3D visual mechinism by neural networkings

Shigeki Sugiyama

doi:10.1117/12.716830

4 May 2007 3D visual mechinism by neural networkings

Shigeki Sugiyama

Proceedings Volume 6538, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense VI; 653811 (2007) https://doi.org/10.1117/12.716830
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

Abstract

There are some computer vision systems that are available on a market but those are quite far from a real usage of our daily life in a sense of security guard or in a sense of a usage of recognition of a target object behaviour. Because those surroundings' sensing might need to recognize a detail description of an object, like "the distance to an object" and "an object detail figure" and "its figure of edging", which are not possible to have a clear picture of the mechanisms of them with the present recognition system. So for doing this, here studies on mechanisms of how a pair of human eyes can recognize a distance apart, an object edging, and an object in order to get basic essences of vision mechanisms. And those basic mechanisms of object recognition are simplified and are extended logically for applying to a computer vision system. Some of the results of these studies are introduced on this paper.

Citation Download Citation

Shigeki Sugiyama "3D visual mechinism by neural networkings", Proc. SPIE 6538, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense VI, 653811 (4 May 2007); https://doi.org/10.1117/12.716830

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available