Loading...
Please wait, while we are loading the content...
Similar Documents
Motion Segmentation Based on Motion/Brightness Integration and Oscillatory Correlation (2000)
| Content Provider | CiteSeerX |
|---|---|
| Author | Cesmeli, Erdogan Wang, Deliang |
| Abstract | A segmentation method based on the integration of motion and brightness is proposed for image sequences. The method is composed of two parallel pathways that process motion and brightness, respectively. Inspired by the visual system, the motion pathway has two stages. The first stage estimates local motion at locations with reliable information. The second stage performs segmentation based on local motion estimates. In the brightness pathway, the input scene is segmented into regions based on brightness distribution. Subsequently, segmentation results from the two pathways are integrated to refine motion estimates. The final segmentation is performed in the motion network based on refined estimates. For segmentation, locally excitatory globally inhibitory oscillator network (LEGION) architecture is employed whereby the oscillators corresponding to a region of similar motion/brightness oscillate in synchrony and different regions attain different phases. Results on synthetic and real im... |
| File Format | |
| Volume Number | 11 |
| Journal | IEEE Trans. Neural Networks |
| Language | English |
| Publisher Date | 2000-01-01 |
| Access Restriction | Open |
| Subject Keyword | Oscillatory Correlation Motion Segmentation Motion Brightness Integration Different Phase Motion Estimate Reliable Information Motion Pathway Refined Estimate Segmentation Method Final Segmentation Brightness Distribution Different Region Local Motion Estimate Brightness Pathway Segmentation Result Parallel Pathway Inhibitory Oscillator Network Similar Motion Brightness Oscillate Motion Network Input Scene Real Im Second Stage Performs Visual System First Stage Estimate Local Motion Image Sequence |
| Content Type | Text |
| Resource Type | Article |
