Journal of Internet of Things and Convergence (사물인터넷융복합논문지)

The Korea Internet of Things Society (한국사물인터넷학회)
권호 표지
DOI QR코드

DOI QR Code

Enhanced Indoor Localization Scheme Based on Pedestrian Dead Reckoning and Kalman Filter Fusion with Smartphone Sensors

스마트폰 센서를 이용한 PDR과 칼만필터 기반 개선된 실내 위치 측위 기법

  • Harun Jamil (Department of Computer Engineering, Jeju National University) ;
  • Naeem Iqbal (Department of Computer Engineering, Jeju National University) ;
  • Murad Ali Khan (Department of Computer Engineering, Jeju National University) ;
  • Syed Shehryar Ali Naqvi (Big Data Research Center and Department of Computer Engineering, Jeju National University) ;
  • Do-Hyeun Kim (Big Data Research Center and Department of Computer Engineering, Jeju National University)
  • Received : 2024.07.10
  • Accepted : 2024.08.09
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Indoor localization is a critical component for numerous applications, ranging from navigation in large buildings to emergency response. This paper presents an enhanced Pedestrian Dead Reckoning (PDR) scheme using smartphone sensors, integrating neural network-aided motion recognition, Kalman filter-based error correction, and multi-sensor data fusion. The proposed system leverages data from the accelerometer, magnetometer, gyroscope, and barometer to accurately estimate a user's position and orientation. A neural network processes sensor data to classify motion modes and provide real-time adjustments to stride length and heading calculations. The Kalman filter further refines these estimates, reducing cumulative errors and drift. Experimental results, collected using a smartphone across various floors of University, demonstrate the scheme's ability to accurately track vertical movements and changes in heading direction. Comparative analyses show that the proposed CNN-LSTM model outperforms conventional CNN and Deep CNN models in angle prediction. Additionally, the integration of barometric pressure data enables precise floor level detection, enhancing the system's robustness in multi-story environments. Proposed comprehensive approach significantly improves the accuracy and reliability of indoor localization, making it viable for real-world applications.

실내 위치 측위는 대형 건물에서 내비게이션부터 비상 대응까지 다양한 애플리케이션이다. 본 논문에서는 스마트폰 센서를 이용하고 신경망 기반 동작 인식, 칼만 필터 기반 오류 수정, 다중 센서 데이터 융합을 통합한 향상된 PDR(Pedestrian Dead Reckoning) 기반 보행자 실내 위치 측위 기법을 제시한다. 제안된 기법은 가속도계, 자력계, 자이로스코프, 기압계의 데이터를 활용하여 사용자의 위치와 방향을 정확하게 측위하며, 신경망은 센서 데이터를 처리하여 동작 모드를 분류하고 보폭과 방향 계산에 대한 실시간 조정을 제공한다. 칼만 필터는 이러한 추정치를 더욱 구체화하여 누적 오류와 드리프트를 줄이며, 대형 건물의 여러 층에서 스마트폰을 사용하여 수집한 실험 결과는 수직 이동과 진행 방향 변화를 정확하게 추적하는 능력을 보여준다. 성능 비교 분석 결과에서 제안된 CNN-LSTM 모델은 각도예측에서 기존 CNN 및 Deep CNN 모델보다 성능이 뛰어난 것으로 나타났으며. 또한 기압 데이터를 통합하여 정확한 바닥 수준 감지가 가능해 다층 환경에서 시스템의 견고성을 향상시켰으며, 이 제안된 접근 방식은 실내 위치 파악의 정확성과 신뢰성을 크게 향상시켜 실제 응용 분야에서 활용 가능성이 높다고 판단된다.

Keywords

Acknowledgement

This work was supported by the 2024 education, research and student guidance grant funded by Jeju National University. Any correspondence related to this paper should be addressed to Do Hyeun Kim..

References

  1. Harle, R. (2013). A survey of indoor inertial positioning systems for pedestrians. IEEE Communications Surveys & Tutorials, 15(3), 1281-1293. https://doi.org/10.1109/SURV.2012.121912.00075
  2. Virrantaus, K.; Markkula, J.; Garmash, A.; Terziyan, V.; Veijalainen, J.; Katanosov, A.; Tirri, H. Developing GIS-supported location-based services. In Proceedings of the Second International Conference on Web Information Systems Engineering, Kyoto, Japan, pp.66-75, 2001. Virrantaus, K., Markkula, J., Garmash, A., Terziyan, V., Veijalainen, J., Katanosov, A., & Tirri, H. (2001, December).
  3. Grewal, M. S., Weill, L. R., & Andrews, A. P. (2007). Global positioning systems, inertial navigation, and integration. John Wiley & Sons.
  4. Bill, R., Cap, C., Kofahl, M., & Mundt, T. (2004). Indoor and outdoor positioning in mobile environments a review and some investigations on wlan positioning. Geographic Information Sciences, 10(2), 91-98.
  5. Wu, C.; Yang, Z.; Liu, Y. Wireless Indoor Localization. IEEE Trans. Parallel Distrib. Syst. pp.839-848, 2012.
  6. Bulusu, N., Heidemann, J., & Estrin, D. (2000). GPS-less low-cost outdoor localization for very small devices. IEEE personal communications, 7(5), 28-34. https://doi.org/10.1109/98.878533
  7. Liu, H., Darabi, H., Banerjee, P., & Liu, J. (2007). Survey of wireless indoor positioning techniques and systems. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 37(6), 1067-1080. https://doi.org/10.1109/TSMCC.2007.905750
  8. Jamil, F., Iqbal, N., Ahmad, S., & Kim, D. H. (2020). Toward accurate position estimation using learning to prediction algorithm in indoor navigation. Sensors, 20(16), 4410..
  9. Jamil, F., & Kim, D. H. (2019). Improving accuracy of the alpha-beta filter algorithm using an ANN-based learning mechanism in indoor navigation system. Sensors, 19(18), 3946..
  10. Jamil, F., & Kim, D. (2021). Enhanced Kalman filter algorithm using fuzzy inference for improving position estimation in indoor navigation. Journal of Intelligent & Fuzzy Systems, 40(5), 8991-9005. https://doi.org/10.3233/JIFS-201352
  11. Jamil, H., Qayyum, F., Jamil, F., & Kim, D. H. (2021). Enhanced pdr-ble compensation mechanism based on hmm and awcla for improving indoor localization. Sensors, 21(21), 6972..
  12. Dobbins, C., Rawassizadeh, R., & Momeni, E. (2017). Detecting physical activity within lifelogs towards preventing obesity and aiding ambient assisted living. Neurocomputing, 230, 110-132.. https://doi.org/10.1016/j.neucom.2016.02.088
  13. Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2015). Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2625-2634).
  14. Burgos, C. P., Gartner, L., Ballester, M. A. G., Noailly, J., Stocker, F., Schonfelder, M., ... & Tassani, S. (2020). In-ear accelerometer-based sensor for gait classification. IEEE Sensors Journal, 20(21), 12895-12902. https://doi.org/10.1109/JSEN.2020.3002589
  15. Chan, T. F., Golub, G. H., & LeVeque, R. J. (1982). Updating formulae and a pairwise algorithm for computing sample variances. In COMPSTAT 1982 5th Symposium held at Toulouse 1982: Part I: Proceedings in Computational Statistics (pp. 30-41). Physica-Verlag HD.