Detail publikace

Automatic Camera Calibration by Landmarks on Rigid Objects

BARTL, V. ŠPAŇHEL, J. DOBEŠ, P. JURÁNEK, R. HEROUT, A.

Originální název

Automatic Camera Calibration by Landmarks on Rigid Objects

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

This article presents a new method for automatic calibration of surveillance cameras. We are dealing with traffic surveillance and therefore the camera is calibrated by observing vehicles; however, other rigid objects can be used instead. The proposed method is using keypoints or landmarks automatically detected on the observed objects by a convolutional neural network. By using fine-grained recognition of the vehicles (calibration objects), and by knowing the 3D positions of the landmarks for the (very limited) set of known objects, the extracted keypoints are used for calibration of the camera, resulting in internal (focal length) and external (rotation, translation) parameters and scene scale of the surveillance camera. We collected a dataset in two parking lots and equipped it with a calibration ground truth by measuring multiple distances in the ground plane. This dataset seems to be more accurate than the existing comparable data (GT calibration error reduced from 4.62% to 0.99%). Also, the experiments show that our method overcomes the best existing alternative in terms of accuracy (error reduced from 6.56% to 4.03%) and our solution is also more flexible in terms of viewpoint change and other.

Klíčová slova

camera calibration, optimization, surveillance

Autoři

BARTL, V.; ŠPAŇHEL, J.; DOBEŠ, P.; JURÁNEK, R.; HEROUT, A.

Vydáno

8. 9. 2020

Nakladatel

Springer International Publishing

ISSN

1432-1769

Periodikum

Machine Vision and Applications

Ročník

32

Číslo

1

Stát

Spojené státy americké

Strany od

2

Strany do

15

Strany počet

13

URL

BibTex

@article{BUT168175,
  author="Vojtěch {Bartl} and Jakub {Špaňhel} and Petr {Dobeš} and Roman {Juránek} and Adam {Herout}",
  title="Automatic Camera Calibration by Landmarks on Rigid Objects",
  journal="Machine Vision and Applications",
  year="2020",
  volume="32",
  number="1",
  pages="2--15",
  doi="10.1007/s00138-020-01125-x",
  issn="1432-1769",
  url="https://www.fit.vut.cz/research/publication/12345/"
}