Abstract
Due to the widespread use of dash cams (car DVRs), the estimation of geometric distortions introduced by such equipment is of particular interest. However, such geometric distortions are often complex and cannot be described using classical radial models. In this paper, we propose an original method for the estimation of complex geometric distortions. At the first step of the proposed method, we build distortion models based on the polynomial approximation of the lines of a calibration pattern for each particular processed frame. At the second step, we calculate the correction field and consistently refine it using built polynomial models.
In the experimental study, we apply the proposed technique to estimate the distortion of the DVR recording using the calibration pattern. We tune the order of polynomials, select optimal aggregation technique, and show how the reconstruction error changes with the number of processed frames. The experiments show that the proposed method can be successfully applied to estimate complex geometric distortions induced by car DVRs.
The reported study was funded by RFBR according to the research project no. 17-29-03190.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hartley, R., Zisserman, A.: Multiple View Geometry. Cambridge University Press, New York (2000)
Ma, L., Chen, Y., Moore, K.L.: Flexible camera calibration using a new analytical radial undistortion formula with application to mobile robot localization. In: IEEE International Symposium on Intelligent Control (2003)
Zhang, Z.: Flexible camera calibration by viewing a plane from unknown orientation. In: IEEE International Conference on Computer Vision, pp. 666–673 (1999)
Slama, C.C.: Manual of Photogrammetry, 4th edn. American Society of Photogrammetry, Falls Church (1980)
Ma, L., Chen, Y., Moore, K.L.: Rational radial distortion models of camera lenses with analytical solution for distortion correction International. J. Inf. Acquis. 1(02), 135–147 (2004)
Brauer-Burchardt, C., Voss, K.: A new algorithm to correct fish-eye- and strong wide-angle lens-distortion from single images. In: International Conference on Image Processing, pp. 225–228 (2001)
Camera calibration with OpenCV. Electronic resource. https://docs.opencv.org/2.4/doc/tutorials/calib3d/camera_calibration/camera_calibration.html. Accessed 4 Mar 2019
Camera Calibrator: Electronic resource. https://www.mathworks.com/help/vision/ref/cameracalibrator-app.html. Accessed 4 Mar 2019
Tang, Zh., Grompone von Gioi, R., Monasse, P., Morel, J.-M.: A precision analysis of camera distortion models. IEEE Trans. Image Process. 26(6), 2694–2704 (2017)
Dashcam: Electronic resource. https://en.wikipedia.org/wiki/Dashcam. Accessed 4 Mar 2019
Myasnikov, E.V.: Compensation of the complex geometric distortions induced by a car digital video recording equipment. In: CEUR Workshop Proceedings, vol. 2210, pp. 410–416 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Myasnikov, E. (2019). Estimation of Non-radial Geometric Distortions for Dash Cams. In: van der Aalst, W., et al. Analysis of Images, Social Networks and Texts. AIST 2019. Lecture Notes in Computer Science(), vol 11832. Springer, Cham. https://doi.org/10.1007/978-3-030-37334-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-37334-4_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37333-7
Online ISBN: 978-3-030-37334-4
eBook Packages: Computer ScienceComputer Science (R0)