FAST, BIOLOGICALLY INSPIRED CORNER DETECTION USING A SQUARE SPIRAL ADDRESS SCHEME AND ARTIFICIAL EYE TREMOR

John Fegan; Sonya Coleman; Dermot Kerr; Bryan Scotney

FAST, BIOLOGICALLY INSPIRED CORNER DETECTION USING A SQUARE SPIRAL ADDRESS SCHEME AND ARTIFICIAL EYE TREMOR

Research output: Contribution to conference › Paper › peer-review

220 Downloads (Pure)

Abstract

This paper presents an efficient approach to corner detection in images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard ‘cornerness’ measure. A computationally efficient use of the spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. Comparative evaluation of three corner detection methods is presented and results demonstrate significantly faster processing times than other well-known corner detection methods.

Original language	English
Number of pages	5
Publication status	Accepted - 20 Jun 2018
Event	International Conference on Artificial Intelligence and Pattern Recognition - North China University of Technology (NCUT), Beijing, China Duration: 18 Aug 2018 → 20 Aug 2018 http://www.aipr.net

Conference

Conference	International Conference on Artificial Intelligence and Pattern Recognition
Abbreviated title	AIPR 2018
Country/Territory	China
City	Beijing
Period	18/08/18 → 20/08/18
Internet address	http://www.aipr.net

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

Accepted paperAuthor Accepted Manuscript, 293 KBLicence: Unspecified

Cite this

@conference{3571295e8e364968859456bc124c91c9,

title = "FAST, BIOLOGICALLY INSPIRED CORNER DETECTION USING A SQUARE SPIRAL ADDRESS SCHEME AND ARTIFICIAL EYE TREMOR",

abstract = "This paper presents an efficient approach to corner detection in images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard {\textquoteleft}cornerness{\textquoteright} measure. A computationally efficient use of the spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. Comparative evaluation of three corner detection methods is presented and results demonstrate significantly faster processing times than other well-known corner detection methods.",

author = "John Fegan and Sonya Coleman and Dermot Kerr and Bryan Scotney",

year = "2018",

month = jun,

day = "20",

language = "English",

note = "International Conference on Artificial Intelligence and Pattern Recognition , AIPR 2018 ; Conference date: 18-08-2018 Through 20-08-2018",

url = "http://www.aipr.net",

}

TY - CONF

T1 - FAST, BIOLOGICALLY INSPIRED CORNER DETECTION USING A SQUARE SPIRAL ADDRESS SCHEME AND ARTIFICIAL EYE TREMOR

AU - Fegan, John

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - Scotney, Bryan

PY - 2018/6/20

Y1 - 2018/6/20

N2 - This paper presents an efficient approach to corner detection in images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard ‘cornerness’ measure. A computationally efficient use of the spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. Comparative evaluation of three corner detection methods is presented and results demonstrate significantly faster processing times than other well-known corner detection methods.

AB - This paper presents an efficient approach to corner detection in images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard ‘cornerness’ measure. A computationally efficient use of the spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. Comparative evaluation of three corner detection methods is presented and results demonstrate significantly faster processing times than other well-known corner detection methods.

M3 - Paper

T2 - International Conference on Artificial Intelligence and Pattern Recognition

Y2 - 18 August 2018 through 20 August 2018

ER -

FAST, BIOLOGICALLY INSPIRED CORNER DETECTION USING A SQUARE SPIRAL ADDRESS SCHEME AND ARTIFICIAL EYE TREMOR

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this