Biological inspired CMOS foveated sensor: For neural network training

Yongwoo Jeong; Albert H. Titus

doi:10.1109/SAS.2011.5739779

Biological inspired CMOS foveated sensor: For neural network training

Yongwoo Jeong
, Albert H. Titus

Department of Biomedical Engineering

SUNY Buffalo

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

1 Scopus citations

Abstract

In this work we describe the design and testing of a custom CMOS-based motion detection system that derives its functionality from biology. The system will beone component of a CMOS visual sensor system that will identify and foveate on objects. The system is inspired by different animals that perform similar functions and have similar retinal structures. For example, we mimic frog's eye using a hemispherical surface structure to provide a wider field of view. In addition, we mimic the human retina with a combination of fovea and peripheral light detectors. The result is a sensor array that combines these aspects to attend and foveate on objects of interest.

Original language	English
Title of host publication	SAS 2011 - IEEE Sensors Applications Symposium, Proceedings
Pages	183-187
Number of pages	5
DOIs	https://doi.org/10.1109/SAS.2011.5739779
State	Published - 2011
Event	6th IEEE Sensors Applications Symposium, SAS 2011 - San Antonio, TX, United States Duration: Feb 22 2011 → Feb 24 2011

Publication series

Name	SAS 2011 - IEEE Sensors Applications Symposium, Proceedings

Conference

Conference	6th IEEE Sensors Applications Symposium, SAS 2011
Country/Territory	United States
City	San Antonio, TX
Period	02/22/11 → 02/24/11

Keywords

CMOS
foveate
frog
hemispherical
motion sensor
retina

Access to Document

10.1109/SAS.2011.5739779

Cite this

@inproceedings{e384bf0e0525441dbc496c8a29829c0d,

title = "Biological inspired CMOS foveated sensor: For neural network training",

abstract = "In this work we describe the design and testing of a custom CMOS-based motion detection system that derives its functionality from biology. The system will beone component of a CMOS visual sensor system that will identify and foveate on objects. The system is inspired by different animals that perform similar functions and have similar retinal structures. For example, we mimic frog's eye using a hemispherical surface structure to provide a wider field of view. In addition, we mimic the human retina with a combination of fovea and peripheral light detectors. The result is a sensor array that combines these aspects to attend and foveate on objects of interest.",

keywords = "CMOS, foveate, frog, hemispherical, motion sensor, retina",

author = "Yongwoo Jeong and Titus, \{Albert H.\}",

year = "2011",

doi = "10.1109/SAS.2011.5739779",

language = "English",

isbn = "9781424480647",

series = "SAS 2011 - IEEE Sensors Applications Symposium, Proceedings",

pages = "183--187",

booktitle = "SAS 2011 - IEEE Sensors Applications Symposium, Proceedings",

note = "6th IEEE Sensors Applications Symposium, SAS 2011 ; Conference date: 22-02-2011 Through 24-02-2011",

}

Jeong, Y & Titus, AH 2011, Biological inspired CMOS foveated sensor: For neural network training. in SAS 2011 - IEEE Sensors Applications Symposium, Proceedings., 5739779, SAS 2011 - IEEE Sensors Applications Symposium, Proceedings, pp. 183-187, 6th IEEE Sensors Applications Symposium, SAS 2011, San Antonio, TX, United States, 02/22/11. https://doi.org/10.1109/SAS.2011.5739779

TY - GEN

T1 - Biological inspired CMOS foveated sensor

T2 - 6th IEEE Sensors Applications Symposium, SAS 2011

AU - Jeong, Yongwoo

AU - Titus, Albert H.

PY - 2011

Y1 - 2011

N2 - In this work we describe the design and testing of a custom CMOS-based motion detection system that derives its functionality from biology. The system will beone component of a CMOS visual sensor system that will identify and foveate on objects. The system is inspired by different animals that perform similar functions and have similar retinal structures. For example, we mimic frog's eye using a hemispherical surface structure to provide a wider field of view. In addition, we mimic the human retina with a combination of fovea and peripheral light detectors. The result is a sensor array that combines these aspects to attend and foveate on objects of interest.

AB - In this work we describe the design and testing of a custom CMOS-based motion detection system that derives its functionality from biology. The system will beone component of a CMOS visual sensor system that will identify and foveate on objects. The system is inspired by different animals that perform similar functions and have similar retinal structures. For example, we mimic frog's eye using a hemispherical surface structure to provide a wider field of view. In addition, we mimic the human retina with a combination of fovea and peripheral light detectors. The result is a sensor array that combines these aspects to attend and foveate on objects of interest.

KW - CMOS

KW - foveate

KW - frog

KW - hemispherical

KW - motion sensor

KW - retina

UR - https://www.scopus.com/pages/publications/84884659534

U2 - 10.1109/SAS.2011.5739779

DO - 10.1109/SAS.2011.5739779

M3 - Conference contribution

AN - SCOPUS:84884659534

SN - 9781424480647

T3 - SAS 2011 - IEEE Sensors Applications Symposium, Proceedings

SP - 183

EP - 187

BT - SAS 2011 - IEEE Sensors Applications Symposium, Proceedings

Y2 - 22 February 2011 through 24 February 2011

ER -

Biological inspired CMOS foveated sensor: For neural network training

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this