ismar 2010
DESCRIPTION
TRANSCRIPT
![Page 1: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/1.jpg)
Interactive Modelling for AR Applications John Bastian, Ben Ward, Rhys Hill, Anton van den Hengel, Anthony Dick
Australian Centre for Visual TechnologiesSchool of Computer ScienceUniversity of Adelaide
![Page 2: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/2.jpg)
Introduction Our method allows users to rapidly build
3D models forManipulation within AR workspaceUse as occlusion masks
Our approach is characterised byAn interactive modelling processModelling by segmentation and silhouette
carving
![Page 3: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/3.jpg)
Overview Video an object with a hand-held webcam Track camera movement with PTAM User selects object in one frame System segments object in subsequent frames Observations are combined to construct the
3D model
![Page 4: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/4.jpg)
Segmentation User marks the object, using a
mouse or the camera Build foreground and background
colour models from user marking Apply graph cut segmentation
Optimal segmentation given colour models and image edges
Additional marking refines the segmentation
![Page 5: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/5.jpg)
Segmentation
![Page 6: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/6.jpg)
Silhouette Carving Use the silhouettes
to generate 3D models
Start with a volume around the object
Remove voxels with projection outside the silhouette
![Page 7: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/7.jpg)
Feedback Current shape estimate is used to
predict subsequent silhouettes Predicted silhouette is used to:
Define cut regionUpdate colour modelsReduce ambiguity when foreground has
similar colour to background
![Page 8: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/8.jpg)
3D Prior Silhouette is predicted from
current shape estimate Initial mesh used until volume
is defined Volume model is used to
generate a confidence map for inclusion of each pixel in the silhouette
![Page 9: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/9.jpg)
User Feedback User can view
the model as its shape evolves
![Page 10: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/10.jpg)
Results
![Page 11: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/11.jpg)
Results
![Page 12: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/12.jpg)
Results
![Page 13: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/13.jpg)
Future Work Register models from a
database to the images Incorporate photoconsistency Use more sophisticated
segmentation Increased automation
![Page 14: ISMAR 2010](https://reader037.vdocuments.net/reader037/viewer/2022102813/5482bbdfb4af9f7d148b47d1/html5/thumbnails/14.jpg)
Questions?