Extracting motion information from digital video sequences
US8335350B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Feb 24, 2011 |
| Grant date | Dec 18, 2012 |
| Priority date | — |
| Expiry date | May 5, 2031 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T7/215
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for analyzing a digital video sequence of a scene to extract background motion information and foreground motion information, comprising: analyzing at least a portion of a plurality of image frames captured at different times to determine corresponding one-dimensional image frame representations; combining the one-dimensional frame representations to form a two-dimensional spatiotemporal representation of the video sequence; using a data processor to identify a set of trajectories in the two-dimensional spatiotemporal representation of the video sequence; analyzing the set of trajectories to identify a set of foreground trajectory segments representing foreground motion information and a set of background trajectory segments representing background motion information; and storing an indication of the foreground motion information or the background motion information or both in a processor-accessible memory.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.