OS15-5 Individual recognition of food in bulk by using 3D model of food

Title:	OS15-5 Individual recognition of food in bulk by using 3D model of food
Publication:	ICAROB2025
Volume:	30
Pages:	455-459
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2025.OS15-5
Author(s):	Yuya Otsu, Tokuo Tsuji, Tatsuhiro Hiramitsu, Hiroaki Seki
Publication Date:	February 13, 2025
Keywords:	Instance segmentation, Color space, 3D model
Abstract:	In this paper, we propose a method of individual recognition of food in bulk by using 3D model of food. First, color images and depth images of them are generated by using 3D model of food and physics engine of simulator. Then, color and depth composite images are created by converting two channels from color images and one channel from depth images. In the experiments, the accuracy of individual recognition of food in bulk with color and depth composite images are shown to compare the accuracy with only color images.
PDF File:	https://alife-robotics.co.jp/members2025/icarob/data/html/data/OS/OS15/OS15-5.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/