Colour Based Man-Made Object Detection in an Aerial Image

David Tien, Xiao Yi, Mansuo Zhao

Research output: Book chapter/Published conference paperConference paperpeer-review

15 Downloads (Pure)

Abstract

paper presents a colour based approach for urban object recognition. The main framework is to separate candidature objects by the nearest neighbour classification and then the desired objects are identified from the candidates with the help of geometry features. For the classification, the points of a targeting classifier and a non targeting classifier are established from training samples. The experiment shows the method is superior to other methods in extracting urban objects with mixed colours or single colour in various illuminations.
Original languageEnglish
Title of host publication4th ICITA 2007
EditorsShi Guanfan
Place of PublicationSydney, Australia
PublisherMacquarie Scientific Press
Pages306-309
Number of pages4
ISBN (Electronic)9780980326703
Publication statusPublished - 2007
EventInternational Conference on Information Technology and Applications (ICITA) - Harbin, China, China
Duration: 15 Jan 200718 Jan 2007

Conference

ConferenceInternational Conference on Information Technology and Applications (ICITA)
Country/TerritoryChina
Period15/01/0718/01/07

Fingerprint

Dive into the research topics of 'Colour Based Man-Made Object Detection in an Aerial Image'. Together they form a unique fingerprint.

Cite this