EUVIMEDEUVIMED entdecken
Crossref

Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling

Shoufeng Jin, Zixuan Yang, Grzegorz Królczykg, Xinying Liu, Paolo Gardoni, Zhixiong Li

Waste Management · 2023-05 · 162 · 123-130

DOI: 10.1016/j.wasman.2023.02.014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Waste Management, 2023-05. Verfasst von Shoufeng Jin und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710600, China. Hauptthemen laut MEDLINE: Refuse Disposal, Waste Management, Deep Learning, Garbage. Die Arbeit wurde bisher 136-mal zitiert (Crossref) und nennt 28 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Waste recycling is a critical issue for environment pollution management while garbage classification determines the recycling efficiency. In order to reduce labor costs and increase garbage classification capacity, a machine vision system is established based on the deep learning and transfer learning. In this new method, an improved MobileNetV2 deep learning model is proposed for garbage detection and classification, where the attention mechanism is introduced into the first and last convolution layers of the MobileNetV2 model to improve the recognition accuracy and the transfer learning uses a set of pre-trained weight parameters to extend the model generalization ability. In addition, the principal component analysis (PCA) is employed to reduce the dimension of the last fully connected layer to enable real-time operation of the developed model on an edge device. The experimental results demonstrate that the proposed method generates 90.7 % of the garbage classification accuracy on the "Huawei Cloud" datasets, the average inference time is 600 ms on the raspberry Pi 4B microprocessor, and the model volume compression is 30.1 % of the basic MobileNetV2 model. Furthermore, a garbage sorting porotype is designed and manufactured to evaluate the performance of the proposed MobileNetV2 model on the real-world garbage identification, which turns out that the average garbage classification accuracy is 89.26 %. Hence, the developed garbage sorting porotype can be used a effective tool for sustainable waste recycling.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Refuse DisposalWaste ManagementDeep LearningGarbageRecycling

Stichwörter der Autor:innen

Deep learningGarbage classificationMachine visionWaste management

Autor:innen und Institutionen

  • College of Mechanical and Electrical Engineering, Xi'an Polytechnic University, Xi'an 710600, China.
  • Faculty of Mechanical Engineering, Opole University of Technology, Opole 45-758, Poland.
  • Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA.
  • Donghai Laboratory, Zhoushan 316021, Zhejiang, China; Yonsei Frontier Lab, Yonsei University, Seoul 03722, South Korea. Electronic address: zhixiong.li@yonsei.ac.kr.

Zitieren

APA

Jin, S., Yang, Z., Królczykg, G., Liu, X., Gardoni, P., & Li, Z. (2023). Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling. Waste Management, 162, 123-130. https://doi.org/10.1016/j.wasman.2023.02.014

Vancouver

Jin S, Yang Z, Królczykg G, Liu X, Gardoni P, Li Z. Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling. Waste Management. 2023;162:123-130. doi:10.1016/j.wasman.2023.02.014

BibTeX
@article{Jin2023,
  author = {Jin, Shoufeng and Yang, Zixuan and Królczykg, Grzegorz and Liu, Xinying and Gardoni, Paolo and Li, Zhixiong},
  title = {Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling},
  journal = {Waste Management},
  year = {2023},
  volume = {162},
  pages = {123--130},
  doi = {10.1016/j.wasman.2023.02.014}
}
Kostenlos starten →