Salvato in:
Dettagli Bibliografici
Autori principali: Rahman, Raiyan, Chowdhury, Mohsena, Tang, Yueyang, Gao, Huayi, Yin, George, Wang, Guanghui
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.15175
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909084577431552
author Rahman, Raiyan
Chowdhury, Mohsena
Tang, Yueyang
Gao, Huayi
Yin, George
Wang, Guanghui
author_facet Rahman, Raiyan
Chowdhury, Mohsena
Tang, Yueyang
Gao, Huayi
Yin, George
Wang, Guanghui
contents The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions. The LILA home composter presents a convenient means of recycling kitchen scraps and daily food waste into nutrient-rich, high-quality compost. To capture the nutritional information of the produced compost, we have created and annotated a large high-resolution image dataset of kitchen food waste with segmentation masks of 19 nutrition-rich categories. Leveraging this dataset, we benchmarked four state-of-the-art semantic segmentation models on food waste segmentation, contributing to the assessment of compost quality of Nitrogen, Phosphorus, or Potassium. The experiments demonstrate promising results of using segmentation models to discern food waste produced in our daily lives. Based on the experiments, SegFormer, utilizing MIT-B5 backbone, yields the best performance with a mean Intersection over Union (mIoU) of 67.09. Class-based results are also provided to facilitate further analysis of different food waste classes.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15175
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimation
Rahman, Raiyan
Chowdhury, Mohsena
Tang, Yueyang
Gao, Huayi
Yin, George
Wang, Guanghui
Computer Vision and Pattern Recognition
The escalating global concern over extensive food wastage necessitates innovative solutions to foster a net-zero lifestyle and reduce emissions. The LILA home composter presents a convenient means of recycling kitchen scraps and daily food waste into nutrient-rich, high-quality compost. To capture the nutritional information of the produced compost, we have created and annotated a large high-resolution image dataset of kitchen food waste with segmentation masks of 19 nutrition-rich categories. Leveraging this dataset, we benchmarked four state-of-the-art semantic segmentation models on food waste segmentation, contributing to the assessment of compost quality of Nitrogen, Phosphorus, or Potassium. The experiments demonstrate promising results of using segmentation models to discern food waste produced in our daily lives. Based on the experiments, SegFormer, utilizing MIT-B5 backbone, yields the best performance with a mean Intersection over Union (mIoU) of 67.09. Class-based results are also provided to facilitate further analysis of different food waste classes.
title Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.15175