Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?
Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur Graph Search.
In this paper, we present a flexible new technique for single-viewpoint omnidirectional camera calibration. The proposed method only re-quires the camera to observe a planar pattern shown at a few different orienta-tions. Either the camera or the planar pattern can be freely moved. No a priori knowledge of the motion is required, nor a specific model of the omnidirec-tional sensor. The only assumption is that the image projection function can be described by a Taylor series expansion whose coefficients are estimated by solving a two-step least-squares linear minimization problem. To test the pro-posed technique, we calibrated a panoramic camera having a vision angle greater than 200° in the vertical direction, and we obtained very good results. To investigate the accuracy of the calibration, we also used the estimated omni-camera model in a structure from motion experiment. We obtained a 3D metric reconstruction of a scene from two highly distorted omnidirectional images by using image correspondences only. Compared with classical techniques, which rely on a specific parametric model of the omnidirectional camera, the pro-posed procedure is independent of the sensor, easy to use and flexible.
Marcos Rubinstein, Farhad Rachidi-Haeri, Elias Per Joachim Le Boudec, Chaouki Kasmi, Nicolas Mora Parra, Emanuela Radici
Michael Christoph Gastpar, Alper Köse, Ahmet Arda Atalik
Michael Christoph Gastpar, Alper Köse, Ahmet Arda Atalik