Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy

Research Article

An Object Detection and Scaling Model for Plastic Waste Sorting

Download671 downloads
  • @INPROCEEDINGS{10.4108/eai.20-11-2021.2314204,
        author={Abhishek  Padalkar and Pramod  Pathak and Paul  Stynes},
        title={An Object Detection and Scaling Model for Plastic Waste Sorting},
        proceedings={Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy},
        publisher={EAI},
        proceedings_a={CAIP},
        year={2021},
        month={12},
        keywords={plastic waste sorting object detection and scaling model scaled-yolov4 efficientdet},
        doi={10.4108/eai.20-11-2021.2314204}
    }
    
  • Abhishek Padalkar
    Pramod Pathak
    Paul Stynes
    Year: 2021
    An Object Detection and Scaling Model for Plastic Waste Sorting
    CAIP
    EAI
    DOI: 10.4108/eai.20-11-2021.2314204
Abhishek Padalkar1, Pramod Pathak1, Paul Stynes1,*
  • 1: National College of Ireland, Mayor Street, IFSC, Dublin 01, Ireland
*Contact email: paul.stynes@ncirl.ie

Abstract

Plastic waste sorting involves the separation of plastic into its individual plastic types. This research proposes an Object Detection and Scaling Model for plastic waste sorting to detect four types of plastics using the WaDaBa dataset. This research compares the Object Detection and Scaling Models Scaled-Yolov4 and EfficientDet. Results demonstrate that Scaled-Yolov4- CSP outperforms the state of the art, Colour-Histogram based Canny-Edge-Gaussian Filter, by 21% accuracy.