Shape from Video

TitleShape from Video
Publication TypeConference Papers
Year of Publication1999
AuthorsBrodsky T, Fermüller C, Aloimonos Y
Conference NameComputer Vision and Pattern Recognition, IEEE Computer Society Conference on
Date Published1999///
PublisherIEEE Computer Society
Conference LocationLos Alamitos, CA, USA
Keywordsepipolar minimization, model extraction, Motion analysis, vision and graphics

This paper presents a novel technique for recovering the shape of a static scene from a video sequence due to a rigidly moving camera. The solution procedure consists of two stages. In the first stage, the rigid motion of the camera at each instant in time is recovered. This provides the transformation between successive viewing positions. The solution is achieved through new constraints which relate 3D motion and shape directly to the image derivatives. These constraints allow the combination of the processes of 3D motion estimation and segmentation by exploiting the geometry and statistics inherent in the data. In the second stage the scene surfaces are reconstructed through an optimization procedure which utilizes data from all the frames of a short video sequence. A number of experimental results demonstrate the potential of the approach.