Title: A Fast and Efficient VOP Extraction Method Based on Watershed Segmentation
1A Fast and Efficient VOP Extraction Method Based
on Watershed Segmentation
- Alireza Tavakkoli
- Dr. Shohreh Kasaei
- Gholamreza Amayeh
- Sharif University of Technology
2Outline
- Problem Definition.
- Literature Review.
- Proposed Method.
- Performance Analysis.
- Conclusions.
3Content-Based Functionalities in Video
- User Interaction.
- Very Low Bit-rate Video Compression.
- Video Indexing.
- Object-Based Video Coding Systems
- MPEG 4.
- H.263.
4Video Object Plane (VOP).
- A Video Scene is decomposed into VOPs.
- Multiple VOPs shape Video Object Layers.
- Proposing an Automatic VOP Extractor is a very
difficult task.
5VOP Extraction
- Spatio-Temporal Segmentation
- Spatial Segmentation
- Watershed Segmentation.
- Temporal Information
- Motion Detection.
- Change Detection Masks.
6Watershed Segmentation
- Rain Fall Simulation
- Immersion Simulation
- Vincent Soille (1991).
7Drawbacks of Watershed Segmentation
- Results in over segmentation.
- Very time consuming.
- Solutions
- Region Merging Techniques.
- Predictive Watershed.
8Over Segmentation
9Region Merging Using Modified Gradient
10Preparing Image for Watershed Segmentation
11Resulting Watershed Segmentation
12Predictive Watershed
13Prediction of Watershed
14Why CDM?
- Distance Learning Application
- Video is supposed to have stationary Background.
- Real time video compression system.
- Stationary Background
- No Global Motion.
- No Camera Motion.
- No Illumination Changes.
15CDM and Noise
- Difference Noise
- Gaussian Noise
- Due to intensity changes.
- Can be reduced by a Hypothesis test.
- Hypothesis test
- Noise if H0 True.
- Object if H1 True.
16Region Labeling Method Hypothesis Test
17Watershed Update
18VOP Extraction Algorithm
19Experimental Results
20Experimental Results (Contd.)
21Experimental Results (Contd.)
22Experimental Results (Contd.)
23Experimental Results (Contd.)
Matlab 6.2 Software, Pentium 4, 2.0GHz.
24Conclusions
- Ceasing the Over segmentation Problem.
- Speeding up the conventional method using
temporal information. - A fast VOP extraction algorithm to be used in
real time video processing systems.
25Questions?