Name
Abstract | ||
|---|---|---|
In this paper, a human action recognition system is proposed. The system is based on new, descriptive 'temporal template' features in order to achieve high-speed recognition in real-time, embedded applications. The limitations of the well-known 'Motion History Image' (MHI) temporal template are addressed and a new 'Motion History Histogram' (MHH) feature is proposed to capture more motion information in the video. MHH not only provides rich motion information, but also remains computationally inexpensive. To further improve classification performance, we combine both MHI and MHH into a low dimensional feature vector which is processed by a support vector machine (SVM). Experimental results show that our new representation can achieve a significant improvement in the performance of human action recognition over existing comparable methods, which use 2D temporal template based representations. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1016/j.patrec.2009.03.003 | Pattern Recognition Letters |
Keywords | Field | DocType |
low dimensional feature vector,motion information,human action recognition system,motion history image,event recognition,motion analysis,embedded vision,gesture recognition,visual motion recognition,descriptive temporal template feature,machine learning,temporal template,motion history,new representation,high-speed recognition,human action recognition,classification performance,feature vector,comparative method,support vector machine | Histogram,Signal processing,Computer vision,Feature vector,Pattern recognition,Computer science,Support vector machine,Action recognition,Gesture recognition,Visual motion,Artificial intelligence,Motion analysis | Journal |
Volume | Issue | ISSN |
30 | 12 | Pattern Recognition Letters |
Citations | PageRank | References |
17 | 0.74 | 27 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hongying Meng | 1 | 832 | 69.39 |
| Nick Pears | 2 | 410 | 30.57 |