| EPSRC Reference: |
GR/M74306/01 |
| Title: |
OPTIMAL AUTOMATIC MULTIPLE-CUE SCENE SEGMENTATION |
| Principal Investigator: |
Vlachos, Dr T |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Sch of Electronics & Physical Sciences |
| Organisation: |
University of Surrey |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 October 1999 |
Ends: |
30 September 2002 |
Value (£): |
52,121
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Object-based video manipulation offers many well-documented advantages. It is common practice in television production in the form of chroma-keying and recently it has been the focus of MPEG-4, the emerging standard for multimedia coding. However, schemes like the above rely on stable segmentations performed in a controlled environment such as a studio or synthetically generated by computer. In contrast, fully-automatic segmentation of arbitrary-content video is an elusive problem for which no known algorithm provides a satisfactory solution.This project aims at the development of automatic video segmentation techniques for object identification using graph-theoretical image analysis tools. Graphs are powerful mathematical models capable of capturing important relationships between structural image elements and have been used very successfully for still image segmentation. According to this techniques recursive manipulation of graph attributes enables bottom-up segmentation of images by region merging. The novelty of the proposed approach lies in the incorporation of motion, in a graph-theoretical framework, as an essential cue for segmentation. Motion estimates will combined with other cues, such as depth and texture, to influence graph evolution. Segmentations guided by motion smoothness criteria, both in a spatial and a temporal context, are expected to be stable, reliable and robust against occlusions.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.surrey.ac.uk |