Physische Intelligenz Article 2017

A deep learning based fusion of RGB camera information and magnetic localization information for endoscopic capsule robots

41315 2017 39 fig3 html

A reliable, real time localization functionality is crutial for actively controlled capsule endoscopy robots, which are an emerging, minimally invasive diagnostic and therapeutic technology for the gastrointestinal (GI) tract. In this study, we extend the success of deep learning approaches from various research fields to the problem of sensor fusion for endoscopic capsule robots. We propose a multi-sensor fusion based localization approach which combines endoscopic camera information and magnetic sensor based localization information. The results performed on real pig stomach dataset show that our method achieves sub-millimeter precision for both translational and rotational movements.

Author(s): Turan, Mehmet and Shabbir, Jahanzaib and Araujo, Helder and Konukoglu, Ender and Sitti, Metin
Journal: International Journal of Intelligent Robotics and Applications
Volume: 1
Number (issue): 4
Pages: 442--450
Year: 2017
Bibtex Type: Article (article)
DOI: https://doi.org/10.1007/s41315-017-0039-1
Electronic Archiving: grant_archive

BibTex

@article{Turan2017,
  title = {A deep learning based fusion of RGB camera information and magnetic localization information for endoscopic capsule robots},
  journal = {International Journal of Intelligent Robotics and Applications},
  abstract = {A reliable, real time localization functionality is crutial for actively controlled capsule endoscopy robots, which are an emerging, minimally invasive diagnostic and therapeutic technology for the gastrointestinal (GI) tract. In this study, we extend the success of deep learning approaches from various research fields to the problem of sensor fusion for endoscopic capsule robots. We propose a multi-sensor fusion based localization approach which combines endoscopic camera information and magnetic sensor based localization information. The results performed on real pig stomach dataset show that our method achieves sub-millimeter precision for both translational and rotational movements.},
  volume = {1},
  number = {4},
  pages = {442--450},
  year = {2017},
  slug = {turan2017},
  author = {Turan, Mehmet and Shabbir, Jahanzaib and Araujo, Helder and Konukoglu, Ender and Sitti, Metin}
}