Name
Abstract | ||
|---|---|---|
This paper proposes a novel nonlinear manifold learning method for addressing the ill-posed problem of occluded human action analysis. As we know, a person can perform a broad variety of movements. To capture the multiplicity of a human action, this paper creates a low-dimensional manifold for capturing the intra-path and inter-path contexts of an event. Then, an action path matching scheme can be applied for seeking the best event path for linking the missed information between occluded persons. After that, a recovering scheme is proposed for repairing an occluded object to a complete one. Then, each action can be converted to a series of action primitives through posture analysis. Since occluded objects are handled, there will be many posture-symbol-converting errors. Instead of using a specific symbol, we code a posture using not only its best matched key posture but also its similarities among other key postures. Then, recognition of an action taken from occlude objects can be modeled as a matrix matching problem. With the matrix representation, different actions can be more robustly and effectively matched by comparing their Kullback-Leibler(KL) distances. |
Year | Venue | Keywords |
|---|---|---|
2012 | ICPR | kl distances,image matching,recovering scheme,kullback-leibler distances,occluded human action analysis,event intrapath contexts,learning (artificial intelligence),matrix representation,key posture code analysis,ill-posed problem,nonlinear manifold learning method,matrix algebra,missed information linking,low-dimensional dynamic manifold model,occlude object modelling,posture-symbol-converting errors,action path matching scheme,occluded persons,action primitives,action recognition,matrix matching problem,gesture recognition,occluded object repairing,event interpath contexts,learning artificial intelligence |
Field | DocType | ISSN |
Computer vision,Pattern recognition,Symbol,Image matching,Matrix (mathematics),Computer science,Matrix algebra,Gesture recognition,Artificial intelligence,Nonlinear manifold,Matrix representation,Manifold | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-4673-2216-4 | 1 | 0.37 |
References | Authors | |
9 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Li-Chih Chen | 1 | 55 | 5.37 |
| Jun-Wei Hsieh | 2 | 751 | 67.88 |
| Chi-Hung Chuang | 3 | 47 | 9.06 |
| Chang-Yu Huang | 4 | 43 | 4.65 |
| Duan-Yu Chen | 5 | 296 | 28.79 |