6533b824fe1ef96bd12808c6

RESEARCH PRODUCT

Architectural Scenes Reconstruction from Uncalibrated Photos and Map Based Model Knowledge

Antonio ChellaIgnazio Infantino

subject

Plane (geometry)business.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONTriangulation (social science)Triangulation (computer vision)Iterative reconstructionProjection (linear algebra)Image (mathematics)Trifocal tensorSimple (abstract algebra)Computer Science::Computer Vision and Pattern RecognitionHomographyComputer visionArtificial intelligencebusiness

description

In this paper we consider the problem of reconstructing architectural scenes from multiple photographs taken from arbitrarily viewpoints. The original contribution of this work is the use of a map as a source of a priori knowledge and geometric constraints in order to obtain in a fast and simple way a detailed model of a scene. We suppose images are uncalibrated and have at least one planar structure as a facade for exploiting the planar homography induced between world plane and image to calculate a first estimation of the projection matrix. Estimations are improved by using correspondences between images and map. We show how these simple constraints can be used to calibrate the cameras, to recover the projection matrices for each viewpoint, and to obtain 3D models by using triangulation.

https://doi.org/10.1007/3-540-45411-x_37