Corvinus
Corvinus

Instance Segmentation in Industry 5.0 Applications Based on the Automated Generation of Point Clouds

Monsone, Cristina R. and Csapó, Ádám Balázs (2025) Instance Segmentation in Industry 5.0 Applications Based on the Automated Generation of Point Clouds. Acta Polytechnica Hungarica, 22 (6). pp. 25-46. DOI 10.12700/APH.22.6.2025.6.3

[img] PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB

Official URL: https://doi.org/10.12700/APH.22.6.2025.6.3


Abstract

In this paper, we explore the utility of classical neural network-based approaches, originally designed for processing 2D images, in semantic segmentation and object recognition tasks within the context of 3D point cloud images generated from handheld video recordings. Our investigation centers around the use of a custom-created, small-sized training dataset, consisting of 108 RGB images of humans and cobots in diverse industrial settings. This dataset allows us to demonstrate that flexible segmentation and recognition applications can be built even with a restricted dataset developed using widely available low-cost tools and modern convolutional neural net architectures. Downstream benefits of the approach include the ability to detect humans and human gestures, as well as to rapidly prototype digital twins in Industry 5.0 environments.

Item Type:Article
Uncontrolled Keywords:industrial image datasets; point-cloud generation; convolutional neural networks; instance segmentation
Divisions:Corvinus Institute for Advanced Studies (CIAS)
Subjects:Automatizálás, gépesítés
Computer science
DOI:10.12700/APH.22.6.2025.6.3
ID Code:10982
Deposited By: MTMT SWORD
Deposited On:06 Mar 2025 10:16
Last Modified:06 Mar 2025 10:16

Repository Staff Only: item control page

Downloads

Downloads per month over past year

View more statistics