Publication Details

Fully Automatic Horizon Estimation for Surveillance Cameras

BARTL Vojtěch and HEROUT Adam. Fully Automatic Horizon Estimation for Surveillance Cameras. In: 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA). Sydney: Institute of Electrical and Electronics Engineers, 2017, pp. 23-30. ISBN 978-1-5386-2839-3.
Czech title
Plně automatické určení horizontu pro dohledové kamery
Type
conference paper
Language
english
Authors
Keywords

horizon estimation, video surveillance, camera calibration, object tracking, trajectories, vanishing points

Abstract

This paper deals with automatic estimation of the horizon in videos from fixed surveillance cameras. The proposed algorithm is fully automatic in the sense that no user input is needed per-camera and it works with various scenes (indoor, outdoor, traffic, pedestrian, livestock, etc.). The algorithm detects moving objects, tracks them in time, assesses some of their geometric properties related to the object dimensions and infers observations related to the position of the horizon. We collected a dataset of 47 public camera streams observing suitable scenes of various nature. We annotated ground truth horizons based on geometric properties in the images and by direct human input. We evaluate the proposed algorithm and compare it to human guesses - it turns out that the algorithm is on par with humans or it outperforms them in the difficult scenes.

Published
2017
Pages
23-30
Proceedings
2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Conference
Digital Image Computing: Techniques and Applications 2017, Sydney, AU
ISBN
978-1-5386-2839-3
Publisher
Institute of Electrical and Electronics Engineers
Place
Sydney, AU
DOI
UT WoS
000427643000004
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11369,
   author = "Vojt\v{e}ch Bartl and Adam Herout",
   title = "Fully Automatic Horizon Estimation for Surveillance Cameras",
   pages = "23--30",
   booktitle = "2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",
   year = 2017,
   location = "Sydney, AU",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "978-1-5386-2839-3",
   doi = "10.1109/DICTA.2017.8227437",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11369"
}
Back to top