Fisheye Image Correction Based on Straight-Line Detection and Preservation

Qieshi Zhang, Seiichiro Kamata

研究成果: Conference contribution

3 引用 (Scopus)

抄録

Fisheye lenses are widely used when the users want to capture the image/video with wide field of view (FoV) which is particularly suited to surveillance monitoring and vehicle camera. However, no projection from the actual scene in wide FoV image can avoid the distortion. If this problem cannot be solved, the fisheye image will difficult be used for object detection or analysis due to the distorted shapes of the scene objects. To correct this problem and obtain the natural-looking image, a two-step correction approach is proposed. Firstly, adaptive latitude and longitude correction are presented and the Hough transform is used to detect and estimate the straight-line. Secondly, the straight-line preserving and orientation, consistency based optimization is examined to obtain the final correction result. To compare the effectiveness of the proposed method, some fisheye correction methods are discussed. The experimental results demonstrate that the proposed method can obtain the coherent natural-looking.

元の言語English
ホスト出版物のタイトルProceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
出版者Institute of Electrical and Electronics Engineers Inc.
ページ1793-1797
ページ数5
ISBN(印刷物)9781479986965
DOI
出版物ステータスPublished - 2016 1 12
イベントIEEE International Conference on Systems, Man, and Cybernetics, SMC 2015 - Kowloon Tong, Hong Kong
継続期間: 2015 10 92015 10 12

Other

OtherIEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
Hong Kong
Kowloon Tong
期間15/10/915/10/12

Fingerprint

Hough transforms
Lenses
Cameras
Monitoring
Object detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Information Systems and Management
  • Control and Systems Engineering

これを引用

Zhang, Q., & Kamata, S. (2016). Fisheye Image Correction Based on Straight-Line Detection and Preservation. : Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015 (pp. 1793-1797). [7379446] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2015.314

Fisheye Image Correction Based on Straight-Line Detection and Preservation. / Zhang, Qieshi; Kamata, Seiichiro.

Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1793-1797 7379446.

研究成果: Conference contribution

Zhang, Q & Kamata, S 2016, Fisheye Image Correction Based on Straight-Line Detection and Preservation. : Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015., 7379446, Institute of Electrical and Electronics Engineers Inc., pp. 1793-1797, IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015, Kowloon Tong, Hong Kong, 15/10/9. https://doi.org/10.1109/SMC.2015.314
Zhang Q, Kamata S. Fisheye Image Correction Based on Straight-Line Detection and Preservation. : Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1793-1797. 7379446 https://doi.org/10.1109/SMC.2015.314
Zhang, Qieshi ; Kamata, Seiichiro. / Fisheye Image Correction Based on Straight-Line Detection and Preservation. Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1793-1797
@inproceedings{37916cdaeeb54d14aa328dd2e542ceac,
title = "Fisheye Image Correction Based on Straight-Line Detection and Preservation",
abstract = "Fisheye lenses are widely used when the users want to capture the image/video with wide field of view (FoV) which is particularly suited to surveillance monitoring and vehicle camera. However, no projection from the actual scene in wide FoV image can avoid the distortion. If this problem cannot be solved, the fisheye image will difficult be used for object detection or analysis due to the distorted shapes of the scene objects. To correct this problem and obtain the natural-looking image, a two-step correction approach is proposed. Firstly, adaptive latitude and longitude correction are presented and the Hough transform is used to detect and estimate the straight-line. Secondly, the straight-line preserving and orientation, consistency based optimization is examined to obtain the final correction result. To compare the effectiveness of the proposed method, some fisheye correction methods are discussed. The experimental results demonstrate that the proposed method can obtain the coherent natural-looking.",
keywords = "Fisheye image correction, straight-line detection, straight-line preservation, wide field of view (FoV)",
author = "Qieshi Zhang and Seiichiro Kamata",
year = "2016",
month = "1",
day = "12",
doi = "10.1109/SMC.2015.314",
language = "English",
isbn = "9781479986965",
pages = "1793--1797",
booktitle = "Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fisheye Image Correction Based on Straight-Line Detection and Preservation

AU - Zhang, Qieshi

AU - Kamata, Seiichiro

PY - 2016/1/12

Y1 - 2016/1/12

N2 - Fisheye lenses are widely used when the users want to capture the image/video with wide field of view (FoV) which is particularly suited to surveillance monitoring and vehicle camera. However, no projection from the actual scene in wide FoV image can avoid the distortion. If this problem cannot be solved, the fisheye image will difficult be used for object detection or analysis due to the distorted shapes of the scene objects. To correct this problem and obtain the natural-looking image, a two-step correction approach is proposed. Firstly, adaptive latitude and longitude correction are presented and the Hough transform is used to detect and estimate the straight-line. Secondly, the straight-line preserving and orientation, consistency based optimization is examined to obtain the final correction result. To compare the effectiveness of the proposed method, some fisheye correction methods are discussed. The experimental results demonstrate that the proposed method can obtain the coherent natural-looking.

AB - Fisheye lenses are widely used when the users want to capture the image/video with wide field of view (FoV) which is particularly suited to surveillance monitoring and vehicle camera. However, no projection from the actual scene in wide FoV image can avoid the distortion. If this problem cannot be solved, the fisheye image will difficult be used for object detection or analysis due to the distorted shapes of the scene objects. To correct this problem and obtain the natural-looking image, a two-step correction approach is proposed. Firstly, adaptive latitude and longitude correction are presented and the Hough transform is used to detect and estimate the straight-line. Secondly, the straight-line preserving and orientation, consistency based optimization is examined to obtain the final correction result. To compare the effectiveness of the proposed method, some fisheye correction methods are discussed. The experimental results demonstrate that the proposed method can obtain the coherent natural-looking.

KW - Fisheye image correction

KW - straight-line detection

KW - straight-line preservation

KW - wide field of view (FoV)

UR - http://www.scopus.com/inward/record.url?scp=84964427005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964427005&partnerID=8YFLogxK

U2 - 10.1109/SMC.2015.314

DO - 10.1109/SMC.2015.314

M3 - Conference contribution

SN - 9781479986965

SP - 1793

EP - 1797

BT - Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -