Invisible Headlights Dataset for Traversability Estimation in Long-Wave Hyperspectral Imagery

The Invisible Headlights Dataset consists of long wave (LW) hyperspectral imagery (HSI) from diverse off-road scenes including forest, desert, snow, ponds, and open fields. Imagery was collected during both the daytime and nighttime, in various weather conditions, and includes challenging scenes with a wide range of obstacles. In addition to LW HSI, our dataset contains corresponding traversability annotations and visible imagery.

The LW HSI and corresponding traversability annotations are publicly available.

We hope this dataset can facilitate future research. If you find this data useful, please cite our WACV 2024 publication:

F. Yellin, S. McCloskey, C. Hill, E. Smith, and B. Clipp, “Concurrent Band Selection and Traversability Estimation from Long-Wave Hyperspectral Imagery in Off-Road Settings,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.

bibtex

@InProceedings{Yellin_2024_WACV,
    author = {Yellin, Florence and McCloskey, Scott and Hill, Cole and Smith, Eric and Clipp, Brian},
    title = {Concurrent Band Selection and Traversability Estimation from Long-Wave Hyperspectral Imagery in Off-Road Settings},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month = {January},
    year = {2024}
}