Detail publikace

Fully Automatic Horizon Estimation for Surveillance Cameras

BARTL, V. HEROUT, A.

Originální název

Fully Automatic Horizon Estimation for Surveillance Cameras

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

BARTL, V.; HEROUT, A.

Vydáno

2. 12. 2017

Nakladatel

Institute of Electrical and Electronics Engineers

Místo

Sydney

ISBN

978-1-5386-2839-3

Kniha

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

Strany od

23

Strany do

30

Strany počet

8

URL

https://www.fit.vut.cz/research/publication/11369/

BibTex

@inproceedings{BUT144420,
  author="Vojtěch {Bartl} and Adam {Herout}",
  title="Fully Automatic Horizon Estimation for Surveillance Cameras",
  booktitle="2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",
  year="2017",
  pages="23--30",
  publisher="Institute of Electrical and Electronics Engineers",
  address="Sydney",
  doi="10.1109/DICTA.2017.8227437",
  isbn="978-1-5386-2839-3",
  url="https://www.fit.vut.cz/research/publication/11369/"
}