Brown Applied Mathematics Pattern Theory and Vision Seminar
Abstract: We describe progress in matching shots which are images of the same 3D location in a film. The problem is hard because the camera viewpoint may change substantially between shots, with consequent changes in the imaged appearance of the scene due to foreshortening, scale changes, partial occlusion and lighting changes.
We develop and compare two methods which achieve this task. In the first method we match key frames between shots using wide baseline matching techniques. The wide baseline method represents each frame by a set of viewpoint invariant local features. The local spatial support of the features means that segmentation of the frame (e.g. into foreground/ background) is not required, and partial occlusion is tolerated.
In the second method we employ the temporal continuity within a shot to compute invariant descriptors for tracked features. The temporal information increases both the signal to noise ratio of the data and the stability of the computed features.
Results of matching shots for a number of different scene types are illustrated on an entire commercial film.
<--- 2002 Index