SeasoNet: A Seasonal Scene Classification, segmentation and Retrieval dataset for satellite Imagery over Germany

TL;DR

SeasoNet is a comprehensive large-scale satellite imagery dataset with multi-season, multi-label land cover annotations designed for scene classification, segmentation, and retrieval tasks, enabling advanced remote sensing applications.

Contribution

The paper introduces SeasoNet, the largest multi-season satellite imagery dataset with pixel-level land cover labels, facilitating diverse scene understanding tasks in remote sensing.

Findings

State-of-the-art deep networks achieve baseline performance on scene classification.

SeasoNet enables cross-season image retrieval and land cover mapping.

The dataset supports self-supervised feature learning in remote sensing.

Abstract

This work presents SeasoNet, a new large-scale multi-label land cover and land use scene understanding dataset. It includes $1\,759\,830$ images from Sentinel-2 tiles, with 12 spectral bands and patch sizes of up to $ 120 \ \mathrm{px} \times 120 \ \mathrm{px}$. Each image is annotated with large scale pixel level labels from the German land cover model LBM-DE2018 with land cover classes based on the CORINE Land Cover database (CLC) 2018 and a five times smaller minimum mapping unit (MMU) than the original CLC maps. We provide pixel synchronous examples from all four seasons, plus an additional snowy set. These properties make SeasoNet the currently most versatile and biggest remote sensing scene understanding dataset with possible applications ranging from scene classification over land cover mapping to content-based cross season image retrieval and self-supervised feature learning. We provide baseline results by evaluating state-of-the-art deep networks on the new dataset in scene classification and semantic segmentation scenarios.