Automatic radial distortion estimation from a single image | |
| Author | Bukhari, Faisal |
| Call Number | AIT Diss. no.CS-12-05 |
| Subject(s) | Computer vision Image processing |
| Note | A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Dissertation ; no. CS-12-05 |
| Abstract | Many computer vision algorithms rely on the assumptions of the pinhole camera model, butlins distortion with off-the-shelf cameras is usually significant enough to violate this as-sumption. Many methods for radial distortion estimation have been proposed, but they all have limitations. Robust automatic radial distortion estimation from a single natural image would be extremely useful for many applications, particularly those in human-made environments containing abundant lines. For example, it could be used in place of an extensive calibration procedure to get a mobile robot or quadrotor experiment up and running quickly in an indoor environment.In this dissertation we propose a new and fully automatic method for radial distortion estimation based on the plumb-line approach.First, the method works from a single image and does not require a special calibration pattern.It is based on Fitzgibbon’s division model.Second, we devise a new algorithm for robust estimation of circular arcs.Third, we design and implement a new algorithm for robust estimation of lens distortion parameters based on the estimated circular arcs.Fourth, we perform an extensive empirical study of the method on synthetic images. Wedevelop our own data set for synthetic images under different levels of lambda and distortioncenter.Fifth, we perform a comparative statistical analysis of how different circle fitting methods contribute to accurate distortion parameter estimation.Sixth, we provide qualitative results on a wide variety of challenging real images. The Experiments demonstrate the method’s ability to accurately identify distortion parameters and remove distortion from images. Seventh, we perform a direct comparison of our method with that of Alvarez et al. (Alvarez, Gomez, & Sendra, 2009), the only researchers who have provided a publicly accessible implementation of their method, on synthetic images.Finally, we provide the source code based on OpenCV (Bradski, 2000) online1for re-searchers interested in evaluating or extending our procedure. |
| Year | 2012 |
| Corresponding Series Added Entry | Asian Institute of Technology. Dissertation ; no. CS-12-05 |
| Type | Dissertation |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Afzulpurkar, Nitin V.;Duboz, Raphael; |
| Scholarship Donor(s) | Higher Education Commission (HEC), Pakistan;Asian Institute of Technology Fellowship; |
| Degree | Thesis (Ph.D.) - Asian Institute of Technology, 2012 |