Scene activity analysis using statistical and semantic features learnt from object trajectory data
US8855361B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 30, 2010 |
| Grant date | Oct 7, 2014 |
| Priority date | — |
| Expiry date | Dec 9, 2031 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/54
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Trajectory information of objects appearing in a scene can be used to cluster trajectories into groups of trajectories according to each trajectory's relative distance between each other for scene activity analysis. By doing so, a database of trajectory data can be maintained that includes the trajectories to be clustered into trajectory groups. This database can be used to train a clustering system, and with extracted statistical features of resultant trajectory groups a new trajectory can be analyzed to determine whether the new trajectory is normal or abnormal. Embodiments described herein, can be used to determine whether a video scene is normal or abnormal. In the event that the new trajectory is identified as normal the new trajectory can be annotated with the extracted semantic data. In the event that the new trajectory is determined to be abnormal a user can be notified that an abnormal behavior has occurred.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.