Invention Grant
- Patent Title: Real-time action detection and classification
- Patent Title (中): 实时动作检测与分类
-
Application No.: US12488911Application Date: 2009-06-22
-
Publication No.: US08634638B2Publication Date: 2014-01-21
- Inventor: Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
- Applicant: Feng Han , Hui Cheng , Jiangjian Xiao , Harpreet Singh Sawhney , Sang-Hack Jung , Rakesh Kumar , Yanlin Guo
- Applicant Address: US CA Menlo Park
- Assignee: SRI International
- Current Assignee: SRI International
- Current Assignee Address: US CA Menlo Park
- Agency: Moser Taboada
- Main IPC: G06K9/62
- IPC: G06K9/62

Abstract:
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.
Public/Granted literature
- US20090316983A1 Real-Time Action Detection and Classification Public/Granted day:2009-12-24
Information query