Abstract | ||
---|---|---|
We address the problem of human action understanding of the upper human body from video sequences. Time-sequential images expressing human actions are transformed to sequences of feature vectors containing the configuration of the human body. A human is modeled as a collection of body parts, linked in a kinematic structure. The relation of the joints is used to estimate the human pose. A proposed layered HMM framework decomposes the human action recognition problem into two layers. The first layer models the actions of two arms individually from low-level features. The second layer models the interrelationship of two arm as an action. Experiments with a set of six types of human actions demonstrate the effectiveness of our proposed scheme, and the comparisons with other HMM systems show the robustness. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICME.2008.4607719 | 2008 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-4 |
Keywords | Field | DocType |
feature vectors,hidden markov models,feature vector,skin,estimation,human body,feature extraction,torso,image recognition,training data | Kinematics,Computer science,Action recognition,Robustness (computer science),Artificial intelligence,Computer vision,Torso,Feature vector,Pattern recognition,Feature extraction,Speech recognition,Hidden Markov model,Human body | Conference |
Citations | PageRank | References |
4 | 0.41 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yen-chieh Wu | 1 | 4 | 0.41 |
Hsuan-Sheng Chen | 2 | 115 | 7.36 |
Wen-Jiin Tsai | 3 | 174 | 19.57 |
Suh-Yin Lee | 4 | 1596 | 319.67 |
Jen-Yu Yu | 5 | 104 | 12.13 |