Skip to main content

Sparse motion bases selection for human motion denoising.

Xiao, J., Feng, Y., Ji, M., Yang, X., Zhang, J. J. and Zhuang, Y., 2015. Sparse motion bases selection for human motion denoising. Signal Processing, 110, 108- 122.

Full text available as:

Signals_Proc.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.


DOI: 10.1016/j.sigpro.2014.08.017


Human motion denoising is an indispensable step of data preprocessing for many motion data based applications. In this paper, we propose a data-driven based human motion denoising method that sparsely selects the most correlated subset of motion bases for clean motion reconstruction. Meanwhile, it takes the statistic property of two common noises, i.e., Gaussian noise and outliers, into account in deriving the objective functions. In particular, our method firstly divides each human pose into five partitions termed as poselets to gain a much fine-grained pose representation. Then, these poselets are reorganized into multiple overlapped poselet groups using a lagged window moving across the entire motion sequence to preserve the embedded spatial 13temporal motion patterns. Afterward, five compacted and representative motion dictionaries are constructed in parallel by means of fast K-SVD in the training phase; they are used to remove the noise and outliers from noisy motion sequences in the testing phase by solving !131-minimization problems. Extensive experiments show that our method outperforms its competitors. More importantly, compared with other data-driven based method, our method does not need to specifically choose the training data, it can be more easily applied to real-world applications.

Item Type:Article
Uncontrolled Keywords:Human motion denoising; Data-driven; Poselet model; ℓ1-minimization
Group:Faculty of Media & Communication
ID Code:21396
Deposited By: Symplectic RT2
Deposited On:01 Sep 2014 10:38
Last Modified:14 Mar 2022 13:49


Downloads per month over past year

More statistics for this item...
Repository Staff Only -