Michihiro Uenohara, Takeo Kanade, Vision-Based Object Registration
for Real-Time Image Overlay, 1995 Conference on Computer Vision,
Virtual Reality and Robotics in Medicine, Nice, France, April, 1995.
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.