Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques
Abstract The expansion of LEAN and small batch manufacturing demands flexible automated workstations capable of switching between sorting various wastes over time. To address this challenge, our study is focused on assessing the ability of the Segment Anything Model (SAM) family of deep learning arc...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87226-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571641202212864 |
|---|---|
| author | Arso M. Vukicevic Milos Petrovic Nebojsa Jurisevic Marko Djapan Nikola Knezevic Aleksandar Novakovic Kosta Jovanovic |
| author_facet | Arso M. Vukicevic Milos Petrovic Nebojsa Jurisevic Marko Djapan Nikola Knezevic Aleksandar Novakovic Kosta Jovanovic |
| author_sort | Arso M. Vukicevic |
| collection | DOAJ |
| description | Abstract The expansion of LEAN and small batch manufacturing demands flexible automated workstations capable of switching between sorting various wastes over time. To address this challenge, our study is focused on assessing the ability of the Segment Anything Model (SAM) family of deep learning architectures to separate highly variable objects during robotic waste sorting. The proposed two-step procedure for generic versatile visual waste sorting is based on the SAM architectures (original SAM, FastSAM, MobileSAMv2, and EfficientSAM) for waste object extraction from raw images, and the use of classification architecture (MobileNetV2, VGG19, Dense-Net, Squeeze-Net, ResNet, and Inception-v3) for accurate waste sorting. Such a pipeline brings two key advantages that make it more applicable in industry practice by: 1) eliminating the necessity for developing dedicated waste detection and segmentation algorithms for waste object localization, and 2) significantly reducing the time and costs required for adapting the solution to different use cases. With the proposed procedure, switching to a new waste type sorting is reduced to only two steps: The use of SAM for the automatic object extraction, followed by their separation into corresponding classes used to fine-tune the classifier. Validation on four use cases (floating waste, municipal waste, e-waste, and smart bins) shows robust results, with accuracy ranging from 86 to 97% when using the MobileNetV2 with SAM and FastSAM architectures. The proposed approach has a high potential to facilitate deployment, increase productivity, lower expenses, and minimize errors in robotic waste sorting while enhancing overall recycling and material utilization in the manufacturing industry. |
| format | Article |
| id | doaj-art-2e0c2d636e2443ee827fb1b24832cd58 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2e0c2d636e2443ee827fb1b24832cd582025-02-02T12:23:54ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-025-87226-xVersatile waste sorting in small batch and flexible manufacturing industries using deep learning techniquesArso M. Vukicevic0Milos Petrovic1Nebojsa Jurisevic2Marko Djapan3Nikola Knezevic4Aleksandar Novakovic5Kosta Jovanovic6Faculty of Engineering, University of KragujevacSchool of Electrical Engineering, University of BelgradeFaculty of Engineering, University of KragujevacFaculty of Engineering, University of KragujevacSchool of Electrical Engineering, University of BelgradeSchool of Mathematics and Physics, Queen’s University BelfastSchool of Electrical Engineering, University of BelgradeAbstract The expansion of LEAN and small batch manufacturing demands flexible automated workstations capable of switching between sorting various wastes over time. To address this challenge, our study is focused on assessing the ability of the Segment Anything Model (SAM) family of deep learning architectures to separate highly variable objects during robotic waste sorting. The proposed two-step procedure for generic versatile visual waste sorting is based on the SAM architectures (original SAM, FastSAM, MobileSAMv2, and EfficientSAM) for waste object extraction from raw images, and the use of classification architecture (MobileNetV2, VGG19, Dense-Net, Squeeze-Net, ResNet, and Inception-v3) for accurate waste sorting. Such a pipeline brings two key advantages that make it more applicable in industry practice by: 1) eliminating the necessity for developing dedicated waste detection and segmentation algorithms for waste object localization, and 2) significantly reducing the time and costs required for adapting the solution to different use cases. With the proposed procedure, switching to a new waste type sorting is reduced to only two steps: The use of SAM for the automatic object extraction, followed by their separation into corresponding classes used to fine-tune the classifier. Validation on four use cases (floating waste, municipal waste, e-waste, and smart bins) shows robust results, with accuracy ranging from 86 to 97% when using the MobileNetV2 with SAM and FastSAM architectures. The proposed approach has a high potential to facilitate deployment, increase productivity, lower expenses, and minimize errors in robotic waste sorting while enhancing overall recycling and material utilization in the manufacturing industry.https://doi.org/10.1038/s41598-025-87226-xWaste SortingArtificial IntelligenceDeep LearningRecyclingManufacturing |
| spellingShingle | Arso M. Vukicevic Milos Petrovic Nebojsa Jurisevic Marko Djapan Nikola Knezevic Aleksandar Novakovic Kosta Jovanovic Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques Scientific Reports Waste Sorting Artificial Intelligence Deep Learning Recycling Manufacturing |
| title | Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| title_full | Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| title_fullStr | Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| title_full_unstemmed | Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| title_short | Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| title_sort | versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques |
| topic | Waste Sorting Artificial Intelligence Deep Learning Recycling Manufacturing |
| url | https://doi.org/10.1038/s41598-025-87226-x |
| work_keys_str_mv | AT arsomvukicevic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT milospetrovic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT nebojsajurisevic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT markodjapan versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT nikolaknezevic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT aleksandarnovakovic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques AT kostajovanovic versatilewastesortinginsmallbatchandflexiblemanufacturingindustriesusingdeeplearningtechniques |