Civilian ship classification based on structure features in high resolution SAR images

Shaofeng Jiang; Chao Wang; Hong Zhang; Fan Wu; Bo Zhang

doi:10.1117/12.979643

11 December 2012 Civilian ship classification based on structure features in high resolution SAR images

Shaofeng Jiang, Chao Wang, Hong Zhang, Fan Wu, Bo Zhang

Proceedings Volume 8525, Remote Sensing of the Marine Environment II; 852505 (2012) https://doi.org/10.1117/12.979643
Event: SPIE Asia-Pacific Remote Sensing, 2012, Kyoto, Japan

Abstract

With the globalization there is an increasing degree of concern on the ship traffic monitoring. Civilian ship classification is an important research area, as it can help to improve sea traffic surveillance and control activities. By making use of the new generation SAR satellites like COSMO-SkyMed, civilian ship classification in high resolution SAR images is a hotspot and preceding problem in SAR applications. This paper presents a ship classification method that uses single-pol COSMO-SkyMed images to categorize civilian ships into three types, including bulk carriers, container ships and oil tankers. The experimental results based on ship structure features show that the whole classification accuracy is above 80%.

Citation Download Citation

Shaofeng Jiang, Chao Wang, Hong Zhang, Fan Wu, and Bo Zhang "Civilian ship classification based on structure features in high resolution SAR images", Proc. SPIE 8525, Remote Sensing of the Marine Environment II, 852505 (11 December 2012); https://doi.org/10.1117/12.979643

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