Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste
The introduction of sophisticated waste treatment plants is making the process of trash sorting and recycling more and more effective and eco-friendly. Studies on Automated Waste Sorting (AWS) are greatly contributing to making the whole recycling process more efficient. However, a relevant issue, w...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/7/8/144 |
_version_ | 1797523358708924416 |
---|---|
author | Arianna Patrizi Giorgio Gambosi Fabio Massimo Zanzotto |
author_facet | Arianna Patrizi Giorgio Gambosi Fabio Massimo Zanzotto |
author_sort | Arianna Patrizi |
collection | DOAJ |
description | The introduction of sophisticated waste treatment plants is making the process of trash sorting and recycling more and more effective and eco-friendly. Studies on Automated Waste Sorting (AWS) are greatly contributing to making the whole recycling process more efficient. However, a relevant issue, which remains unsolved, is how to deal with the large amount of waste that is littered in the environment instead of being collected properly. In this paper, we introduce BackRep: a method for building waste recognizers that can be used for identifying and sorting littered waste directly where it is found. BackRep consists of a data-augmentation procedure, which expands existing datasets by cropping solid waste in images taken on a uniform (white) background and superimposing it on more realistic backgrounds. For our purpose, realistic backgrounds are those representing places where solid waste is usually littered. To experiment with our data-augmentation procedure, we produced a new dataset in realistic settings. We observed that waste recognizers trained on augmented data actually outperform those trained on existing datasets. Hence, our data-augmentation procedure seems a viable approach to support the development of waste recognizers for urban and wild environments. |
first_indexed | 2024-03-10T08:41:49Z |
format | Article |
id | doaj.art-4a78d7d3f8a24b368cf974a53beaa6e6 |
institution | Directory Open Access Journal |
issn | 2313-433X |
language | English |
last_indexed | 2024-03-10T08:41:49Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Imaging |
spelling | doaj.art-4a78d7d3f8a24b368cf974a53beaa6e62023-11-22T08:14:01ZengMDPI AGJournal of Imaging2313-433X2021-08-017814410.3390/jimaging7080144Data Augmentation Using Background Replacement for Automated Sorting of Littered WasteArianna Patrizi0Giorgio Gambosi1Fabio Massimo Zanzotto2Dipartimento di Ingegneria dell’Impresa, University of Rome Tor Vergata, I-00133 Rome, ItalyDipartimento di Ingegneria dell’Impresa, University of Rome Tor Vergata, I-00133 Rome, ItalyDipartimento di Ingegneria dell’Impresa, University of Rome Tor Vergata, I-00133 Rome, ItalyThe introduction of sophisticated waste treatment plants is making the process of trash sorting and recycling more and more effective and eco-friendly. Studies on Automated Waste Sorting (AWS) are greatly contributing to making the whole recycling process more efficient. However, a relevant issue, which remains unsolved, is how to deal with the large amount of waste that is littered in the environment instead of being collected properly. In this paper, we introduce BackRep: a method for building waste recognizers that can be used for identifying and sorting littered waste directly where it is found. BackRep consists of a data-augmentation procedure, which expands existing datasets by cropping solid waste in images taken on a uniform (white) background and superimposing it on more realistic backgrounds. For our purpose, realistic backgrounds are those representing places where solid waste is usually littered. To experiment with our data-augmentation procedure, we produced a new dataset in realistic settings. We observed that waste recognizers trained on augmented data actually outperform those trained on existing datasets. Hence, our data-augmentation procedure seems a viable approach to support the development of waste recognizers for urban and wild environments.https://www.mdpi.com/2313-433X/7/8/144automated waste sortingconvolutional neural networksbackground replacementdata augmentationcomputer visiondeep learning |
spellingShingle | Arianna Patrizi Giorgio Gambosi Fabio Massimo Zanzotto Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste Journal of Imaging automated waste sorting convolutional neural networks background replacement data augmentation computer vision deep learning |
title | Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste |
title_full | Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste |
title_fullStr | Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste |
title_full_unstemmed | Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste |
title_short | Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste |
title_sort | data augmentation using background replacement for automated sorting of littered waste |
topic | automated waste sorting convolutional neural networks background replacement data augmentation computer vision deep learning |
url | https://www.mdpi.com/2313-433X/7/8/144 |
work_keys_str_mv | AT ariannapatrizi dataaugmentationusingbackgroundreplacementforautomatedsortingoflitteredwaste AT giorgiogambosi dataaugmentationusingbackgroundreplacementforautomatedsortingoflitteredwaste AT fabiomassimozanzotto dataaugmentationusingbackgroundreplacementforautomatedsortingoflitteredwaste |