Year: 2005
Type: conference-paper
Abstract: In this paper we present a new solution for real-time 3D camera pose estimation for Augmented Reality (AR)\napplications. The tracking system does not require special engineering of the environment, such as placing\nmarkers or beacons. The required input data are a CAD model of the target object to be tracked, and a calibrated\nreference image of it. We consider the whole process of camera tracking, and developed both an autonomous\ninitialization and a real-time tracking procedure. The system is robust to abrupt camera motions, strong changes\nof the lighting conditions and partial occlusions. To avoid typical jitter and drift problems the tracker performs\nfeature matching not only in an iterative manner, but also against stable reference features, which are dynamically\ncached in case of high confidence. We present experimental results generated with help of synthetic\nground truth, real off-line and on-line image sequences using different types of target objects.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2170911670