EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation

Piotr Wozniak iD, Dominik Ozog iD

Sensors · 2023

DOI: 10.3390/s23136134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Piotr Wozniak und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer and Control Engineering, Faculty of Electrical and Computer Engineering, Rzeszow University of Technology, Al. Powstańców Wars…. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The article presents an algorithm for the multi-domain visual recognition of an indoor place. It is based on a convolutional neural network and style randomization. The authors proposed a scene classification mechanism and improved the performance of the models based on synthetic and real data from various domains. In the proposed dataset, a domain change was defined as a camera model change. A dataset of images collected from several rooms was used to show different scenarios, human actions, equipment changes, and lighting conditions. The proposed method was tested in a scene classification problem where multi-domain data were used. The basis was a transfer learning approach with an extension style applied to various combinations of source and target data. The focus was on improving the unknown domain score and multi-domain support. The results of the experiments were analyzed in the context of data collected on a humanoid robot. The article shows that the average score was the highest for the use of multi-domain data and data style enhancement. The method of obtaining average results for the proposed method reached the level of 92.08%. The result obtained by another research team was corrected.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsAlgorithmsLearningLightingNeural Networks, Computer

Stichwörter der Autor:innen

CNNsdomain generalizationmulti-domain learningtransfer learningvisual place recognition

Autor:innen und Institutionen

  • Department of Computer and Control Engineering, Faculty of Electrical and Computer Engineering, Rzeszow University of Technology, Al. Powstańców Warszawy 12, 35-959 Rzeszow, Poland.

ORCID-Profile: Piotr Wozniak, Dominik Ozog

Zitieren

APA

Wozniak, P., & Ozog, D. (2023). Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation. Sensors. https://doi.org/10.3390/s23136134

Vancouver

Wozniak P, Ozog D. Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation. Sensors. 2023. doi:10.3390/s23136134

BibTeX
@article{Wozniak2023,
  author = {Wozniak, Piotr and Ozog, Dominik},
  title = {Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23136134}
}
Kostenlos starten →