A CNN solution for depth estimation from binocular stereo imagery

Novel results and experiments are presented on the application of cellular neural networks to binocular stereo vision. A cellular neural network (CNN) universal machine (UM) algorithm is described for depth estimation as part of a stereo-vision-based guidance system for autonomous vehicles. Being mo...

Full description

Saved in:
Bibliographic Details
Published in1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications Proceedings pp. 218 - 223
Main Authors Radvanyi, A.G., Kozek, T., Chua, L.O.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1998
Subjects
Automated highways
Cellular neural networks
Computer networks
Computer vision
Electronic mail
Image edge detection
Image segmentation
Laboratories
Mobile robots
Remotely operated vehicles
Online AccessGet full text
ISBN0780348672
9780780348677
DOI10.1109/CNNA.1998.685368

Cover

More Information
Summary:Novel results and experiments are presented on the application of cellular neural networks to binocular stereo vision. A cellular neural network (CNN) universal machine (UM) algorithm is described for depth estimation as part of a stereo-vision-based guidance system for autonomous vehicles. Being most amenable to revealing stereo correspondence, extraction of vertical edges is performed first. Then their distance from the observer in 3D space is established through a stereo matching scheme. The performance of the algorithm is demonstrated on real-life highway imagery and it is shown that very low latency real-time operation is attainable via the CNN-UM.
ISBN:0780348672
9780780348677
DOI:10.1109/CNNA.1998.685368