Improving a Real-Time Neural-Based Stereo Vision System

doi:10.1006/rtim.2000.0214

Real-Time Imaging

Volume 7, Issue 1, February 2001, Pages 59-76

https://doi.org/10.1006/rtim.2000.0214 Get rights and content

Abstract

Refinements of the energy expression of a real-time neural-based stereo vision system are presented. The neural network optimizes a scalar functional, that represents an area-based stereo matching algorithm. The neural system is reviewed and its performances presented. The proposed improvements are in terms of the exploitation of the image chromatic content and of local pixel information relative to the distance from an image feature. Experimental results showing the performance improvements are presented on synthetic and on real images. The hardware implementation currently in progress will straightforwardly benefit from these improvements.

References (34)

A. Zanela et al.
Sensing the third dimension in stereo vision systems: a cellular neural networks approach
Engineering Applications of Artificial Intelligence
(1998)
J.R. Jordan et al.
Using chromatic information in edge-based stereo correspondence
CVGIP: Image Understanding
(1991)
J.R. Jordan et al.
Using chromatic information in dense stereo correspondence
Pattern Recognition
(1992)
R. March
Visual reconstruction with discontinuities using variational methods
Image and Vision Computing
(1992)
S.S. Iyengar et al.
Autonomous Mobile Robot
(1991)
Salichs, M. A. Halme, A. 1998, Proc. of the 3rd IFAC Symposium on Intelligent Autonomous...
D. Marr
Vision
(1982)
S.I. Gallant
Neural network learning and expert systems
(1993)
J.J. Hopfield et al.
“Neural” Computation of Decisions in Optimisation Problems
Biological Cybernetics
(1985)
L.O. Chua et al.
Cellular Neural Network: Theory
IEEE Transaction on Circuits and Systems
(1988)

L.O. Chua et al.

Cellular Neural Network: Applications

IEEE Transaction on Circuits and Systems

(1988)

J.R. Jordan et al.

Computational stereo vision using colour

IEEE Control Systems Magazine

(1988)

Koschan, A. Rodehorst, V. Spiller, K. 1996, Color stereo vision using hierarchical block matching and active color...

Koschan, A. 1997, Improving robot vision by color information, Proc. 7th International Conference on Artificial...

S. Shah et al.

Mobile robot navigation and scene modeling using stereo fish-eye lens system

Machine Vision and Application

(1997)

T. Poggio et al.

Computational vision and regularization theory

Nature

(1985)

Cited by (6)

The application of deep learning in stereo matching and disparity estimation: A bibliometric review
2024, Expert Systems with Applications
Estimating the depth of the 3D world from 2D images is a classic and important issue in computer vision, which has been widely studied for decades. With the remarkable effect of deep learning on various computer vision tasks, scholars have become increasingly interested in exploring stereo matching (i.e., disparity estimation) with deep learning. We reviewed related studies through bibliometrics, and especially extracted research hotspots and evolution context in the field, aiming to facilitate researchers in clarifying the positioning of their research and finding new inspiration. Specifically, we summarized the distribution of publication years, countries/regions, institutions, authors, research areas, document types, etc. of the research in this field. According to the analysis of information from these publications, we presented an overview of this field and divided its development into three stages: the preliminary exploration period (1999–2011), the gradual awakening period (2012–2016), and the vigorous development period (2017- present). Finally, we analyzed and predicted the future research directions.
Real-time disparity estimation using foreground segmentation for stereo sequences
2006, Optical Engineering
A constrained nonlinear energy minimization framework for the regularization of the stereo correspondence problem
2005, IEEE Transactions on Circuits and Systems for Video Technology
Real-time depth reconstruction from stereo sequences
2005, Proceedings of SPIE - The International Society for Optical Engineering
A Collective-Based Adaptive Symbiotic Model for Surface Reconstruction in Area-Based Stereo
2003, IEEE Transactions on Evolutionary Computation
Using a Video Device and a Deep Learning-Based Pose Estimator to Assess Gait Impairment in Neurodegenerative Related Disorders: A Pilot Study
2022, Applied Sciences (Switzerland)

^f1: [email protected]

^f2: [email protected]

View full text

Regular ArticleImproving a Real-Time Neural-Based Stereo Vision System

Abstract

Engineering Applications of Artificial Intelligence

CVGIP: Image Understanding

Pattern Recognition

Image and Vision Computing

Autonomous Mobile Robot

Vision

Neural network learning and expert systems

“Neural” Computation of Decisions in Optimisation Problems

Biological Cybernetics

Cellular Neural Network: Theory

IEEE Transaction on Circuits and Systems

Cellular Neural Network: Applications

IEEE Transaction on Circuits and Systems

Computational stereo vision using colour

IEEE Control Systems Magazine

Mobile robot navigation and scene modeling using stereo fish-eye lens system

Machine Vision and Application

Computational vision and regularization theory

Nature

Regular Article
Improving a Real-Time Neural-Based Stereo Vision System