JOURNAL ARTICLE
Methods for volume inference of non-medical objects from images: A short review.
Published In: Journal of Ambient Intelligence & Smart Environments, 2024, v. 16, n. 4. P. 541 1 of 3
Database: Applied Science & Technology Source Ultimate 2 of 3
Authored By: Nabitchita, Baticté; Gonçalves, Norberto Jorge; Coelho, Paulo Jorge; Pimenta, Luís; Zdravevski, Eftim; Lameski, Petre; Costa, Mónica; Neves, Paulo Alexandre; Pires, Ivan Miguel 3 of 3
Abstract
This article systematically reviews image processing techniques for measuring object volume from 2D images, analyzing 25 studies published between 2010 and 2023. It highlights a range of computational methods, including classical computer vision approaches and deep learning models such as convolutional neural networks (CNNs), applied primarily to food-related objects but also to various other items and scenarios. The review identifies key datasets used in the field, notes the diversity of evaluation metrics, and discusses applications in areas like dietary assessment, object monitoring, and 3D reconstruction. While advancements in accuracy and methodology are evident, challenges remain regarding hardware limitations, model generalization, and dataset incompatibility, underscoring the need for more robust, efficient, and real-time capable volume estimation solutions.
Additional Information
- Source:Journal of Ambient Intelligence & Smart Environments. 2024/12, Vol. 16, Issue 4, p541
- Document Type:Article
- Subject Area:Mathematics
- Publication Date:2024
- ISSN:18761364
- DOI:10.3233/AIS-230193
- Accession Number:181971849
- Copyright Statement:Copyright of Journal of Ambient Intelligence & Smart Environments is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Looking to go deeper into this topic? Look for more articles on EBSCOhost.