Talks and Poster Presentations (with Proceedings-Entry):
M. Banaeyan, H. Huber, W. Kropatsch, R. Barth:
"A Novel Concept for Smart Camera Image Stitching";
Talk: 21st Computer Vision Winter Workshop (CVWW2016),
Rimske Toplice, Slovenia;
2016-02-03
- 2016-02-05; in: "Proceedings of the 21st Computer Vision Winter Workshop",
L. Cehovin, R. Mandeljc, V. Struc (ed.);
Slovenian Pattern Recognition Society,
Ljubljana, February 2016
(2016),
ISBN: 978-961-90901-7-6;
9 pages.
English abstract:
As panoramic images are widely used
in many applications, efficient image stitching meth-
ods that provide visually pleasant image mosaics are
needed. In this paper we discuss a novel concept for
smart camera image stitching based on graph pyra-
mids. For a multi-camera system, the images have
to be aligned accordingly to create an image mosaic.
Instead of calculating the corresponding transforma-
tions centrally, we aim at enabling each camera to in-
dividually calculate the transformation of the image
it takes. Graph pyramids used for image segmenta-
tion provide information about the segmentation pro-
cess. We analyze how this information can be used to
calculate the transformations for image alignment.
Electronic version of the publication:
http://publik.tuwien.ac.at/files/publik_252744.pdf
Created from the Publication Database of the Vienna University of Technology.