Real-Time Vision Based Object Registration for Image Overlay - Robotics Institute Carnegie Mellon University

Real-Time Vision Based Object Registration for Image Overlay

Michihiro Uenohara and Takeo Kanade
Conference Paper, Proceedings of 1st International Conference on Computer Vision, Virtual Reality, and Robotics in Medicine (CVRMed '95), April, 1995

Abstract

This paper presents computer vision based techniques for object registration, real-time tracking, and image overlay. The capability can be used to superimpose registered images such as those from CT or MRI onto a video image of a patient's body. Real-time object registration enables an image to be overlaid consistently onto objects even while the object or the viewer is moving. The video image of a patient's body is used as input for object registration. Reliable real-time object registration at frame rate (30 Hz) is realized by a combination of techniques, including template matching based feature detection, feature correspondence by geometric constraints, and pose calculation of objects from feature positions in the image. Two types of image overlay systems are presented. The first one registers objects in the image and projects pre-operative model data onto a raw camera image. The other computes the position of image overlay directly from 2D feature positions without any prior models. With the techniques developed in this paper, interactive video, which transmits images of a patient to the expert and sends them back with some image overlay, can be realized.

BibTeX

@conference{Uenohara-1995-13859,
author = {Michihiro Uenohara and Takeo Kanade},
title = {Real-Time Vision Based Object Registration for Image Overlay},
booktitle = {Proceedings of 1st International Conference on Computer Vision, Virtual Reality, and Robotics in Medicine (CVRMed '95)},
year = {1995},
month = {April},
}