Unsupervised learning of temporal anomalies for a video surveillance system
US8167430B2 · kind B2 · utility
19Cited by
23References
25Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Aug 31, 2009 |
| Grant date | May 1, 2012 |
| Priority date | — |
| Expiry date | Nov 9, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/955
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are described for analyzing a stream of video frames to identify temporal anomalies. A video surveillance system configured to identify when agents depicted in the video stream engage in anomalous behavior, relative to the time-of-day (TOD) or day-of-week (DOW) at which the behavior occurs. A machine-learning engine may establish the normalcy of a scene by observing the scene over a specified period of time. Once the observations of the scene have matured, the actions of agents in the scene may be evaluated and classified as normal or abnormal temporal behavior, relative to the past observations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.