Methods and systems for collaborative-writing-surface image formation
Aspects of the present invention relate to methods and systems for capturing, sharing and recording the information on a collaborative writing surface. According to a first aspect of the present invention, currently persistent collaborative-writing-surface content may be imaged during periods of occlusion by an occluder. According to a second aspect of the present invention, the occluder may be imaged as transparent allowing the visibility of the occluded currently persistent collaborative-writing-surface content. According to a third aspect of the present invention, the occluder may be imaged as a silhouette allowing visibility of the occluded currently persistent collaborative-writing-surface content.
1. A non-transitory computer readable medium encoded with a computer program code for causing a computing system to execute a method for forming an image of a collaborative writing surface, said method comprising:
determining an occluded portion of a current frame, wherein said determining comprises tracking an occluder and said tracking comprises:
receiving a segmentation mask;
performing component filtering on said segmentation mask;
caching said filtered segmentation mask, thereby producing a filtered segmentation mask appearance over time;
estimating a global motion direction based on said appearance over time; and
determining a magnitude associated with said global motion direction; and
blending a prior result image with said current frame, wherein said occluded portion of said current frame is rendered based on a corresponding portion of said prior result image.
2. The computer readable medium as described in claim 1 , said method further comprising imaging said occluder as partially transparent in said image of said collaborative writing surface.
3. The computer readable medium as described in claim 1 , said method further comprising imaging said occluder as a silhouette in said image of said collaborative writing surface.
4. The computer readable medium as described in claim 1 , said method further comprising:
determining an activity level associated with said collaborative writing surface; and
performing said blending only when said activity level indicates a change in the content on said collaborative writing surface.
5. The computer readable medium as described in claim 1 , said method further comprising preprocessing a captured frame to form said current frame.
6. The computer readable medium as described in claim 5 , said method further comprising correcting said captured frame for perspective distortion and cropping said corrected captured frame to a region-of-interest associated with said collaborative writing surface to form said current frame.
7. The computer readable medium as described in claim 1 , wherein said collaborative writing surface is a surface selected from the group consisting of flipchart, a whiteboard, a chalkboard and a piece of paper.
8. A collaboration system comprising:
a collaborative writing surface;
a capture device for acquiring a captured image corresponding to said collaborative writing surface; and
a virtual-transparency capture controller for forming an image of said collaborative writing surface, wherein said image is a blended version of a prior result image with a current frame related to said captured image, wherein an occluded portion of said current frame is rendered based on a corresponding portion of said prior result image; and
wherein said virtual-transparency capture controller comprises:
a foreground-object segmenter for identifying an occluder in said current frame; and
an occluder tracker for tracking said occluder.
9. The system as described in claim 8 , wherein said collaborative writing surface is a surface selected from the group consisting of flipchart, a whiteboard, a chalkboard and a piece of paper.
10. The system as described in claim 8 further comprising an image rectifier for eliminating perspective distortion in said captured image to form said current frame.
11. The system as described in claim 8 further comprising an image demosaicer for demosaicing said captured image to form said current frame.
12. The system as described in claim 8 , wherein said occluder is imaged as partially transparent in said image of said collaborative writing surface.
13. The system as described in claim 8 , wherein said occluder is imaged as a silhouette in said image of said collaborative writing surface.
14. The system as described in claim 8 , wherein said occluder tracker comprises:
a segmentation-mask receiver for receiving a segmentation mask;
a component filter for performing component filtering on said segmentation mask;
a cache for caching said filtered segmentation mask, thereby producing a filtered segmentation mask appearance over time;
a motion estimator for estimating a global motion direction based on said appearance over time; and
a magnitude determiner for determining a magnitude associated with said global motion direction.
15. The system as described in claim 8 , wherein said virtual-transparency capture control performs said blending only when an activity level indicates a change in the content on said collaborative writing surface.
16. The system as described in claim 8 further comprising an image enhancer for enhancing said image of said collaborative writing surface.