Equisolid fisheye stereovision calibration and point cloud computation

Julien Moreau (1) , Sébastien Ambellouis (1) , Yassine Ruichek (2)

1 IFSTTAR/COSYS/LEOST - Laboratoire Électronique Ondes et Signaux pour les Transports
2 SET - Laboratoire Systèmes et Transports

This paper deals with dense 3D point cloud computation of urban environments around a vehicle. The idea is to use two fisheye views to get 3D coordinates of the surrounding scene’s points. The first contribution of this paper is the adaptation of an omnidirectional stereovision self-calibration algorithm to an equisolid fisheye projection model. The second contribution is the description of a new epipolar matching based on a scan-circle principle and a dynamic programming technique adapted for fisheye images. The method is validated using both synthetic images for which ground truth is available and real images of an urban scene.

Mots clés: IMAGE; TRAITEMENT DES IMAGES; PROGRAMMATION; ZONE URBAINE; VEHICULE; TRAITEMENT D'IMAGE

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Julien Moreau, Sébastien Ambellouis, Yassine Ruichek. Equisolid fisheye stereovision calibration and point cloud computation. ISPRS-SSG 2013, conference on Serving Society with Geoinformatics, Nov 2013, Antalya, Turkey. 6p. ⟨hal-00912647⟩