Given the hyper-spectral imaging unique potentials in grasping the polymer characteristics of different materials, it is commonly used in sorting procedures. In a practical plastic sorting scenario, multiple plastic flakes may overlap which depending on their characteristics, the overlap can be reflected in their spectral signature. In this work, we use hyper-spectral imaging for the segmentation of three types of plastic flakes and their possible overlapping combinations. We propose an intuitive and simple multi-label encoding approach, bitfield encoding, to account for the overlapping regions. With our experiments, we show that the bitfield encoding improves over the baseline single-label approach and we further demonstrate its potential in predicting multiple labels for overlapping classes even when the model is only trained with non-overlapping classes.
@article{arxiv.2203.12350,
title = {Hyper-Spectral Imaging for Overlapping Plastic Flakes Segmentation},
author = {Guillem Martinez and Maya Aghaei and Martin Dijkstra and Bhalaji Nagarajan and Femke Jaarsma and Jaap van de Loosdrecht and Petia Radeva and Klaas Dijkstra},
journal= {arXiv preprint arXiv:2203.12350},
year = {2022}
}