Abstract
At present, inertial motion capture systems are widely used by consumer users due to their advantages of easy deployment and low price. The inertial sensor itself does not accurately locate itself in 3D space. The most accurate localization method is currently represented by the algorithm of forward kinematic estimation of crotch position, and the accurate estimation of this algorithm needs to be based on the accurate judgment of foot-ground contact. In this work, we implemented plain Bayesian, decision tree, random forest, SVM, and GBDT models to find the model with the highest recognition rate of classified foot-ground contact states. This work evaluates the quality of each algorithm in terms of computational speed and accuracy, achieving SOTA under the condition of wearing only crotch, left and right thigh, and left and right calf IMUs compared to most people in the field using 17 IMUs for the whole body. Finally, this paper uses SVM models to classify foot-ground contact states for captured poses, yielding an average foot-ground contact accuracy of 97% for various motions. The method in this paper is applicable to any inertial motion capture system and satisfies the accuracy of an inertial motion capture system for foot-ground contact detection, providing kinematic constraints for pose estimation and global position estimation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
XsensMVN (2019). https://www.xsens.com/products/xsens-mvn-analyze/
Perception Neuron (2019). http://www.neuronmocap.com/
Roetenberg, D., Luinge, H., Slycke, P.: Xsens MVN: full 6DOF human motion tracking using miniature inertial sensors. Xsens Motion Technologies BV (2009)
Yan, H., Shan, Q., Furukawa, Y.: RIDI: robust IMU double integration. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 641–656. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_38
Suresh, R., Sridhar, V., Pramod, J., Talasila, V.: Zero Velocity Potential Update (ZUPT) as a Correction Technique. In: 2018 3rd International Conference On Internet Of Things: Smart Innovation And Usages (IoT-SIU), pp. 1–8 (2018)
Zampella, F., Jiménez, A., Seco, F., Prieto, J., Guevara, J.: Simulation of foot-mounted IMU signals for the evaluation of PDR algorithms. In: 2011 International Conference On Indoor Positioning And Indoor Navigation, pp. 1–7 (2011)
Wang, Q., Guo, Z., Sun, Z., Cui, X., Liu, K.: Research on the forward and reverse calculation based on the adaptive zero-velocity interval adjustment for the foot-mounted inertial pedestrian-positioning system. Sensors 18, 1642 (2018). https://www.mdpi.com/1424-8220/18/5/1642
Manchola, M., Bernal, M., Múnera, M., Cifuentes, C.: Gait phase detection for lower-limb exoskeletons using foot motion data from a single inertial measurement unit in hemiparetic individuals. Sensors 19, 2988 (2019)
Zhen, T., Yan, L., Yuan, P.: Walking gait phase detection based on acceleration signals using LSTM-DNN algorithm. Algorithms 12, 253 (2019)
Ma, H., Yan, W., Yang, Z., Liu, H.: Real-time foot-ground contact detection for inertial motion capture based on an adaptive weighted Naive Bayes model. IEEE Access 7, 130312–130326 (2019)
Miezal, M., Taetz, B., Bleser, G.: Real-time inertial lower body kinematics and ground contact estimation at anatomical foot points for agile human locomotion. In: 2017 IEEE International Conference On Robotics And Automation (ICRA), pp. 3256–3263 (2017)
Hu, J., Cao, H., Zhang, Y., Zhang, Y.: Wearable plantar pressure detecting system based on FSR. In: 2018 2nd IEEE Advanced Information Management, Communicates, Electronic And Automation Control Conference (IMCEC), pp. 1687–1691 (2018)
Ma, H., Liao, W.: Human gait modeling and analysis using a semi-Markov process with ground reaction forces. IEEE Trans. Neural Syst. Rehabilit. Eng. 25, 597–607 (2017)
ESP-Now (2022). https://www.espressif.com.cn/en/products/software/esp-now/overview
Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and regression trees. (Routledge 2017)
Ho, T.: Random decision forests. In: Proceedings Of 3rd International Conference On Document Analysis And Recognition, vol. 1, pp. 278–282 (1995)
Zhang, Z., Jung, C.: GBDT-MO: gradient-boosted decision trees for multiple outputs. IEEE Trans. Neural Netw. Learn. Syst. 32, 3156–3167 (2021)
Huang, Y., Kaufmann, M., Aksan, E., Black, M., Hilliges, O., Pons-Moll, G.: Deep inertial poser learning to reconstruct human pose from SparseInertial measurements in real time. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37, 1–15 (2018)
Karl Pearson, F.R.S.: LIII. On lines and planes of closest fit to systems of points in space. London Edinburgh Dublin Philosop. Mag. J. Sci. 2, 559–572 (1901)
Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2, 1–27 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xia, D., Zhu, Y., Zhang, H. (2023). Real-Time Inertial Foot-Ground Contact Detection Based on SVM. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1793. Springer, Singapore. https://doi.org/10.1007/978-981-99-1645-0_44
Download citation
DOI: https://doi.org/10.1007/978-981-99-1645-0_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1644-3
Online ISBN: 978-981-99-1645-0
eBook Packages: Computer ScienceComputer Science (R0)