Real-time plastic litter detection using hyperspectral sensing on drone

Abstract

A hyperspectral sensing system operating in the SWIR band (900-1700nm) was previously developed for drone- based detection of plastic litter in the environment. The detection software is based on a linear classifier trained on examples, that detects plastics and transmits information to a ground station that visualizes on a map the location of points surveyed, labeled as plastics where applicable. In this paper, we report on implementation of plastics litter detection in real time, while the drone is flying.