Dense Structure from a Dense Optical Flow Sequence

Author: Xiong Y.   Shafer S.A.  

Publisher: Academic Press

ISSN: 1077-3142

Source: Computer Vision and Image Understanding, Vol.69, Iss.2, 1998-02, pp. : 222-245

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

This paper presents a structure-from-motion system which delivers dense structure information from a sequence of dense optical flows. Most traditional feature-based approaches cannot be extended to compute dense structure due to impractical computational complexity. We demonstrate that by decomposing uncertainty information into independent and correlated parts and employing an eigen-based uncertainty representation, we can decrease these complexities from O(N2) to O(N) for every frame, where N is the number of pixels in the images. We also show that our new representation of structural information makes it easy to merge over a long image sequence even when no specific feature is tracked over multiple frames. Copyright 1998 Academic Press.