Denoising of Joint Tracking Data by Kinect Sensors Using Clustered Gaussian Process Regression
An-Ti Chiang, Qi Chen, Shijie Li, Yao Wang, Mei Fu, An-Ti Chiang, Qi Chen, Shijie Li, Yao Wang, Mei Fu
Abstract
Using Kinect sensors to monitor and provide feedback to patients performing intervention or rehabilitation exercises is an upcoming trend in healthcare. However, the joint positions measured by the Kinect sensor are often unreliable, especially for joints that are occluded by other parts of the body. Motion capture (MOCAP) systems using multiple cameras from different view angles can accurately track marker positions on the patient. But such systems are costly and inconvenient to patients. In this work, we simultaneously capture the joint positions using both a Kinect sensor and a MOCAP system during a training stage and train a Gaussian Process regression model to map the noisy Kinect measurements to the more accurate MOCAP measurements. To deal with the inherent variations in limb lengths and body postures among different people, we further propose a joint standardization method, which translates the raw joint positions of different people into a standard coordinate, where the distance between each pair of adjacent joints is kept at a reference distance. Our experiments show that the denoised Kinect measurements by the proposed method are more accurate than several benchmark methods.
Keywords: Gaussian process regression; denoising of Kinect measurements.
Figures
References
- Zhou L, Liu Z, Leung H, Shum HPH. Posture reconstruction using kinect with a probabilistic model. Proc. 20th ACM Symp. Virtual Real. Softw. Technol; 2014. pp. 117–125.
- Shum H, Ho E, Jiang Y, Takagi S. Real-time posture reconstruction for microsoft kinect. IEEE Trans Cybern. 2013 Oct;43(5):1357–1369.
- Wei X, Zhang P, Chai J. Accurate realtime full-body motion capture using a single depth camera. ACM Transactions on Graphics (TOG) 2012;31(6):188.
- Tripathy SR, Chakravarty K, Sinha A, Chatterjee D, Saha SK. Constrained Kalman Filter for Improving Kinect Based Measurements. Proc. International Symposium on Circuits and Systems (ISCAS); 2017.
http://optitrack.com/
- Armstrong HG. Anthropometry and mass distribution for human analogues. Military male aviators. 1988;1
http://go.microsoft.com/fwlink/?LinkID=403900&clcid=0x409
- Rasmussen CE, Williams CKI. Gaussian Processes for Machine Learning. 1. The MIT Press; 2006. p. 449.p. 450.p. 452.
- Cao Y, Brubaker MA, Fleet DJ, Hertzmann A. Efficient Optimization for Sparse Gaussian Process Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2015;37(12):2415–2427.
- Snelson E, Ghahramani Z. Sparse Gaussian processes using pseudo-inputs. In: Weiss Y, Scholkopf B, Platt J, editors. Advances in Neural Information Processing Systems 18. Cambridge, Massachussetts: The MIT Press; 2006.
- Fu MR, Axelrod D, Guth A, Alcarese FC, Qiu Z, Goldberg J, Kim J, Scagliola J, Kleinman R, Haber J. Proactive approach to lymphedema risk reduction: a prospective study. Ann Surg Oncol. 2014;21(11):3481–3498. doi: 10.1245/s10434-014-3761-z. Online First.
- Liu Z, Zhou L, Leung H, Shum HPH. Kinect Posture Reconstruction Based on a Local Mixture of Gaussian Process Models. IEEE Trans Vis Computer Graph. 2016;22:2437–2450.
Source: PubMed