A constraint learning feedback dynamic model for stereopsis

Author

Bokil, Amol ; Khotanzad, Alireza

Author_Institution

Texas Instrum. Inc., Dallas, TX, USA

Volume

17

Issue

11

fYear

1995

fDate

11/1/1995 12:00:00 AM

Firstpage

1095

Lastpage

1100

Abstract

This paper presents a stereo matcher inspired by the earlier work of Marr and Poggio (1976). Two major extensions are introduced: the algorithm is extended to gray-level images, and the inhibitory/excitatory weights of the model are learned rather than set a priori according to “uniqueness” and “continuity” constraints. Gray level stereo pairs of real scenes with known disparity maps are used to train the model. The trained system is successfully tested on other gray level stereo pairs of real scenes as well as a set of random dot stereograms. Performance is compared to a recent stereo matching algorithm

Keywords

computer vision; feedback; learning (artificial intelligence); recurrent neural nets; stereo image processing; Marr-Poggio algorithm; backpropagation; constraint learning; disparity maps; feedback dynamic model; gradient descent method; gray-level images; inhibitory/excitatory weights; random dot stereograms; recurrent neural network; stereo pairs; stereopsis; Cameras; Feedback; Geometrical optics; Image analysis; Image processing; Instruments; Layout; Neurofeedback; Recurrent neural networks; System testing;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.473237

Filename

473237