본문 바로가기
KERD
논문KCI 등재

스마트폰 내장 센서와 SimilarNet을 이용한 보행자 방향 감지

Pedestrian direction detection using smartphone integrated sensors and deep learning

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류컴퓨터학

초록

본 논문에서는 SimilarNet을 이용한 1:1 비교 기법을 시계열 분석에 적용한 보행 상태 추정 모델을 제안한다. SimilarNet은 1:1 비교에 특화된 모델을 설계하기 위한 딥러닝 레이어이며, 이를 응용하면 시계열의 분류 등 다양한 문제를 해결할 수 있다. 제안 모델은 SimilarNet을 이용하여 사용자의 보행 상태에 따라 분류된 센서 측정 데이터와 현재 시점의 센서 측정 데이터를 1:1로 비교하여 사용자 보행 상태를 추정한다. 실험 결과 본 논문에서 제안하는 모델은 동일한 임베딩 모델을 사용한 기존 분류 모델보다 44.11% 향상된 정확도와 기존 모델보다 30% 우수한 학습 성공률을 보인다.

Abstract

In this paper, we propose a pedestrian walking state estimation model using SimilarNet. The SimilarNet is a deep learning layer to perform the one-to-one comparison operation and is applicable to various problems such as time-series classification. Using the SimilarNet, the proposed model estimates the user's walking state by comparing sensor measurement data classified according to the user's walking state with sensor measurement data at a specific time point. Extensive experiments show that the proposed model achieves a 44.11% improvement in accuracy and a 30% higher learning success rate compared to classification models based on the same embedding model.

참고문헌 (30)

  1. J. Yoo, "Trends in Technical Development and Standardization of Indoor Location Based Services", Electronics and Telecommunications Trends, 29(5), pp.51~60 (2014)
  2. C. Yi, "SimilarNet: Pair wise Similarity Comparator Layer for Versatile Comparison", TechRxiv, ~ (2023)
  3. A Million!, "Indoor Positioning and Navigation with Camera Phones", IEEE Pervasive Computing, 8(2), pp.22~31 (2009)
  4. C. W. Lee., "Improving Mobility for the Visually Impaired: A Wearable Indoor Positioning System Based on Visual Markers", IEEE Consumer Electronics Magazine, 7(3), pp.12~20 (2018)
  5. R Mautz, "Survey of optical indoor positioning systems", 2011 International Conference on Indoor Positioning and Indoor Navigation, pp.1~7 (2011)
  6. A Raza, "Comparing and Evaluating Indoor Positioning Techniques", 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (2021)
  7. S Beauregard, "Pedestrian Dead Reckoning(PDR)and GPS for Indoor Positioning", Proc, of 3rd Workshop on Positioning. Navigation and Communication (WFNC) (2006)
  8. A R. Jimenez, "A comparison of Pedestrian Dead-Reckoning algorithms using a low-cost MEMS IMU", 2009 IEEE International Symposium on Intelligent Signal Processing (2009)
  9. W. Kang, "SmartPDR: Smart-phone-Based Pedestrian Dead Reckoning for Indoor Localization", IEEE Sensors Journal, 15(5), pp.2906~2916 (2015)
  10. Y. Wu, "A Survey of the Research Status of Pedestrian Dead Reckoning Systems Based on Inertial Sensors", International Journal of Automation and Computing, 16, pp.65~83 (2019)
  11. X. Hou, "Pedestrian Dead Reckoning With Wearable Sensors : A Systematic Review", IEEE Sensors Jounal, 21(1), pp.143~152 (2021)
  12. O. Asraf, "PDRNet: A Deep-Learning Pedestrian Dead Reckoning Framework", IEEE Sensors Journal, 22(6), pp.4932~4939 (2022)
  13. H. Durrant-Whyte, "Simultaneous localization and mapping: part I", IEEE Robotics & Automation Magazine, 13(2), pp.99~110 (2006)
  14. T. Bailey, "Simultaneous localization and mapping (SLAM): part II", IEEE Robotics & Automation Magazine, 13(3), pp.108~117 (2006)
  15. J. Fuentes-Pacheco, "Visual simultaneous localization and mapping: a survey", Artificial Intelligence Review, 43, pp.55~81 (2015)
  16. S. Saeedi, "Multiple robot simultaneous localization and mapping: A review", Journal of Field Robotics, 33(1), pp.3~46 (2016)
  17. S. Thrun, "Robotics and cognitive approaches to spatial mapping", pp.13~41 (2008)
  18. C. Cadena et al., "Past. Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age", IEEE Transactions on Robotics, 32(6), pp.1309~1332 (2016)
  19. J. A. Placed, "A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers", IEEE Transactions on Robotics, 39(3), pp.1686~1705 (2023)
  20. R. Z. U. Rehman et al., "Accelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease : What Counts?", IEEE Open Journal of Engineering in Medicine and Biology, 1, pp.65~73 (2020)
  21. T. Ebara et al, "Reliability of smartphone-based gait measurements for quantification of physical activity", inactivity levels, 2017, pp.59(6), 506~512
  22. O. S. Schneider et al, "Real-time gait classification for persuasive smartphone apps : Structuring the literature and pushing the limits", Proceedings of the 2013 international conference on Intelligent user interfaces (IUI '13), pp.161~172 (2013)
  23. G. Zhao, "3D gait recognition using multiple cameras", 7th International Conference on Automatic Face and Gesture Recognition (FGR06), pp.529~534 (2006)
  24. E. Stone, "Evaluation of an Inexpensive Depth Camera for In-home Gait Assessment", Journal of Ambient Intelligence and Smart Environments, 3(4), pp.349~361 (2011)
  25. M. Nieto-Hidalgo et al., "A vision based proposed for classification of normal and abnormal gait using RGB camera", Journal of Biomedical Informatics, 63, pp.82~89 (2016)
  26. D. M. Peters et al., "Utilization of wearable technology to assess gait and mobility poststroke: a systematic review", Journal of NeuroEngineering and Rehabilitation, 18(67) (2021)
  27. J. S. Bridle, "Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters", Advances in Neural Information Processing Systems, 2, pp.211~217 (1989)
  28. S. Chopra, "Learning a similarity metric discriminatively. with application to face verification", 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 1, pp.539~546 (2005)
  29. F. Sung, "Learning to compare: Relation network for few-shot learning", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1199~1208 (2018)
  30. J. Snell, "Prototypical Networks for Few-shot Learning", Advances in Neural Information Processing Systems, 30 (2017)

관련 논문AI추천

이 간행물의 다른 논문 (9건)