Paper Info
Title
Reconstruction Of Architectural Scenes From Uncalibrated Photos And Maps
Abstract
We consider the problem of reconstructing architectural scenes from multiple photographs taken from arbitrary viewpoints. The original contribution is the use of a map as a source of geometric constraints to obtain in a fast and simple way a detailed model of a scene. We suppose that images arc 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 and recover the projection matrices for each viewpoint. Finally, triangulation is used to recover 3D models of the scene and to visualise new viewpoints. Our approach needs minimal a priori information about the camera being used. A working system has been designed and implemented to allow the user to interactively build a model from Uncalibrated images from arbitrary viewpoints and a simple map.
Year
Venue
Keywords
2000
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
3D reconstruction, planar homography, self-calibration
Field
DocType
Volume
Computer vision,Computer graphics (images),Matrix (mathematics),Viewpoints,Computer science,A priori and a posteriori,Projection (linear algebra),Triangulation (social science),Planar,Artificial intelligence,3D reconstruction,Homography (computer vision)
Conference
E84D
Issue
ISSN
Citations 
12
1745-1361
2
PageRank 
References 
Authors
0.47
17
3
Name
Order
Citations
PageRank
Ignazio Infantino115132.13
Roberto Cipolla29413827.88
Antonio Chella337465.74