Advanced

A system for automatic pose-estimation from a single image in a city scene

Johansson, Björn LU and Cipolla, R (2002) Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition, and Applications In Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition, and Application p.68-73
Abstract
We describe an automatic system for pose-estimation from a single image in a city scene. Each building has a model consisting of a number of parallel planes associated with it. The homographies for the best match of the planes to the image is estimated automatically for each of the possible buildings. We show how the estimation of the homographies can be done effectively by reducing the search space and using fast convolution. The model having the best match is then used to determine the position and orientation of the camera. The results of a number of experiments of the system in realistic circumstances is also presented
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
automatic pose-estimation system, city scene, parallel plane matching, automatic homography estimation, search space reduction, building models, fast convolution, single image, camera position, camera estimation
in
Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition, and Application
pages
68 - 73
publisher
ACTA Press
conference name
Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition, and Applications
ISBN
0-88986-338-5
language
English
LU publication?
yes
id
52e99b93-ef0f-4be1-a9e5-00a57c1e0771 (old id 610685)
alternative location
http://mi.eng.cam.ac.uk/reports/svr-ftp/cipolla_iasted02.pdf
date added to LUP
2007-11-27 15:44:06
date last changed
2016-04-16 10:31:39
@misc{52e99b93-ef0f-4be1-a9e5-00a57c1e0771,
  abstract     = {We describe an automatic system for pose-estimation from a single image in a city scene. Each building has a model consisting of a number of parallel planes associated with it. The homographies for the best match of the planes to the image is estimated automatically for each of the possible buildings. We show how the estimation of the homographies can be done effectively by reducing the search space and using fast convolution. The model having the best match is then used to determine the position and orientation of the camera. The results of a number of experiments of the system in realistic circumstances is also presented},
  author       = {Johansson, Björn and Cipolla, R},
  isbn         = {0-88986-338-5},
  keyword      = {automatic pose-estimation system,city scene,parallel plane matching,automatic homography estimation,search space reduction,building models,fast convolution,single image,camera position,camera estimation},
  language     = {eng},
  pages        = {68--73},
  publisher    = {ARRAY(0x82bd738)},
  series       = {Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition, and Application},
  title        = {A system for automatic pose-estimation from a single image in a city scene},
  year         = {2002},
}