Sea-land segmentation based on template matching

Shanlan Nie; Haopeng Zhang; Zhiguo Jiang

doi:10.1145/3033288.3033309

Sea-land segmentation based on template matching

Shanlan Nie
, Haopeng Zhang
, Zhiguo Jiang

School of Astronautics

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

In this paper, a novel sea-land segmentation method based on template matching is proposed. Firstly, we use OTSU to get coastline curve from harbor image. Subsequently, the curvature integral of the coastline curve is calculated as our matching signature, and matched parts between the two curves are found by using normalized cross-correlation. Finally, affine transformation is estimated and applied, thus completing the sea-land segmentation in harbor image. In order to research the limit capacity of template matching over the image resolution and relative angle between template image and harbor image, experiments on Google Map dataset had been made, and the boundary condition on resolution and angle was analyzed based on the experimental results.

Original language	English
Title of host publication	Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016
Publisher	Association for Computing Machinery
Pages	32-36
Number of pages	5
ISBN (Electronic)	9781450347938
DOIs	https://doi.org/10.1145/3033288.3033309
State	Published - 17 Dec 2016
Event	5th International Conference on Network, Communication and Computing, ICNCC 2016 - Kyoto, Japan Duration: 17 Dec 2016 → 21 Dec 2016

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	5th International Conference on Network, Communication and Computing, ICNCC 2016
Country/Territory	Japan
City	Kyoto
Period	17/12/16 → 21/12/16

Keywords

Curvature integral
Sea-land segmentation
Template matching

Access to Document

10.1145/3033288.3033309

Cite this

@inproceedings{487ccfd098394c8588dcf633d631b2d2,

title = "Sea-land segmentation based on template matching",

abstract = "In this paper, a novel sea-land segmentation method based on template matching is proposed. Firstly, we use OTSU to get coastline curve from harbor image. Subsequently, the curvature integral of the coastline curve is calculated as our matching signature, and matched parts between the two curves are found by using normalized cross-correlation. Finally, affine transformation is estimated and applied, thus completing the sea-land segmentation in harbor image. In order to research the limit capacity of template matching over the image resolution and relative angle between template image and harbor image, experiments on Google Map dataset had been made, and the boundary condition on resolution and angle was analyzed based on the experimental results.",

keywords = "Curvature integral, Sea-land segmentation, Template matching",

author = "Shanlan Nie and Haopeng Zhang and Zhiguo Jiang",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 5th International Conference on Network, Communication and Computing, ICNCC 2016 ; Conference date: 17-12-2016 Through 21-12-2016",

year = "2016",

month = dec,

day = "17",

doi = "10.1145/3033288.3033309",

language = "英语",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery ",

pages = "32--36",

booktitle = "Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016",

address = "美国",

}

Nie, S, Zhang, H & Jiang, Z 2016, Sea-land segmentation based on template matching. in Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016. ACM International Conference Proceeding Series, Association for Computing Machinery , pp. 32-36, 5th International Conference on Network, Communication and Computing, ICNCC 2016, Kyoto, Japan, 17/12/16. https://doi.org/10.1145/3033288.3033309

Sea-land segmentation based on template matching. / Nie, Shanlan; Zhang, Haopeng ; Jiang, Zhiguo.
Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016. Association for Computing Machinery , 2016. p. 32-36 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Sea-land segmentation based on template matching

AU - Nie, Shanlan

AU - Zhang, Haopeng

AU - Jiang, Zhiguo

PY - 2016/12/17

Y1 - 2016/12/17

N2 - In this paper, a novel sea-land segmentation method based on template matching is proposed. Firstly, we use OTSU to get coastline curve from harbor image. Subsequently, the curvature integral of the coastline curve is calculated as our matching signature, and matched parts between the two curves are found by using normalized cross-correlation. Finally, affine transformation is estimated and applied, thus completing the sea-land segmentation in harbor image. In order to research the limit capacity of template matching over the image resolution and relative angle between template image and harbor image, experiments on Google Map dataset had been made, and the boundary condition on resolution and angle was analyzed based on the experimental results.

AB - In this paper, a novel sea-land segmentation method based on template matching is proposed. Firstly, we use OTSU to get coastline curve from harbor image. Subsequently, the curvature integral of the coastline curve is calculated as our matching signature, and matched parts between the two curves are found by using normalized cross-correlation. Finally, affine transformation is estimated and applied, thus completing the sea-land segmentation in harbor image. In order to research the limit capacity of template matching over the image resolution and relative angle between template image and harbor image, experiments on Google Map dataset had been made, and the boundary condition on resolution and angle was analyzed based on the experimental results.

KW - Curvature integral

KW - Sea-land segmentation

KW - Template matching

UR - https://www.scopus.com/pages/publications/85018366271

U2 - 10.1145/3033288.3033309

DO - 10.1145/3033288.3033309

M3 - 会议稿件

AN - SCOPUS:85018366271

T3 - ACM International Conference Proceeding Series

SP - 32

EP - 36

BT - Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016

PB - Association for Computing Machinery

T2 - 5th International Conference on Network, Communication and Computing, ICNCC 2016

Y2 - 17 December 2016 through 21 December 2016

ER -

Sea-land segmentation based on template matching

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this