Yan, J;
He, G;
Basiri, A;
Hancock, C;
(2018)
Vision-Aided Indoor Pedestrian Dead Reckoning.
In:
Proceedings of the 2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).
IEEE: Houston, TX, USA.
Preview |
Text
Basiri_Vision-Aided Indoor Pedestrian Dead Reckoning-2.pdf - Accepted Version Download (698kB) | Preview |
Abstract
Vision-aided inertial navigation has become a more popular method for indoor positioning recently. This popularity is basically due to the development of light-weighted and low-cost Micro Electro-Mechanical Systems (MEMS) as well as advancement and availability of CCD cameras in public indoor area. While the use of inertial sensors and cameras are limited to the challenge of drift accumulation and object detection in line of sight, respectively, the integration of these two sensors can compensate their drawbacks and provide more accurate positioning solutions. This study builds up upon earlier research on “Vision-Aided Indoor Pedestrian Tracking System”, to address challenges of indoor positioning by providing more accurate and seamless solutions. The study improves the overall design and implementation of inertial sensor fusion for indoor applications. In this regard, genuine indoor maps and geographical information, i.e. digitized floor plans, are used for visual tracking application the pilot study. Both of inertial positioning and visual tracking components can work stand-alone with additional location information from the maps. In addition, while the visual tracking component can help to calibrate pedestrian dead reckoning and provides better accuracy, inertial sensing module can alternatively be used for positioning and tracking when the user cannot be detected by the camera until being detected in video again. The mean accuracy of this positioning system is 10.98% higher than uncalibrated inertial positioning during experiment.
| Type: | Proceedings paper |
|---|---|
| Title: | Vision-Aided Indoor Pedestrian Dead Reckoning |
| Event: | 2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) |
| Location: | Texas, USA |
| Dates: | 14 May 2018 - 17 May 2018 |
| ISBN-13: | 978-1-5386-2222-3 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/I2MTC.2018.8409599 |
| Publisher version: | https://doi.org/10.1109/I2MTC.2018.8409599 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Pedestrian dead reckoning; pedestrian detection; deep learning; sensor fusion; indoor optical positioning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Centre for Advanced Spatial Analysis |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10044615 |
Archive Staff Only
 |
View Item |
