Line-Based Structure from Motion for Urban Environments

We present a novel method for recovering the 3D-line structure of a scene from multiple widely separated views. Traditional optimization-based approaches to line-based structure from motion minimize the error between measured line segments and the projections of corresponding 3D lines. In such a cas...

Full description

Saved in:
Bibliographic Details
Published in:3DPVT 2006 : Third International Symposium on 3D Data Processing, Visualization, and Transmission : June 14-16, 2006, University of North Carolina, Chapel Hill, USA pp. 846 - 853
Main Authors: Schindler, G., Krishnamurthy, P., Dellaert, F.
Format: Conference Proceeding
Language:English
Japanese
Published: IEEE 01.06.2006
Subjects:
Image edge detection
Image reconstruction
Layout
Motion measurement
ISBN:0769528252, 9780769528250
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a novel method for recovering the 3D-line structure of a scene from multiple widely separated views. Traditional optimization-based approaches to line-based structure from motion minimize the error between measured line segments and the projections of corresponding 3D lines. In such a case, 3D lines can be optimized using a minimum of 4 parameters. We show that this number of parameters can be further reduced by introducing additional constraints on the orientations of lines in a 3D scene. In our approach, 2D-lines are automatically detected in images with the assistance of an EM-based vanishing point estimation method which assumes the existence of edges along mutally orthogonal vanishing directions. Each detected line is automatically labeled with the orientation (e.g. vertical, horizontal) of the 3D line which generated the measurement, and it is this additional knowledge that we use to reduce the number of degrees of freedom of 3D lines during optimization. We present 3D reconstruction results for urban scenes based on manually established feature correspondences across images.
ISBN:0769528252
9780769528250
DOI:10.1109/3DPVT.2006.90