Caltech Aerial RGB-Thermal Dataset in the Wild
This dataset addresses the need for robust perception algorithms in aerial robotics for adverse conditions, but it is incremental as it focuses on data collection and benchmarking rather than novel methods.
The authors introduced the first publicly-available RGB-thermal dataset for aerial robotics in natural environments, capturing diverse terrains across the U.S. with synchronized data and semantic annotations, and used it to propose benchmarks for segmentation, translation, and tracking, highlighting challenges from domain shifts.
We present the first publicly-available RGB-thermal dataset designed for aerial robotics operating in natural environments. Our dataset captures a variety of terrain across the United States, including rivers, lakes, coastlines, deserts, and forests, and consists of synchronized RGB, thermal, global positioning, and inertial data. We provide semantic segmentation annotations for 10 classes commonly encountered in natural settings in order to drive the development of perception algorithms robust to adverse weather and nighttime conditions. Using this dataset, we propose new and challenging benchmarks for thermal and RGB-thermal (RGB-T) semantic segmentation, RGB-T image translation, and motion tracking. We present extensive results using state-of-the-art methods and highlight the challenges posed by temporal and geographical domain shifts in our data. The dataset and accompanying code is available at https://github.com/aerorobotics/caltech-aerial-rgbt-dataset.