ELCVIA Electronic Letters on Computer Vision and Image Analysis (Jul 2007)

Correction for Camera Roll in a Perspectively Distorted Image: Cases for 2 and 3 point perspectives

  • Avinash N.,
  • S. Murali

DOI
https://doi.org/10.5565/rev/elcvia.159
Journal volume & issue
Vol. 6, no. 3

Abstract

Read online

We propose a method for correction of camera roll in a perspectively distorted image. Here we employ the rectification of the horizon line formed from the vanishing points in order to bring back the image rotation caused from the camera roll. In teleconference systems, surveillance system, aerial images of buildings, mobile robots visual system etc., the range of camera’s view spreads with pan, tilt and roll. It is intended to take omni-directional images for wide range coverage, but this invariably introduces rotation in many images due to the roll of the camera. This paper presents the method for camera roll correction by using the perspective distortion in images captured from a pan/tilt/roll camera control system. The proposed method works on two cases, viz. Calibrated and uncalibrated cameras. Calibrated camera with intrinsic calibration of the camera such as optical center and the focal length of the camera in cases of two point perspectives is considered and in case of three point perspective uncalibrated camera is considered and the camera is partially calibrated for the camera principal point and the roll is performed subsequently. The result comparison made reveals more about the usability of the algorithm in case of calibrated and uncalibrated cases of the camera used.

Keywords