Ari Yair Barrera-Animas
Generating real-world-like labelled synthetic datasets for construction site applications
Yair Barrera-Animas, Ari; Davila Delgado, Manuel
Authors
Manuel Davila Delgado Manuel.Daviladelgado@uwe.ac.uk
Associate Professor - AR/VR Development with Artificial Intelligence
Abstract
Having synthetic image generation and automatic labelling as two separate processes remains one of the main limitations of automatic generation of large real-world synthetic datasets. To overcome this drawback, a methodology to perform both tasks in a simultaneous and automatic manner is proposed. To resemble real-world scenarios, a diverse set of rendering configurations of illumination, locations, and sizes are presented. For testing, three synthetic datasets (S, M and SM), oriented to the construction field, were generated. Faster R-CNN, RetinaNet, and YoloV4 detection algorithms were used to independently evaluate the datasets using the COCO evaluation metrics and the PascalVOC Mean Average Accuracy metric. Results show that, in general, the S dataset performed 1.2% better in the evaluation metrics and that the SM dataset obtained better plots of training and validation loss curves in each detector; highlighting the combinational usage of images with single and multiple objects as a better generalisation approach.
Citation
Yair Barrera-Animas, A., & Davila Delgado, M. (2023). Generating real-world-like labelled synthetic datasets for construction site applications. Automation in Construction, 151, Article 104850. https://doi.org/10.1016/j.autcon.2023.104850
Journal Article Type | Article |
---|---|
Acceptance Date | Mar 21, 2023 |
Online Publication Date | Apr 12, 2023 |
Publication Date | Jul 1, 2023 |
Deposit Date | Apr 12, 2023 |
Publicly Available Date | Apr 18, 2023 |
Journal | Automation in Construction |
Print ISSN | 0926-5805 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 151 |
Article Number | 104850 |
DOI | https://doi.org/10.1016/j.autcon.2023.104850 |
Keywords | Object detection, Synthetic dataset, Construction field, Auto-annotation |
Public URL | https://uwe-repository.worktribe.com/output/10622757 |
Publisher URL | https://www.sciencedirect.com/science/article/pii/S0926580523001103 |
Files
Generating real-world-like labelled synthetic datasets for construction site applications
(4.1 Mb)
PDF
Licence
http://creativecommons.org/licenses/by/4.0/
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
You might also like
Monitoring student activities with smartwatches: On the academic performance enhancement
(2019)
Journal Article
HyRA: A hybrid recommendation algorithm focused on smart POI. Ceutà as a study scenario
(2018)
Journal Article
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search