基本信息:
- 专利标题: VIDEO SURVEILLANCE WITH PROBABILISTIC MODELLING OF HUMAN BEHAVIOUR
- 专利标题(中):视频监控与人类行为的概率模型
- 申请号:PCT/IB0302760 申请日:2003-06-18
- 公开(公告)号:WO2004003848A9 公开(公告)日:2004-12-23
- 发明人: TRAJKOVIC MIROSLAV
- 申请人: KONINKL PHILIPS ELECTRONICS NV , PHILIPS CORP
- 专利权人: KONINKL PHILIPS ELECTRONICS NV,PHILIPS CORP
- 当前专利权人: KONINKL PHILIPS ELECTRONICS NV,PHILIPS CORP
- 优先权: US18451202 2002-06-28
- 主分类号: G06T7/00
- IPC分类号: G06T7/00 ; G06K9/00 ; G06K9/62 ; G06K9/66 ; G06T5/00 ; G06T7/20 ; G08B13/194 ; G08B13/196 ; G08B21/04 ; H04N7/18 ; G08B21/02
摘要:
A method and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.
摘要(中):
公开了一种用于对人类或其他有生命物体的行为模式进行建模并检测对行为的重复模式的违反的方法和装置。 随着时间观察一个或多个人的行为,并且行为的特征被记录在多维空间中。 随着时间的推移,多维数据提供了人类行为模式的指示。 在时间,位置和活动(如睡眠和饮食)方面重复的活动将在多维数据中显示为高斯分布或聚类。 可以使用已知的高斯或聚类技术来分析概率分布函数以识别行为及其特征的重复模式,例如均值和方差。 如果适当,可以检测到重复行为模式的偏差并触发警报。
公开/授权文献:
IPC结构图谱:
G | 物理 |
--G06 | 计算;推算;计数 |
----G06T | 一般的图像数据处理或产生 |
------G06T7/00 | 图像分析,例如从位像到非位像 |