S
Shian-Ru Ke
Researcher at University of Washington
Publications - 9
Citations - 461
Shian-Ru Ke is an academic researcher from University of Washington. The author has contributed to research in topics: Hidden Markov model & Pose. The author has an hindex of 6, co-authored 9 publications receiving 389 citations. Previous affiliations of Shian-Ru Ke include National Taiwan University.
Papers
More filters
Journal ArticleDOI
A Review on Video-Based Human Activity Recognition
TL;DR: This survey, which aims to provide a comprehensive state-of-the-art review of the field, also addresses several challenges associated with these systems and applications.
Proceedings ArticleDOI
Real-Time 3D Human Pose Estimation from Monocular View with Applications to Event Detection and Video Gaming
TL;DR: In this approach, human body is automatically detected from video sequence, then image features such as silhouette, edge and color are extracted and integrated to infer 3D human poses by iteratively minimizing the cost function defined between 2D features derived from the projected 3D model and those extracted from video sequences.
Proceedings ArticleDOI
Quasi-periodic action recognition from monocular videos via 3D human models and cyclic HMMs
TL;DR: The experimental results indicate the effectiveness of the proposed system in terms of the view point invariance, the low -dimensional feature vectors, and the encouraging recognition rates.
Proceedings ArticleDOI
View-invariant 3D human body pose reconstruction using a monocular video camera
TL;DR: This view invariant system overcomes the challenges of requiring the modeled human to be viewed from a pre-specified angular perspective so as to initialize the 3D body model configuration, as well as to continuously find the best match between the tracked 2D features with the3D model based on the downhill simplex algorithm.
Journal ArticleDOI
Human Action Recognition Based on 3D Human Modeling and Cyclic HMMs
TL;DR: A system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs) is proposed.