发明授权
US07724962B2 Context adaptive approach in vehicle detection under various visibility conditions
有权
在各种可见度条件下车辆检测中的上下文自适应方法
- 专利标题: Context adaptive approach in vehicle detection under various visibility conditions
- 专利标题(中): 在各种可见度条件下车辆检测中的上下文自适应方法
-
申请号: US11825619申请日: 2007-07-05
-
公开(公告)号: US07724962B2公开(公告)日: 2010-05-25
- 发明人: Ying Zhu , Gregory Baratoff , David Jean Pascal Acunzo
- 申请人: Ying Zhu , Gregory Baratoff , David Jean Pascal Acunzo
- 申请人地址: US NJ Iselin DE Munich
- 专利权人: Siemens Corporation,Siemens Aktiengesellschaft
- 当前专利权人: Siemens Corporation,Siemens Aktiengesellschaft
- 当前专利权人地址: US NJ Iselin DE Munich
- 代理商 Donald B. Paschburg
- 主分类号: G06K9/62
- IPC分类号: G06K9/62
摘要:
Adaptive vision-based vehicle detection methods, taking into account the lighting context of the images are disclosed. The methods categorize the scenes according to their lighting conditions and switch between specialized classifiers for different scene contexts. Four categories of lighting conditions have been identified using a clustering algorithm in the space of image histograms: Daylight, Low Light, Night, and Saturation. Trained classifiers are used for both Daylight and Low Light categories, and a tail-light detector is used for the Night category. Improved detection performance by using the provided context-adaptive methods is demonstrated. A night time detector is also disclosed.
公开/授权文献
信息查询