发明公开
EP1745414A1 METHOD FOR COMBINING BOOSTED CLASSIFIERS FOR EFFICIENT MULTI-CLASS OBJECT DETECTION
审中-公开
方法COMBINING提振高效代号多个类目标检测
- 专利标题: METHOD FOR COMBINING BOOSTED CLASSIFIERS FOR EFFICIENT MULTI-CLASS OBJECT DETECTION
- 专利标题(中): 方法COMBINING提振高效代号多个类目标检测
-
申请号: EP05745708.7申请日: 2005-05-05
-
公开(公告)号: EP1745414A1公开(公告)日: 2007-01-24
- 发明人: BAHLMANN, Claus , ZHU, Ying , COMANICIU, Dorin , KÖHLER, Thorsten , PELLKOFER, Martin
- 申请人: SIEMENS CORPORATE RESEARCH, INC. , SIEMENS AKTIENGESELLSCHAFT
- 申请人地址: 755 College Road East Princeton, New Jersey 08540 US
- 专利权人: SIEMENS CORPORATE RESEARCH, INC.,SIEMENS AKTIENGESELLSCHAFT
- 当前专利权人: SIEMENS CORPORATE RESEARCH, INC.,SIEMENS AKTIENGESELLSCHAFT
- 当前专利权人地址: 755 College Road East Princeton, New Jersey 08540 US
- 代理机构: Vigars, Christopher Ian
- 优先权: US569552P 20040510; US111640 20050421
- 国际公布: WO2005111918 20051124
- 主分类号: G06K9/62
- IPC分类号: G06K9/62
摘要:
A method for training a system for detecting multi-class objects in an image or a video sequence is described. A common ensemble of weak classifiers for a set of object classes is identified. For each object class, a separate weighting scheme is adapted for the ensemble of weak classifiers. A method for detecting objects of multiple classes in an image or a video sequence is also disclosed. Each class is assigned a detector that is implemented by a weighted combination of weak classifiers such that all of the detectors are based on a common ensemble of weak classifiers. Then weights are individually set for each class.
公开/授权文献
信息查询