Journal
IEEE ACCESS
Volume 8, Issue -, Pages 52927-52940Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2980316
Keywords
Skeleton; Noise measurement; Three-dimensional displays; Noise reduction; Kinematics; Loss measurement; Topology; 3D skeleton motion data refinement; noise-agnostic; perceptual constraint; motion autoencoder; Kinect
Categories
Funding
- National Natural Science Foundation of China [61972129, 61602146]
- Fundamental Research Funds for the Central Universities [JZ2018HGTA0215]
Ask authors/readers for more resources
In this paper, we demonstrate a perceptual-based 3D skeleton motion data refinement method based on a bidirectional recurrent autoencoder, called BRA-P. Three main technical contributions are made by the proposed network. First, the proposed BRA-P can address noisy data with different noise types and amplitudes using one network, and this attribute makes the approach more suitable for raw motion data with heterogeneous mixed noise. Second, due to the usage of perceptual loss, which measures the difference in high-level features extracted by a pretrained perceptual autoencoder, BRA-P improves the perceptual similarity between refined motion data and clean motion data, especially for the case where the noisy data and target clean data have different topologies. Third, BRA-P further improves the bone-length consistency and smoothness of the refined motion using the perceptual autoencoder as a postprocessing network. Ablation experiments verify the effect of the three technical contributions of our approach. The results of the experiments on synthetic noise data and raw motion data captured by Kinect demonstrate that our method outperforms several state-of-the-art methods in the cleaning of mixed-noise data by one network.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available