This paper presents a comparative study of various efficient state-of-the-art image segmentation models applied to the challenging task of food localization in trays in canteen environments. Using the UNIMIB2016 dataset, which comprises images of canteen trays with multiple food items, we evaluate the performance of ten deep learning-based methods in terms of their segmentation accuracy measured by the Jaccard Index, and computational efficiency measured by Multiply-Accumulate (MACs) operations and the number of parameters. Our results illustrate a tradeoff between computational demand and accuracy, with DABNet achieving the highest accuracy but at a cost of lower efficiency compared to others, while models like ENet or EDANet offer a balanced solution suitable for real-time applications. The study not only benchmarks these models but also discusses the implications of different architectural choices, such as the use of dilated and depth-wise convolutions, which influence the models' performance. This work aims to guide the selection of appropriate segmentation models for dietary management systems in canteen settings, contributing to advancements in automated food service operations and dietary monitoring.

Piccoli, F., Buzzelli, M., Marelli, D., Bianco, S., Ciocca, G., Schettini, R. (2024). Efficient Deep Learning Methods for Food Localization in Canteen Trays. In 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI) (pp.208-213) [10.1109/rtsi61910.2024.10761232].

Efficient Deep Learning Methods for Food Localization in Canteen Trays

Piccoli, Flavio;Buzzelli, Marco;Marelli, Davide;Bianco, Simone;Ciocca, Gianluigi;Schettini, Raimondo
2024

Abstract

This paper presents a comparative study of various efficient state-of-the-art image segmentation models applied to the challenging task of food localization in trays in canteen environments. Using the UNIMIB2016 dataset, which comprises images of canteen trays with multiple food items, we evaluate the performance of ten deep learning-based methods in terms of their segmentation accuracy measured by the Jaccard Index, and computational efficiency measured by Multiply-Accumulate (MACs) operations and the number of parameters. Our results illustrate a tradeoff between computational demand and accuracy, with DABNet achieving the highest accuracy but at a cost of lower efficiency compared to others, while models like ENet or EDANet offer a balanced solution suitable for real-time applications. The study not only benchmarks these models but also discusses the implications of different architectural choices, such as the use of dilated and depth-wise convolutions, which influence the models' performance. This work aims to guide the selection of appropriate segmentation models for dietary management systems in canteen settings, contributing to advancements in automated food service operations and dietary monitoring.
slide + paper
Food localization, semantic segmentation, canteen automatization, industry 4.0
English
2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)
2024
2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)
9798350362145
26-nov-2024
2024
208
213
https://ieeexplore.ieee.org/document/10761232
reserved
Piccoli, F., Buzzelli, M., Marelli, D., Bianco, S., Ciocca, G., Schettini, R. (2024). Efficient Deep Learning Methods for Food Localization in Canteen Trays. In 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI) (pp.208-213) [10.1109/rtsi61910.2024.10761232].
File in questo prodotto:
File Dimensione Formato  
Piccoli-2024-RTSI-VoR.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 10.68 MB
Formato Adobe PDF
10.68 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/527023
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact