Corner detection for identification of man-made objects in noisy aerial images

Isaac N. Bankman; Eric W. Rogala

doi:10.1117/12.477038

Corner detection for identification of man-made objects in noisy aerial images

Isaac N. Bankman, Eric W. Rogala

School of Medicine

Research output: Contribution to journal › Article › peer-review

Abstract

Corner detection is an essential feature extraction step in many image understanding applications including aerial image analysis and manufactured part inspection. Available corner detectors require the user to set critical manual thresholds, degrade under significant noise levels, or introduce high computational complexity. We present a nonlinear corner detection algorithm that does not require prior image information or any threshold to be set by the user. It provides 100% correct corner detection and fewer than I false positive corner per image when the contrast to noise ratio of the image is 6 or more, under Gaussian white noise.

Original language	English (US)
Pages (from-to)	304-309
Number of pages	6
Journal	Proceedings of SPIE-The International Society for Optical Engineering
Volume	4726
DOIs	https://doi.org/10.1117/12.477038
State	Published - Jan 1 2002

Keywords

Aerial images
Corner detection
Feature extraction
Image understanding

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.477038

Fingerprint Dive into the research topics of 'Corner detection for identification of man-made objects in noisy aerial images'. Together they form a unique fingerprint.

Cite this

@article{22328719822846819dccbc1028ad0354,

title = "Corner detection for identification of man-made objects in noisy aerial images",

abstract = "Corner detection is an essential feature extraction step in many image understanding applications including aerial image analysis and manufactured part inspection. Available corner detectors require the user to set critical manual thresholds, degrade under significant noise levels, or introduce high computational complexity. We present a nonlinear corner detection algorithm that does not require prior image information or any threshold to be set by the user. It provides 100% correct corner detection and fewer than I false positive corner per image when the contrast to noise ratio of the image is 6 or more, under Gaussian white noise.",

keywords = "Aerial images, Corner detection, Feature extraction, Image understanding",

author = "Bankman, {Isaac N.} and Rogala, {Eric W.}",

year = "2002",

month = jan,

day = "1",

doi = "10.1117/12.477038",

language = "English (US)",

volume = "4726",

pages = "304--309",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Corner detection for identification of man-made objects in noisy aerial images

AU - Bankman, Isaac N.

AU - Rogala, Eric W.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Corner detection is an essential feature extraction step in many image understanding applications including aerial image analysis and manufactured part inspection. Available corner detectors require the user to set critical manual thresholds, degrade under significant noise levels, or introduce high computational complexity. We present a nonlinear corner detection algorithm that does not require prior image information or any threshold to be set by the user. It provides 100% correct corner detection and fewer than I false positive corner per image when the contrast to noise ratio of the image is 6 or more, under Gaussian white noise.

AB - Corner detection is an essential feature extraction step in many image understanding applications including aerial image analysis and manufactured part inspection. Available corner detectors require the user to set critical manual thresholds, degrade under significant noise levels, or introduce high computational complexity. We present a nonlinear corner detection algorithm that does not require prior image information or any threshold to be set by the user. It provides 100% correct corner detection and fewer than I false positive corner per image when the contrast to noise ratio of the image is 6 or more, under Gaussian white noise.

KW - Aerial images

KW - Corner detection

KW - Feature extraction

KW - Image understanding

UR - http://www.scopus.com/inward/record.url?scp=0036035277&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036035277&partnerID=8YFLogxK

U2 - 10.1117/12.477038

DO - 10.1117/12.477038

M3 - Article

AN - SCOPUS:0036035277

VL - 4726

SP - 304

EP - 309

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -

Corner detection for identification of man-made objects in noisy aerial images

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this