|
This article is cited in 18 scientific papers (total in 18 papers)
IMAGE PROCESSING, PATTERN RECOGNITION
Blind compensation of radial distortion in a single image using fast Hough transform
I. A. Kunina, S. A. Gladilin, D. P. Nikolaev Institute for Information Transmission Problems RAS, Moscow, Russia
Abstract:
In this paper, we present an automatic technique for compensation of radial distortion, which is characteristic of wide-angle lenses. The proposed method estimates distortion parameters using a single image from unknown source. No calibration objects are required, but it is assumed that the original scene contains straight lines. The method is based on finding such radial distortion parameters, that maximize total length of linear segments. We employ a fast Hough transform to estimate the overall curvature of lines without selecting any. The proposed algorithm is tested on real
images obtained using calibrated camera lenses with different radial distortion.
For the formal evaluation of the algorithm, we propose a quality measure for geometric distortion compensation, which works correctly even in the case when the problem of determining the coefficients is ill-conditioned.
Keywords:
digital image processing, image analysis, lens system design, radial distortion, automatic calibration, fast Hough transform.
Received: 10.05.2016 Accepted: 04.06.2016
Citation:
I. A. Kunina, S. A. Gladilin, D. P. Nikolaev, “Blind compensation of radial distortion in a single image using fast Hough transform”, Computer Optics, 40:3 (2016), 395–403
Linking options:
https://www.mathnet.ru/eng/co156 https://www.mathnet.ru/eng/co/v40/i3/p395
|
Statistics & downloads: |
Abstract page: | 307 | Full-text PDF : | 140 | References: | 28 |
|