Controllable Data Sampling in the Space of Human Poses

Controllable Data Sampling in the Space of Human Poses

Kyungyong Yang1    Kibeom Youn1    Kyungho Lee1    Jehee Lee1

1 Seoul National University  

Sampling Results in the Space of Human Poses



Markerless human pose recognition using a single depth camera plays an important role in interactive graphics applications and user interface design. Recent pose recognition algorithms have adopted machine learning techniques utilizing a large collection of motion capture data. The effectiveness of the algorithms is greatly influenced by the diversity and variability of training data. We present a new sampling method that resamples a collection of human motion data to improve the pose variability and achieve an arbitrary size and level of density in the space of human poses. The space of human poses is high-dimensional and thus brute-force uniform sampling is intractable. We exploit dimensionality reduction and locally stratified sampling to generate either uniform or application-specifically biased distributions in the space of human poses. Our algorithm is learned to recognize such challenging poses such as sit, kneel, stretching and yoga using a remarkably small amount of training data. The recognition algorithm can also be steered to maximize its performance for a specific domain of human poses. We demonstrate that our algorithm performs much better than Kinect SDK for recognizing challenging acrobatic poses, while performing comparably for easy upright standing poses.



Kyungyong Yang, Kibeom Youn, Kyungho Lee, and Jehee Lee,
Controllable Data Sampling in the Space of Human Poses,
Computer Animation and Virtual Worlds 26, no. 3-4 (2015): 457-467.

Download Paper (Author’s Manuscripts) (1.7 MB)

Demo video

Download Video (103 MB)     Download Supplemental Material (3.87 MB)