Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest

TLDR

The paper reports the scientific outcomes of the 2017 IEEE GRSS Data Fusion Contest on local climate zone classification. The contest used a multitemporal, multimodal dataset of Landsat 8, Sentinel‑2 imagery and OpenStreetMap vectors, training and testing on geographically distinct cities to evaluate models for accuracy, generality, and computational efficiency. Participants achieved improved performance through rigorous atmospheric correction, multi‑date imagery, and ensemble methods that fused results from different data sources and time instants.

Abstract

In this paper, we present the scientific outcomes of the 2017 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2017 Contest was aimed at addressing the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap). The competition, based on separate geographical locations for the training and testing of the proposed solution, aimed at models that were accurate (assessed by accuracy metrics on an undisclosed reference for the test cities), general (assessed by spreading the test cities across the globe), and computationally feasible (assessed by having a test phase of limited time). The techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and of mixed ideas and methodologies deriving from computer vision and machine learning but also deeply rooted in the specificities of remote sensing. In particular, rigorous atmospheric correction, the use of multidate images, and the use of ensemble methods fusing results obtained from different data sources/time instants made the difference.