This paper provides a concise tutorial on the Microsoft Kinect technology and the state of art research on human motion tracking and recognition with Microsoft Kinect. A pre-requisite for human motion recognition is feature extraction. There are two types of feature extraction methods: skeleton joint based, and depth/color image based. Given a set of feature vectors, a motion could be recognized using machine learning, direct comparison, or rule-based methods. We also outline future research directions on the Kinect technology.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Lun R, Zhao W B. A survey of applications and human motion recognition with microsoft kinect. Int J Pattern Recogn Artif Intell, 2015, 29: 1555008
Shotton J, Sharp T, Kipman A, et al. Real-time human pose recognition in parts from single depth images. Commun ACM, 2013, 56: 116–124
Xia L, Chen C C, Aggarwal J. View invariant human action recognition using histograms of 3d joints. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Providence, 2012. 20–27
Zhao W B, Lun R, Espy D D, et al. Realtime motion assessment for rehabilitation exercises: integration of kinematic modeling with fuzzy inference. J Artif Intell Soft Comput Res, 2014, 4: 267–285
Zhao WB, LunW, Espy D D, et al. Rule based realtime motion assessment for rehabilitation exercises. In: Proceedings of the IEEE Symposium on Computational Intelligence in Healthcare and e-Health, Orlando, 2014. 133–140
Masood S, Qureshi M P, Shah M B, et al. Dynamic time wrapping based gesture recognition. In: Proceedings of the International Conference on Robotics and Emerging Allied Technologies in Engineering, Islamabad, 2014. 205–210
Miranda L, Vieira T, Martinez D, et al. Real-time gesture recognition from depth data through key poses learning and decision forests. In: Proceedings of the 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, 2012. 268–275
Xu D, Chen Y L, Lin C, et al. Real-time dynamic gesture recognition system based on depth perception for robot navigation. In: Proceedings of the IEEE International Conference on Robotics and Biomimetics, Guangzhou, 2012. 689–694
Sung J, Ponce C, Selman B, et al. Unstructured human activity detection from RGBD images. In: Proceedings of the IEEE International Conference on Robotics and Automation, Saint Paul, 2012. 842–849
Zamborlin B, Bevilacqua F, Gillies M, et al. Fluid gesture interaction design: applications of continuous recognition for the design of modern gestural interfaces. ACM Trans Interact Intell Syst, 2014, 3: 22
Foti D, Kanazawa L. Activities of daily living. In: Pendleton H M, Schultz-Krohn W, eds. Pedretti’s Occupational Therapy: Practice Skills for Physical Dysfunction. St. Louis: Mosby, 2008. 146–194
Zhao W B. On automatic assessment of rehabilitation exercises with realtime feedback. In: Proceedings of the IEEE International Electro-Information Technology Conference, Grand Forks, 2016. 376–381
Zhao W B, Espy D D, Reinthal M A, et al. Privacy-aware human motion tracking with realtime haptic feedback. In: Proceedings of the IEEE International Conference on Mobile Services, New York, 2015. 446–453
Zhao W B, Lun R, Gordon C, et al. A privacy-aware kinect-based system for healthcare professionals. In: Proceedings of the IEEE International Electro-Information Technology Conference, Grand Forks, 2016. 205–210
About this article
Cite this article
Zhao, W. A concise tutorial on human motion tracking and recognition with Microsoft Kinect. Sci. China Inf. Sci. 59, 93101 (2016). https://doi.org/10.1007/s11432-016-5604-y
- Microsoft Kinect
- depth camera
- human motion tracking and recognition
- machine learning