Segment-based human motion compression
Proceedings of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation
Finding repetitive patterns in 3D human motion captured data
Proceedings of the 2nd international conference on Ubiquitous information management and communication
Analysis and synthesis of latin dance using motion capture data
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III
Generating a two-phase lesson for guiding beginners to learn basic dance movements
Computers & Education
| Hi-index | 0.00 |
Determining the complexity of a human motion is useful for human motion analysis with potential applications such as biomechanics, sport training, entertainment. There has not been much research effort in finding a complexity measure to evaluate the whole human body motion automatically. In this paper, we present a novel approach to evaluate the complexity of human motion based on motion captured data. Our proposed complexity measure considers the un-correlation among active joint dimensions and the nonsmoothness of each joint dimension in the temporal direction. It is logical to expect that a motion is more complex if the joint dimensions are less correlated and the temporal movement is less smooth. The experimental results show that our proposed complexity measure is able to cluster the same type of motions and differentiate motions with different observed complexities.