Camera Matchmoving in Unprepared, Unknown Environments

Abstract

Camera matchmoving is an application involving synthesis of real scenes and artificial objects, in which the goal is to insert computer-generated graphical 3D objects into live-action footage depicting unmodeled, arbitrary scenes. This work addresses the problem of tracking the 3D motion of a camera in space, using only the images it acquires while moving freely in unmodeled, arbitrary environments. A novel feature-based method for camera tracking has been developed, intended to facilitate tracking in online, time-critical applications such as video see-through augmented reality and vision-based control. In contrast to several existing techniques, which are designed to operate in a batch, offline mode, assuming that the whole video sequence to be tracked is available before tracking commences, our method operates on images incrementally, as they are being acquired.