Disparity estimation in a layered image for reflection stereo

Authors:
Masao Shimizu;Masatoshi Okutomi;Wei Jiang
Affiliations:
Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan;Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan;Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan
Venue:
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Year:
2009

Citing 7
Cited 0

Cepstral Filtering on a Columnar Image Architecture: A Fast Algorithm for Binocular Stereo Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
An improved illumination model for shaded display

Communications of the ACM
Catadioptric Stereo Using Planar Mirrors

International Journal of Computer Vision
Pseudo-Stereo Vision System: A Detailed Study

Journal of Intelligent and Robotic Systems
Reflection Stereo - Novel Monocular Stereo using a Transparent Plate -

CRV '06 Proceedings of the The 3rd Canadian Conference on Computer and Robot Vision
A Refractive Camera for Acquiring Stereo and Super-resolution Images

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Shape Estimation of Transparent Objects by Using Inverse Polarization Ray Tracing

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

By watching the reflection in the glass window, one can often observe a two-layered image consisting of a front-surface reflection from a glass and a rear-surface reflection through the glass The transparent glass plate reflects and transmits the incident light from its front surface The transmitted light is then reflected from the rear surface and is transmitted again to the air through the front surface These two light paths create a layered image comprising two identical images with a specific displacement depending on the object range Estimating the object range requires the accurate detection of the image shift in the layered image This paper presents a study of the shift estimation method using Fourier transformation of the layered image The maximum location in the Fourier transform of the Fourier power spectrum of the layered image indicates the image shift Experimental results demonstrate the effectiveness of the method compared with a method using an autocorrelation function.