fine-grained, and multi-modal benchmark for the classification of building roof types. It consists of two challenging competition tracks investigating the fusion of optical and SAR data, while focusing on roof type classification and building height estimation, respectively. The data provided by the DFC23 includes several novel properties: Globally Distributed Large-Scale Dataset. A novel large-scale urban building classification and reconstruction dataset is provided. Buildings are distributed across seventeen cities in six continents to cover a wide range of different building styles. This allows capturing the heterogeneity of cities in different continents with various landforms.  Fine-Grained Roof Type Categories. The buildings are labeled according to a detailed (fine-grained)  categorization of roof types. The DFC23 provides nearly 300k instances with twelve different types of building roofs which renders building classification significantly more challenging.Multimodal Data. To facilitate multimodal data fusion, not only optical imagery, but also Synthetic Aperture Radar (SAR) images are provided. The information captured by these different modalities can be jointly exploited, potentially resulting in the development of more accurate building extraction and classification models.