Abstract
Gait information is a useful biometric because it is a user-friendly property and gait is hard to mimic exactly, even by skillful attackers. Most conventional gait authentication schemes assume cooperation by the subjects being recognized. Lack of cooperation could be an obstacle for automated tracking of users and many commercial users require new gait identification schemes that do not require the help of target users. In this work, we study a new person-tracking method based on the combination of some gait features observed from depth sensors. The features are classified into three groups: static, dynamic distances, and dynamic angles. We demonstrate with ten subjects that our proposed scheme works well and the accuracy of equal error ratio can be improved to 0.25 when the top five features are combined.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shiraga, K., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: GEINet: view-invariant gait recognition using a convolutional neural network. In: Proceedings of the 8th IAPR International Conference on Biometrics (ICB 2016), pp. 1–8, Halmstad, Sweden, June 2016
Muaaz, M., Mayrhofer, R.: Smartphone-based gait recognition: from authentication to imitation. IEEE Trans. Mob. Comput. 16, 3209–3221 (2017)
Han, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 316–322 (2006)
Andersson, V., Araujo, R.: Person identification using anthropometric and gait data from kinect sensor. In: AAAI Conference on Artificial Intelligence (2015)
Igual, L., Lapedriza, À., Borràs, R.: Robust gait-based gender classification using depth cameras. EURASIP J. Image Video Process. 2013(1), 1–11 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Mori, T., Kikuchi, H. (2019). Person Tracking Based on Gait Features from Depth Sensors. In: Barolli, L., Kryvinska, N., Enokido, T., Takizawa, M. (eds) Advances in Network-Based Information Systems. NBiS 2018. Lecture Notes on Data Engineering and Communications Technologies, vol 22. Springer, Cham. https://doi.org/10.1007/978-3-319-98530-5_65
Download citation
DOI: https://doi.org/10.1007/978-3-319-98530-5_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98529-9
Online ISBN: 978-3-319-98530-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)