The SEN1-2 Dataset for Deep Learning in SAR-Optical Data Fusion
This provides a foundational resource for researchers in remote sensing and multi-sensor data fusion, addressing a critical bottleneck in the field.
The authors tackled the lack of training data for deep learning in SAR-optical data fusion by publishing the SEN1-2 dataset, which includes 282,384 pairs of image patches collected globally across all seasons, enabling applications like SAR image colorization and matching.
While deep learning techniques have an increasing impact on many technical fields, gathering sufficient amounts of training data is a challenging problem in remote sensing. In particular, this holds for applications involving data from multiple sensors with heterogeneous characteristics. One example for that is the fusion of synthetic aperture radar (SAR) data and optical imagery. With this paper, we publish the SEN1-2 dataset to foster deep learning research in SAR-optical data fusion. SEN1-2 comprises 282,384 pairs of corresponding image patches, collected from across the globe and throughout all meteorological seasons. Besides a detailed description of the dataset, we show exemplary results for several possible applications, such as SAR image colorization, SAR-optical image matching, and creation of artificial optical images from SAR input data. Since SEN1-2 is the first large open dataset of this kind, we believe it will support further developments in the field of deep learning for remote sensing as well as multi-sensor data fusion.