A new multiscale line detection approach for aerial image with complex scene

Jing Wang, Takeshi Ikenaga, Satoshi Goto, Kazuo Kunieda, Makoto Iwata, Hirokazu Koizumi, Hideo Shimazu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Straight lines are important geometric features for aerial image understanding tasks like man-made object detection. As image scene becomes more complex, traditional method like Hough Transform may produce false detections and cannot work efficiently. In this paper, we propose a new multi-scale line detection approach that can efficiently detect semantic lines in aerial image with complex scene. Firstly, a method called "Trichotomy Line Extraction" detects reliable line segments locally. Then multi-scale image system is constructed by wavelet decomposition, from which global information is obtained to detect semantic lines. Experimental results show that proposed method can extract accurate linear features on complex scene aerial images in a robust and efficient way.

Original languageEnglish
Title of host publicationIEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS
Pages1968-1971
Number of pages4
DOIs
Publication statusPublished - 2006
EventAPCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems -
Duration: 2006 Dec 42006 Dec 6

Other

OtherAPCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems
Period06/12/406/12/6

Fingerprint

Antennas
Semantics
Image understanding
Wavelet decomposition
Hough transforms
Object detection

Keywords

  • Man-made object detection
  • Multi-scale line detection
  • Straight line
  • Wavelet decomposition

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Wang, J., Ikenaga, T., Goto, S., Kunieda, K., Iwata, M., Koizumi, H., & Shimazu, H. (2006). A new multiscale line detection approach for aerial image with complex scene. In IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS (pp. 1968-1971). [4145804] https://doi.org/10.1109/APCCAS.2006.342247

A new multiscale line detection approach for aerial image with complex scene. / Wang, Jing; Ikenaga, Takeshi; Goto, Satoshi; Kunieda, Kazuo; Iwata, Makoto; Koizumi, Hirokazu; Shimazu, Hideo.

IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS. 2006. p. 1968-1971 4145804.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, J, Ikenaga, T, Goto, S, Kunieda, K, Iwata, M, Koizumi, H & Shimazu, H 2006, A new multiscale line detection approach for aerial image with complex scene. in IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS., 4145804, pp. 1968-1971, APCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems, 06/12/4. https://doi.org/10.1109/APCCAS.2006.342247
Wang J, Ikenaga T, Goto S, Kunieda K, Iwata M, Koizumi H et al. A new multiscale line detection approach for aerial image with complex scene. In IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS. 2006. p. 1968-1971. 4145804 https://doi.org/10.1109/APCCAS.2006.342247
Wang, Jing ; Ikenaga, Takeshi ; Goto, Satoshi ; Kunieda, Kazuo ; Iwata, Makoto ; Koizumi, Hirokazu ; Shimazu, Hideo. / A new multiscale line detection approach for aerial image with complex scene. IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS. 2006. pp. 1968-1971
@inproceedings{2089cbc70cd84e66a897b8495ee9fd46,
title = "A new multiscale line detection approach for aerial image with complex scene",
abstract = "Straight lines are important geometric features for aerial image understanding tasks like man-made object detection. As image scene becomes more complex, traditional method like Hough Transform may produce false detections and cannot work efficiently. In this paper, we propose a new multi-scale line detection approach that can efficiently detect semantic lines in aerial image with complex scene. Firstly, a method called {"}Trichotomy Line Extraction{"} detects reliable line segments locally. Then multi-scale image system is constructed by wavelet decomposition, from which global information is obtained to detect semantic lines. Experimental results show that proposed method can extract accurate linear features on complex scene aerial images in a robust and efficient way.",
keywords = "Man-made object detection, Multi-scale line detection, Straight line, Wavelet decomposition",
author = "Jing Wang and Takeshi Ikenaga and Satoshi Goto and Kazuo Kunieda and Makoto Iwata and Hirokazu Koizumi and Hideo Shimazu",
year = "2006",
doi = "10.1109/APCCAS.2006.342247",
language = "English",
isbn = "1424403871",
pages = "1968--1971",
booktitle = "IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS",

}

TY - GEN

T1 - A new multiscale line detection approach for aerial image with complex scene

AU - Wang, Jing

AU - Ikenaga, Takeshi

AU - Goto, Satoshi

AU - Kunieda, Kazuo

AU - Iwata, Makoto

AU - Koizumi, Hirokazu

AU - Shimazu, Hideo

PY - 2006

Y1 - 2006

N2 - Straight lines are important geometric features for aerial image understanding tasks like man-made object detection. As image scene becomes more complex, traditional method like Hough Transform may produce false detections and cannot work efficiently. In this paper, we propose a new multi-scale line detection approach that can efficiently detect semantic lines in aerial image with complex scene. Firstly, a method called "Trichotomy Line Extraction" detects reliable line segments locally. Then multi-scale image system is constructed by wavelet decomposition, from which global information is obtained to detect semantic lines. Experimental results show that proposed method can extract accurate linear features on complex scene aerial images in a robust and efficient way.

AB - Straight lines are important geometric features for aerial image understanding tasks like man-made object detection. As image scene becomes more complex, traditional method like Hough Transform may produce false detections and cannot work efficiently. In this paper, we propose a new multi-scale line detection approach that can efficiently detect semantic lines in aerial image with complex scene. Firstly, a method called "Trichotomy Line Extraction" detects reliable line segments locally. Then multi-scale image system is constructed by wavelet decomposition, from which global information is obtained to detect semantic lines. Experimental results show that proposed method can extract accurate linear features on complex scene aerial images in a robust and efficient way.

KW - Man-made object detection

KW - Multi-scale line detection

KW - Straight line

KW - Wavelet decomposition

UR - http://www.scopus.com/inward/record.url?scp=50249151851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249151851&partnerID=8YFLogxK

U2 - 10.1109/APCCAS.2006.342247

DO - 10.1109/APCCAS.2006.342247

M3 - Conference contribution

AN - SCOPUS:50249151851

SN - 1424403871

SN - 9781424403875

SP - 1968

EP - 1971

BT - IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS

ER -