Hyper-Drive: Visible-Short Wave Infrared Hyperspectral Imaging Datasets for Robots in Unstructured Environments

摘要

Hyperspectral sensors have enjoyed widespread use in the realm of remote sensing; however, they require additional considerations for reliable functionality onboard mobile robots. In this work, we introduce a first-of-its-kind system architecture with snapshot hyperspectral cameras and point spectrometers to efficiently generate composite datacubes from a moving robot base. Our system collects and registers datacubes spanning the visible to shortwave infrared (660-1700 nm) spectrum while simultaneously capturing the ambient solar spectrum reflected off a white reference tile. We collect and disseminate a large dataset of more than 500 labeled datacubes from on-road and off-road terrain compliant with the ATLAS ontology to further the integration hyperspectral imaging (HSI). Our analysis of these data demonstrates that HSI is beneficial in terrain class separability and is a significant opportunity to increase understanding of scene composition from a robot-centric context. All code and data are open source online: https://river-lab.github.io/hyper_drive_data