Binocular disparity calculation on a massively-parallel analog vision processor

Soumyajit Mandal; Bertram Shi; Piotr Dudek

doi:10.1109/CNNA.2010.5430282

Binocular disparity calculation on a massively-parallel analog vision processor

Soumyajit Mandal, Bertram Shi, Piotr Dudek

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We studied neuromorphic models of binocular disparity processing and mapped them onto a vision chip containing a massively parallel analog processor array. Our goal was to make efficient use of the available hardware while preserving the fundamental computations performed by the models. We also developed an optical fixture that used mirrors to simultaneously focus two images onto the vision chip. This fixture simulates two horizontally-separated virtual cameras, thereby allowing us to run our binocular disparity estimation algorithms using a single image sensor in real time. © 2010 IEEE.

Original language	English
Title of host publication	2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010\|Int. Workshop Cell. Nanoscale Netw. Appl., CNNA
DOIs	https://doi.org/10.1109/CNNA.2010.5430282
Publication status	Published - 2010
Event	2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010 - Berkeley, CA Duration: 1 Jul 2010 → …

Conference

Conference	2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010
City	Berkeley, CA
Period	1/07/10 → …

Access to Document

10.1109/CNNA.2010.5430282

Cite this

@inproceedings{1744a54b0db449d9aa9598556615cc89,

title = "Binocular disparity calculation on a massively-parallel analog vision processor",

abstract = "We studied neuromorphic models of binocular disparity processing and mapped them onto a vision chip containing a massively parallel analog processor array. Our goal was to make efficient use of the available hardware while preserving the fundamental computations performed by the models. We also developed an optical fixture that used mirrors to simultaneously focus two images onto the vision chip. This fixture simulates two horizontally-separated virtual cameras, thereby allowing us to run our binocular disparity estimation algorithms using a single image sensor in real time. {\textcopyright} 2010 IEEE.",

author = "Soumyajit Mandal and Bertram Shi and Piotr Dudek",

year = "2010",

doi = "10.1109/CNNA.2010.5430282",

language = "English",

isbn = "9781424466795",

booktitle = "2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010|Int. Workshop Cell. Nanoscale Netw. Appl., CNNA",

note = "2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010 ; Conference date: 01-07-2010",

}

Mandal, S, Shi, B & Dudek, P 2010, Binocular disparity calculation on a massively-parallel analog vision processor. in 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010|Int. Workshop Cell. Nanoscale Netw. Appl., CNNA. 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010, Berkeley, CA, 1/07/10. https://doi.org/10.1109/CNNA.2010.5430282

Binocular disparity calculation on a massively-parallel analog vision processor. / Mandal, Soumyajit; Shi, Bertram; Dudek, Piotr.
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010|Int. Workshop Cell. Nanoscale Netw. Appl., CNNA. 2010.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Binocular disparity calculation on a massively-parallel analog vision processor

AU - Mandal, Soumyajit

AU - Shi, Bertram

AU - Dudek, Piotr

PY - 2010

Y1 - 2010

N2 - We studied neuromorphic models of binocular disparity processing and mapped them onto a vision chip containing a massively parallel analog processor array. Our goal was to make efficient use of the available hardware while preserving the fundamental computations performed by the models. We also developed an optical fixture that used mirrors to simultaneously focus two images onto the vision chip. This fixture simulates two horizontally-separated virtual cameras, thereby allowing us to run our binocular disparity estimation algorithms using a single image sensor in real time. © 2010 IEEE.

AB - We studied neuromorphic models of binocular disparity processing and mapped them onto a vision chip containing a massively parallel analog processor array. Our goal was to make efficient use of the available hardware while preserving the fundamental computations performed by the models. We also developed an optical fixture that used mirrors to simultaneously focus two images onto the vision chip. This fixture simulates two horizontally-separated virtual cameras, thereby allowing us to run our binocular disparity estimation algorithms using a single image sensor in real time. © 2010 IEEE.

U2 - 10.1109/CNNA.2010.5430282

DO - 10.1109/CNNA.2010.5430282

M3 - Conference contribution

SN - 9781424466795

BT - 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010|Int. Workshop Cell. Nanoscale Netw. Appl., CNNA

T2 - 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010

Y2 - 1 July 2010

ER -

Binocular disparity calculation on a massively-parallel analog vision processor

Abstract

Conference

Access to Document

Fingerprint

Cite this