Publication detail
Fully Automatic Horizon Estimation for Surveillance Cameras
BARTL, V. HEROUT, A.
Original Title
Fully Automatic Horizon Estimation for Surveillance Cameras
English Title
Fully Automatic Horizon Estimation for Surveillance Cameras
Type
conference paper
Language
en
Original 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.
English 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.
Keywords
horizon estimation, video surveillance, camera calibration, object tracking, trajectories, vanishing points
Released
02.12.2017
Publisher
Institute of Electrical and Electronics Engineers
Location
Sydney
ISBN
978-1-5386-2839-3
Book
2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Edition
NEUVEDEN
Edition number
NEUVEDEN
Pages from
23
Pages to
30
Pages count
8
URL
Documents
BibTex
@inproceedings{BUT144420,
author="Vojtěch {Bartl} and Adam {Herout}",
title="Fully Automatic Horizon Estimation for Surveillance Cameras",
annote="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.",
address="Institute of Electrical and Electronics Engineers",
booktitle="2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",
chapter="144420",
doi="10.1109/DICTA.2017.8227437",
edition="NEUVEDEN",
howpublished="online",
institution="Institute of Electrical and Electronics Engineers",
year="2017",
month="december",
pages="23--30",
publisher="Institute of Electrical and Electronics Engineers",
type="conference paper"
}