Affiliation:
1. Baraja Pty Ltd., Suite 303, Building 1, 3 Richardson Pl., North Ryde, NSW 2113, Australia
Abstract
Light detection and ranging (LIDAR) sensors using a polarization-diverse receiver are able to capture polarimetric information about the target under measurement. We demonstrate this capability using a silicon photonic receiver architecture that enables this on a shot-by-shot basis, enabling polarization analysis nearly instantaneously in the point cloud, and then use this data to train a material classification neural network. Using this classifier, we show an accuracy of 85.4% for classifying plastic, wood, concrete, and coated aluminum.
Reference30 articles.
1. Lidar for self-driving cars;Hecht;Opt. Photonics News,2018
2. What lies beneath: Material classification for autonomous excavators using proprioceptive force sensing and machine learning;Fernando;Autom. Constr.,2020
3. Challenges for future robotic sorters of mixed industrial waste: A survey;Kiyokawa;IEEE Trans. Autom. Sci. Eng.,2022
4. Fast characterization of biomass and waste by infrared spectra and machine learning models;Tao;J. Hazard. Mater.,2020
5. Dashpute, A., Saragadam, V., Alexander, E., Willomitzer, F., Katsaggelos, A., Veeraraghavan, A., and Cossairt, O. (2023, January 17–24). Thermal Spread Functions (TSF): Physics-guided Material Classification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.