Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications

Jhen Kai Liao, Kai-Wei Chiang, Hsiu-Wen Chang, Yu Hua Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recently, indoor navigation has become popular because of the popular smartphone and the growth of Location Based Services (LBS). Pedestrian Dead Reckoning (PDR) has the good potential to confront the challenges in environments lacking a Global Navigation Satellite System (GNSS). However, PDR has inherent errors that accumulated step by step. An image-based localization can as an aiding system, because virtually all mobile devices contain a basic camera sensor. However, the image-based localization requires successive and overlapped images for continuously positioning. In addition, the solutions provided by either image-based localization or a PDR are usually in a relative coordinate system. Therefore, this study proposes a system, which uses space resection-aided PDR with georeferenced images of a previously mapped environment. In order to implement the procedure automatically and reduce the image processing, this study further uses markers in the georeferenced images. After that, Artificial Neural Network (ANN) is novel applied to estimate the distance between the marker and camera. Since the marker is also georeferenced, the camera position is updated through the detected georeferenced marker, estimated distance, and orientation from inertial sensor, and then update the PDR result. The indoor mobile mapping system (IMMS) is used for the effective production of georeferenced images. The result shows the proposed system is able to initialize in indoor without manually given initial position and provides long-term accurate navigation.

Original languageEnglish
Title of host publicationProceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538637555
DOIs
Publication statusPublished - 2018 Dec 4
Event5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018 - Wuhan, China
Duration: 2018 Mar 222018 Mar 23

Publication series

NameProceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018

Other

Other5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018
CountryChina
CityWuhan
Period18-03-2218-03-23

Fingerprint

dead reckoning
Dead Reckoning
navigation
Artificial Neural Network
Navigation
Cameras
Neural networks
markers
Location based services
Smartphones
Sensors
Camera
Mobile devices
cameras
Image processing
Satellites
Relative coordinates
Inertial Sensors
satellite navigation systems
sensors

All Science Journal Classification (ASJC) codes

  • Computational Mathematics
  • Control and Optimization
  • Instrumentation

Cite this

Liao, J. K., Chiang, K-W., Chang, H-W., & Li, Y. H. (2018). Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications. In Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018 [8559833] (Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UPINLBS.2018.8559833
Liao, Jhen Kai ; Chiang, Kai-Wei ; Chang, Hsiu-Wen ; Li, Yu Hua. / Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications. Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. (Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018).
@inproceedings{28dff78c5bcd4dae98f2c1b118f8b3ca,
title = "Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications",
abstract = "Recently, indoor navigation has become popular because of the popular smartphone and the growth of Location Based Services (LBS). Pedestrian Dead Reckoning (PDR) has the good potential to confront the challenges in environments lacking a Global Navigation Satellite System (GNSS). However, PDR has inherent errors that accumulated step by step. An image-based localization can as an aiding system, because virtually all mobile devices contain a basic camera sensor. However, the image-based localization requires successive and overlapped images for continuously positioning. In addition, the solutions provided by either image-based localization or a PDR are usually in a relative coordinate system. Therefore, this study proposes a system, which uses space resection-aided PDR with georeferenced images of a previously mapped environment. In order to implement the procedure automatically and reduce the image processing, this study further uses markers in the georeferenced images. After that, Artificial Neural Network (ANN) is novel applied to estimate the distance between the marker and camera. Since the marker is also georeferenced, the camera position is updated through the detected georeferenced marker, estimated distance, and orientation from inertial sensor, and then update the PDR result. The indoor mobile mapping system (IMMS) is used for the effective production of georeferenced images. The result shows the proposed system is able to initialize in indoor without manually given initial position and provides long-term accurate navigation.",
author = "Liao, {Jhen Kai} and Kai-Wei Chiang and Hsiu-Wen Chang and Li, {Yu Hua}",
year = "2018",
month = "12",
day = "4",
doi = "10.1109/UPINLBS.2018.8559833",
language = "English",
series = "Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018",
address = "United States",

}

Liao, JK, Chiang, K-W, Chang, H-W & Li, YH 2018, Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications. in Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018., 8559833, Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018, Institute of Electrical and Electronics Engineers Inc., 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018, Wuhan, China, 18-03-22. https://doi.org/10.1109/UPINLBS.2018.8559833

Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications. / Liao, Jhen Kai; Chiang, Kai-Wei; Chang, Hsiu-Wen; Li, Yu Hua.

Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8559833 (Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications

AU - Liao, Jhen Kai

AU - Chiang, Kai-Wei

AU - Chang, Hsiu-Wen

AU - Li, Yu Hua

PY - 2018/12/4

Y1 - 2018/12/4

N2 - Recently, indoor navigation has become popular because of the popular smartphone and the growth of Location Based Services (LBS). Pedestrian Dead Reckoning (PDR) has the good potential to confront the challenges in environments lacking a Global Navigation Satellite System (GNSS). However, PDR has inherent errors that accumulated step by step. An image-based localization can as an aiding system, because virtually all mobile devices contain a basic camera sensor. However, the image-based localization requires successive and overlapped images for continuously positioning. In addition, the solutions provided by either image-based localization or a PDR are usually in a relative coordinate system. Therefore, this study proposes a system, which uses space resection-aided PDR with georeferenced images of a previously mapped environment. In order to implement the procedure automatically and reduce the image processing, this study further uses markers in the georeferenced images. After that, Artificial Neural Network (ANN) is novel applied to estimate the distance between the marker and camera. Since the marker is also georeferenced, the camera position is updated through the detected georeferenced marker, estimated distance, and orientation from inertial sensor, and then update the PDR result. The indoor mobile mapping system (IMMS) is used for the effective production of georeferenced images. The result shows the proposed system is able to initialize in indoor without manually given initial position and provides long-term accurate navigation.

AB - Recently, indoor navigation has become popular because of the popular smartphone and the growth of Location Based Services (LBS). Pedestrian Dead Reckoning (PDR) has the good potential to confront the challenges in environments lacking a Global Navigation Satellite System (GNSS). However, PDR has inherent errors that accumulated step by step. An image-based localization can as an aiding system, because virtually all mobile devices contain a basic camera sensor. However, the image-based localization requires successive and overlapped images for continuously positioning. In addition, the solutions provided by either image-based localization or a PDR are usually in a relative coordinate system. Therefore, this study proposes a system, which uses space resection-aided PDR with georeferenced images of a previously mapped environment. In order to implement the procedure automatically and reduce the image processing, this study further uses markers in the georeferenced images. After that, Artificial Neural Network (ANN) is novel applied to estimate the distance between the marker and camera. Since the marker is also georeferenced, the camera position is updated through the detected georeferenced marker, estimated distance, and orientation from inertial sensor, and then update the PDR result. The indoor mobile mapping system (IMMS) is used for the effective production of georeferenced images. The result shows the proposed system is able to initialize in indoor without manually given initial position and provides long-term accurate navigation.

UR - http://www.scopus.com/inward/record.url?scp=85060193215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060193215&partnerID=8YFLogxK

U2 - 10.1109/UPINLBS.2018.8559833

DO - 10.1109/UPINLBS.2018.8559833

M3 - Conference contribution

T3 - Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018

BT - Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Liao JK, Chiang K-W, Chang H-W, Li YH. Artificial neural networks aided image localization for pedestrian dead reckoning for indoor navigation applications. In Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8559833. (Proceedings of 5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2018). https://doi.org/10.1109/UPINLBS.2018.8559833