Geometric primitives detection in aerial image

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

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

1 Citation (Scopus)

Abstract

Geometric Primitives are important features for aerial image interpretation, especially for understanding of manmade objects. With the increasing resolution of aerial image, growing size and complexity of image make it more difficult to efficiently extract dependable geometric features such as lines and corners. In this paper, we propose a novel linear feature extraction approach called 'Trichotomy line Extraction'. According to the knowledge of geometric properties of interested objects in aerial image, i.e. manmade objects, a rule is designed to remove line segments meaningless for boundaries of interested objects. Then line updating is carried out based on spatial and geometric relation between lines, to improve connectivity of boundary lines and also to extract comers on object boundary. Experiment results show that proposed line extraction method can perform efficiently with accurate linear features of objects in large aerial image and meaningless line segments removing process is effective to improve the geometric features' description of object and to reduce computing burden of following step.

Original languageEnglish
Title of host publicationProceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006
Pages400-404
Number of pages5
Volume1
DOIs
Publication statusPublished - 2006
Event5th IEEE International Conference on Cognitive Informatics, ICCI 2006 - Beijing
Duration: 2006 Jul 172006 Jul 19

Other

Other5th IEEE International Conference on Cognitive Informatics, ICCI 2006
CityBeijing
Period06/7/1706/7/19

Fingerprint

Antennas
Feature extraction
Experiments

Keywords

  • Geometric primitive extraction
  • Line updating
  • Trichotomy line extraction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Cite this

Wang, J., Goto, S., Kunieda, K., Iwata, M., Koizumi, H., Shimazu, H., & Ikenaga, T. (2006). Geometric primitives detection in aerial image. In Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006 (Vol. 1, pp. 400-404). [4216440] https://doi.org/10.1109/COGINF.2006.365523

Geometric primitives detection in aerial image. / Wang, Jing; Goto, Satoshi; Kunieda, Kazuo; Iwata, Makoto; Koizumi, Hirokazu; Shimazu, Hideo; Ikenaga, Takeshi.

Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1 2006. p. 400-404 4216440.

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

Wang, J, Goto, S, Kunieda, K, Iwata, M, Koizumi, H, Shimazu, H & Ikenaga, T 2006, Geometric primitives detection in aerial image. in Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. vol. 1, 4216440, pp. 400-404, 5th IEEE International Conference on Cognitive Informatics, ICCI 2006, Beijing, 06/7/17. https://doi.org/10.1109/COGINF.2006.365523
Wang J, Goto S, Kunieda K, Iwata M, Koizumi H, Shimazu H et al. Geometric primitives detection in aerial image. In Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1. 2006. p. 400-404. 4216440 https://doi.org/10.1109/COGINF.2006.365523
Wang, Jing ; Goto, Satoshi ; Kunieda, Kazuo ; Iwata, Makoto ; Koizumi, Hirokazu ; Shimazu, Hideo ; Ikenaga, Takeshi. / Geometric primitives detection in aerial image. Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1 2006. pp. 400-404
@inproceedings{fc7358ebb50a4918a0aa5601e6f252a2,
title = "Geometric primitives detection in aerial image",
abstract = "Geometric Primitives are important features for aerial image interpretation, especially for understanding of manmade objects. With the increasing resolution of aerial image, growing size and complexity of image make it more difficult to efficiently extract dependable geometric features such as lines and corners. In this paper, we propose a novel linear feature extraction approach called 'Trichotomy line Extraction'. According to the knowledge of geometric properties of interested objects in aerial image, i.e. manmade objects, a rule is designed to remove line segments meaningless for boundaries of interested objects. Then line updating is carried out based on spatial and geometric relation between lines, to improve connectivity of boundary lines and also to extract comers on object boundary. Experiment results show that proposed line extraction method can perform efficiently with accurate linear features of objects in large aerial image and meaningless line segments removing process is effective to improve the geometric features' description of object and to reduce computing burden of following step.",
keywords = "Geometric primitive extraction, Line updating, Trichotomy line extraction",
author = "Jing Wang and Satoshi Goto and Kazuo Kunieda and Makoto Iwata and Hirokazu Koizumi and Hideo Shimazu and Takeshi Ikenaga",
year = "2006",
doi = "10.1109/COGINF.2006.365523",
language = "English",
volume = "1",
pages = "400--404",
booktitle = "Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006",

}

TY - GEN

T1 - Geometric primitives detection in aerial image

AU - Wang, Jing

AU - Goto, Satoshi

AU - Kunieda, Kazuo

AU - Iwata, Makoto

AU - Koizumi, Hirokazu

AU - Shimazu, Hideo

AU - Ikenaga, Takeshi

PY - 2006

Y1 - 2006

N2 - Geometric Primitives are important features for aerial image interpretation, especially for understanding of manmade objects. With the increasing resolution of aerial image, growing size and complexity of image make it more difficult to efficiently extract dependable geometric features such as lines and corners. In this paper, we propose a novel linear feature extraction approach called 'Trichotomy line Extraction'. According to the knowledge of geometric properties of interested objects in aerial image, i.e. manmade objects, a rule is designed to remove line segments meaningless for boundaries of interested objects. Then line updating is carried out based on spatial and geometric relation between lines, to improve connectivity of boundary lines and also to extract comers on object boundary. Experiment results show that proposed line extraction method can perform efficiently with accurate linear features of objects in large aerial image and meaningless line segments removing process is effective to improve the geometric features' description of object and to reduce computing burden of following step.

AB - Geometric Primitives are important features for aerial image interpretation, especially for understanding of manmade objects. With the increasing resolution of aerial image, growing size and complexity of image make it more difficult to efficiently extract dependable geometric features such as lines and corners. In this paper, we propose a novel linear feature extraction approach called 'Trichotomy line Extraction'. According to the knowledge of geometric properties of interested objects in aerial image, i.e. manmade objects, a rule is designed to remove line segments meaningless for boundaries of interested objects. Then line updating is carried out based on spatial and geometric relation between lines, to improve connectivity of boundary lines and also to extract comers on object boundary. Experiment results show that proposed line extraction method can perform efficiently with accurate linear features of objects in large aerial image and meaningless line segments removing process is effective to improve the geometric features' description of object and to reduce computing burden of following step.

KW - Geometric primitive extraction

KW - Line updating

KW - Trichotomy line extraction

UR - http://www.scopus.com/inward/record.url?scp=71049142323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71049142323&partnerID=8YFLogxK

U2 - 10.1109/COGINF.2006.365523

DO - 10.1109/COGINF.2006.365523

M3 - Conference contribution

VL - 1

SP - 400

EP - 404

BT - Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006

ER -