发明名称 |
Real-Time Action Detection and Classification |
摘要 |
The present invention relates to a method and system for creating a strong classifier based on motion patterns wherein the strong classifier may be used to determine an action being performed by a body in motion. When creating the strong classifier, action classification is performed by measuring similarities between features within motion patterns. Embodiments of the present invention may utilize candidate part-based action sets and training samples to train one or more weak classifiers that are then used to create a strong classifier.
|
申请公布号 |
US2009316983(A1) |
申请公布日期 |
2009.12.24 |
申请号 |
US20090488911 |
申请日期 |
2009.06.22 |
申请人 |
HAN FENG;CHENG HUI;XIAO JIANGJIAN;SAWHNEY HARPREET SINGH;JUNG SANG-HACK;KUMAR RAKESH;GUO YANLIN |
发明人 |
HAN FENG;CHENG HUI;XIAO JIANGJIAN;SAWHNEY HARPREET SINGH;JUNG SANG-HACK;KUMAR RAKESH;GUO YANLIN |
分类号 |
G06K9/62 |
主分类号 |
G06K9/62 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|