FLAIR #2: textural and temporal information for semantic segmentation from multi-source optical imagery

TL;DR

This paper introduces the FLAIR #2 dataset, combining high-resolution aerial images and Sentinel-2 time series to enhance semantic land cover segmentation through data fusion of spatial, textural, and temporal information.

Contribution

The paper presents a novel dataset and a data fusion workflow that leverages both spatial detail and temporal spectral richness for improved land cover mapping.

Findings

Effective integration of multi-source data improves segmentation accuracy.

The dataset enables exploration of combined spatial and temporal information.

Promotes innovation in Earth Observation data analysis.

Abstract

The FLAIR #2 dataset hereby presented includes two very distinct types of data, which are exploited for a semantic segmentation task aimed at mapping land cover. The data fusion workflow proposes the exploitation of the fine spatial and textural information of very high spatial resolution (VHR) mono-temporal aerial imagery and the temporal and spectral richness of high spatial resolution (HR) time series of Copernicus Sentinel-2 satellite images. The French National Institute of Geographical and Forest Information (IGN), in response to the growing availability of high-quality Earth Observation (EO) data, is actively exploring innovative strategies to integrate these data with heterogeneous characteristics. IGN is therefore offering this dataset to promote innovation and improve our knowledge of our territories.