In-shore ship extraction from HR optical remote sensing image via salience structure and GIS information

Xiaoyuan Ren; Libing Jiang; Xiao-an Tang

doi:10.1117/12.2203662

14 December 2015 In-shore ship extraction from HR optical remote sensing image via salience structure and GIS information

Xiaoyuan Ren, Libing Jiang, Xiao-an Tang

Author Affiliations +

Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 98150U (2015) https://doi.org/10.1117/12.2203662
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China

Abstract

In order to solve the problem of in-shore ship extraction from remote sensing image, a novel method for in-shore ship extraction from high resolution (HR) optical remote sensing image is proposed via salience structure feature and GIS information. Firstly, the berth ROI is located in the image with the aid of the prior GIS auxiliary information. Secondly, the salient corner features at ship bow are extracted from the berth ROI precisely. Finally, a recursive algorithm concerning the symmetric geometry of the ship target is conducted to discriminate the multi docked in-shore targets into mono in-shore ships. The results of the experiments show that the method proposed in this paper can detect the majority of large and medium scale in-shore ships from the optical remote sensing image, including both the mono and the multi adjacent docked in-shore ship cases.

Citation Download Citation

Xiaoyuan Ren, Libing Jiang, and Xiao-an Tang "In-shore ship extraction from HR optical remote sensing image via salience structure and GIS information", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 98150U (14 December 2015); https://doi.org/10.1117/12.2203662

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available