A machine learning-based method in body movement tracking with a small number of sensors
155 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.FEE.2022.171-176Keywords:
Inertial Measurement Unit - IMU; Decision Tree Regression (DTR).Abstract
Most of the current body sensing devices are composed of inertial measurement units (IMUs). The IMU sensors are placed at a different position on the human body and sense their position, rotation, and tilt angle in space, thereby interpolating the movement of parts and the entire human body. Although IMU sensors have high accuracy and fast processing speed, they suffer from a major limitation of being susceptible to external magnetic field sources. This makes the process of re-interpolating the human body become inaccurate in an environment where many strong magnetic fields exist such as metal frames, computers, etc. In this paper, we propose a model to predict the postures of the upper human body, from 03 stable inputs (head, right hand, left hand), thereby reducing the usage of IMU sensors.
References
[1]. Robert-Lachaine, Xavier & Mecheri, Hakim & Larue, Christian & Plamondon, Andre. “Effect of local magnetic field disturbances on inertial measurement units accuracy”. Applied Ergonomics. 63, (2017). 123-132. 10.1016/j.apergo.2017.04.011. DOI: https://doi.org/10.1016/j.apergo.2017.04.011
[2]. Groves, P.D. “Navigation using inertial sensors [Tutorial]”. IEEE Aerosp. Electron. Syst. Mag., 30, 42–69, (2015). DOI: https://doi.org/10.1109/MAES.2014.130191
[3]. Solin, A.; Cortes, S.; Rahtu, E.; Kannala, J. “PIVO: Probabilistic inertial-visual odometry for occlusion-robust navigation”. In Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, pp. 616–625, (2018). DOI: https://doi.org/10.1109/WACV.2018.00073
[4]. Solin, A.; Cortes, S.; Rahtu, E.; Kannala, J. “Inertial odometry on handheld smartphones”. In Proceedings of the 2018 21st International Conference on Information Fusion (FUSION), Cambridge, UK, pp. 1–5, (2018). DOI: https://doi.org/10.23919/ICIF.2018.8455482
[5]. Clark, R.; Wang, S.; Wen, H.; Markham, A.; Trigoni, N. “Vinet: Visual-inertial odometry as a sequence-to-sequence learning problem”. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA, (2017). DOI: https://doi.org/10.1609/aaai.v31i1.11215
[6]. Chen, C.; Rosa, S.; Miao, Y.; Lu, C.X.; Wu, W.; Markham, A.; Trigoni, N. “Selective sensor fusion for neural visual-inertial odometry”. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 10542–10551, (2019). DOI: https://doi.org/10.1109/CVPR.2019.01079
[7]. Li, X.F.; Mao, Y.L.; Xie, L.; Chen, J.B.; Song, C.L. “Applications of zero-velocity detector and Kalman filter in zero velocity update for inertial navigation system”. In Proceedings of the 2014 IEEE Chinese Guidance, Navigation and Control Conference, Yantai, China, pp. 1760–1763, (2014).
[8]. Li, L.; Pan, Y.; Lee, J.K.; Ren, C.; Liu, Y.; Grejner-Brzezinska, D.A.; Toth, C.K. “Cart-mounted geolocation system for unexploded ordnance with adaptive ZUPT assistance”. IEEE Trans. Instrum. Meas. 61, 974–979, (2012). DOI: https://doi.org/10.1109/TIM.2011.2179820
[9]. Yao, Y.; Xu, X.; Xu, X. “An IMM-aided ZUPT methodology for an INS/DVL integrated navigation system”. Sensors, 17, 2030, (2017). DOI: https://doi.org/10.3390/s17092030
[10]. Silva do Monte Lima, J.P.; Uchiyama, H.; Taniguchi, R.I. “End-to-End Learning Framework for IMU-Based 6-DOF Odometry”. Sensors, 19, 3777, (2019). DOI: https://doi.org/10.3390/s19173777
