EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Supplementation of synthetic object replicas for increasing precision of microrobot trajectory keypoints

Modris Laizans, Janis Arents, Oskars Vismanis, Vytautas Bučinskas, Andrius Dzedzickis, Modris Greitans

Robotic Systems and Applications · 2023

DOI: 10.21595/rsa.2023.23128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotic Systems and Applications, 2023. Verfasst von Modris Laizans und 5 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial neural networks are becoming more popular with the development of artificial intelligence. These networks require large amounts of data to function effectively, especially in the field of computer vision. The quality of an object detector is primarily determined by its architecture, but the quality of the data it uses is also important. In this study, we explore the use of novel data set enhancement technique to improve the performance of the YOLOv5 object detector. Overall, we investigate three methods: first, a novel approach using synthetic object replicas to augment the existing real data set without changing the size of the data set; second - rotation augmentation data set propagating technique and their symbiosis, third, only one required class is supplemented. The solution proposed in this article improves the data set with a help of supplementation and augmentation. Lower the influence of the imbalanced data sets by data supplementation with synthetic yeast cell replicas. We also determine the average supplementation values for the data set to determine how many percent of the data set is most effective for the supplementation.

Zitieren

APA

Laizans, M., Arents, J., Vismanis, O., Bučinskas, V., Dzedzickis, A., & Greitans, M. (2023). Supplementation of synthetic object replicas for increasing precision of microrobot trajectory keypoints. Robotic Systems and Applications. https://doi.org/10.21595/rsa.2023.23128

Vancouver

Laizans M, Arents J, Vismanis O, Bučinskas V, Dzedzickis A, Greitans M. Supplementation of synthetic object replicas for increasing precision of microrobot trajectory keypoints. Robotic Systems and Applications. 2023. doi:10.21595/rsa.2023.23128

BibTeX
@article{Laizans2023,
  author = {Laizans, Modris and Arents, Janis and Vismanis, Oskars and Bučinskas, Vytautas and Dzedzickis, Andrius and Greitans, Modris},
  title = {Supplementation of synthetic object replicas for increasing precision of microrobot trajectory keypoints},
  journal = {Robotic Systems and Applications},
  year = {2023},
  doi = {10.21595/rsa.2023.23128}
}
Kostenlos starten →