Polyhedral Object Localization in an Image by Referencing to a Single Model View

Authors:
Ronald Chung;Hau-San Wong
Affiliations:
Department of Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, People's Republic of China. rchung@cuhk.edu.hk;Department of Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, People's Republic of China
Venue:
International Journal of Computer Vision
Year:
2003

Citing 10
Cited 1

Motion and Structure from Orthographic Projections

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing solid objects by alignment with an image

International Journal of Computer Vision
Recognition by Linear Combinations of Models

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
Geometric invariance in computer vision

Geometric invariance in computer vision
Robust recovery of the epipolar geometry for an uncalibrated stereo rig

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
3D motion recovery via affine epipolar geometry

International Journal of Computer Vision
The Quadric Reference Surface: Theory and Applications

International Journal of Computer Vision
Algebraic Functions For Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
What can be seen in three dimensions with an uncalibrated stereo rig

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Wide Baseline Stereo Matching

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision

Rapid and Brief Communication: Image mosaicking for polyhedral scene and in particular singly visible surfaces

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Identifying a three-dimensional (3D) object in an image is traditionally dealt with by referencing to a 3D model of the object. In the last few years there has been a growing interest of using not a 3D shape but multiple views of the object as the reference. This paper attempts a further step in the direction, using not multiple views but a single clean view as the reference model. The key issue is how to establish correspondences from the model view where the boundary of the object is explicitly available, to the scene view where the object can be surrounded by various distracting entities and its boundary disturbed by noise. We propose a solution to the problem, which is based upon a mechanism of predicting correspondences from just four particular initial point correspondences. The object is required to be polyhedral or near-polyhedral. The correspondence mechanism has a computational complexity linear with respect to the total number of visible corners of the object in the model view. The limitation of the mechanism is also analyzed thoroughly in this paper. Experimental results over real images are presented to illustrate the performance of the proposed solution.