Integrating stereo and shape from shading

Author

Mostafa, Mostafa G H ; Yamany, Sameh M. ; Farag, Aly A.

Author_Institution

Comput. Vision & Image Process. Lab., Louisville Univ., KY, USA

Volume

3

fYear

1999

fDate

1999

Firstpage

130

Abstract

This paper presents a new method for integrating different low level vision modules, stereo and shape from shading, in order to improve the 3D reconstruction of visible surfaces of objects from intensity images. The integration process is based on correcting the 3D visible surface obtained from shape from shading using the sparse depth measurements from the stereo module by fitting a surface into the difference between the two data sets. A feedforward neural network is used to fit a surface to the error difference. An extended Kalman filter algorithm is used for the network learning. It is found that the integration of sparse depth measurements has greatly enhanced the 3D visible surface obtained from shape from shading in terms of metric measurements

Keywords

Kalman filters; feedforward neural nets; image recognition; image reconstruction; object recognition; stereo image processing; 3D reconstruction; 3D visible surface; extended Kalman filter algorithm; feedforward neural network; integration process; low level vision modules; metric measurements; network learning; sparse depth measurements; Feedforward neural networks; Image reconstruction; Layout; Machine vision; Neural networks; Shape measurement; Stereo image processing; Stereo vision; Surface fitting; Surface reconstruction;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on

Conference_Location

Kobe

Print_ISBN

0-7803-5467-2

Type

conf

DOI

10.1109/ICIP.1999.817085

Filename

817085