13 April 2018 High-resolution hyperspectral ground mapping for robotic vision
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106961K (2018) https://doi.org/10.1117/12.2310066
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Recently released hyperspectral cameras use large, mosaiced filter patterns to capture different ranges of the light’s spectrum in each of the camera’s pixels. Spectral information is sparse, as it is not fully available in each location. We propose an online method that avoids explicit demosaicing of camera images by fusing raw, unprocessed, hyperspectral camera frames inside an ego-centric ground surface map. It is represented as a multilayer heightmap data structure, whose geometry is estimated by combining a visual odometry system with either dense 3D reconstruction or 3D laser data. We use a publicly available dataset to show that our approach is capable of constructing an accurate hyperspectral representation of the surface surrounding the vehicle. We show that in many cases our approach increases spatial resolution over a demosaicing approach, while providing the same amount of spectral information.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Frank Neuhaus, Frank Neuhaus, Christian Fuchs, Christian Fuchs, Dietrich Paulus, Dietrich Paulus, "High-resolution hyperspectral ground mapping for robotic vision", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106961K (13 April 2018); doi: 10.1117/12.2310066; https://doi.org/10.1117/12.2310066

Back to Top