Publication Details

Camera auto-calibration for complex scenes

ALI, A.; SMRŽ, P. Camera auto-calibration for complex scenes. In SPIE 11605. Rome: SPIE - the international society for optics and photonics, 2021. p. 1-11. ISBN: 978-1-5106-4041-2.
Czech title
Autokalibrace kamery pro složité scény
Type
conference paper
Language
English
Authors
URL
Keywords

camera auto-calibration, pedestrian detection, pedestrian segmentation,
pedestrian tracking, RANSAC, multiple ground planes, fuzzy logic, vanishing
points

Abstract

In this paper, we propose a novel method for automatic camera calibration based
on pedestrians' observations. Our proposed method is capable of estimating
calibration parameters for complex scenes having more than one ground plane.
Unlike existing methods that require time-consuming optimization step, our method
uses real-time re-estimation step based on fuzzy logic while relaxing the
assumption on the number of ground planes in the scene. Furthermore, we propose
a dominant ground plane detection step for better calibration parameter
estimation on complex scenes. To evaluate our proposed method, we run
comprehensive testing using 5 different datasets covering varieties of
calibration parameters and scene properties, we also conduct tests on a synthetic
dataset for more detailed analysis.

Published
2021
Pages
1–11
Proceedings
SPIE 11605
Conference
13th International Conference on Machine Vision, Rome, IT
ISBN
978-1-5106-4041-2
Publisher
SPIE - the international society for optics and photonics
Place
Rome
DOI
UT WoS
000664492700067
EID Scopus
BibTeX
@inproceedings{BUT182943,
  author="Anas {Ali} and Pavel {Smrž}",
  title="Camera auto-calibration for complex scenes",
  booktitle="SPIE 11605",
  year="2021",
  pages="1--11",
  publisher="SPIE - the international society for optics and photonics",
  address="Rome",
  doi="10.1117/12.2586983",
  isbn="978-1-5106-4041-2",
  url="https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11605/116051W/Camera-auto-calibration-for-complex-scenes/10.1117/12.2586983.full?SSO=1"
}
Back to top