A combined use of multispectral and SAR images for ship detection and characterization through object based image analysis

Martina Aiello; Marco Gianinetto

doi:10.1117/12.2277941

5 October 2017 A combined use of multispectral and SAR images for ship detection and characterization through object based image analysis

Martina Aiello, Marco Gianinetto

Author Affiliations +

Proceedings Volume 10428, Earth Resources and Environmental Remote Sensing/GIS Applications VIII; 104280A (2017) https://doi.org/10.1117/12.2277941
Event: SPIE Remote Sensing, 2017, Warsaw, Poland

Abstract

Marine routes represent a huge portion of commercial and human trades, therefore surveillance, security and environmental protection themes are gaining increasing importance. Being able to overcome the limits imposed by terrestrial means of monitoring, ship detection from satellite has recently prompted a renewed interest for a continuous monitoring of illegal activities. This paper describes an automatic Object Based Image Analysis (OBIA) approach to detect vessels made of different materials in various sea environments. The combined use of multispectral and SAR images allows for a regular observation unrestricted by lighting and atmospheric conditions and complementarity in terms of geographic coverage and geometric detail. The method developed adopts a region growing algorithm to segment the image in homogeneous objects, which are then classified through a decision tree algorithm based on spectral and geometrical properties. Then, a spatial analysis retrieves the vessels’ position, length and heading parameters and a speed range is associated. Optimization of the image processing chain is performed by selecting image tiles through a statistical index. Vessel candidates are detected over amplitude SAR images using an adaptive threshold Constant False Alarm Rate (CFAR) algorithm prior the object based analysis. Validation is carried out by comparing the retrieved parameters with the information provided by the Automatic Identification System (AIS), when available, or with manual measurement when AIS data are not available. The estimation of length shows R²=0.85 and estimation of heading R²=0.92, computed as the average of R² values obtained for both optical and radar images.

Conference Presentation

Citation Download Citation

Martina Aiello and Marco Gianinetto "A combined use of multispectral and SAR images for ship detection and characterization through object based image analysis", Proc. SPIE 10428, Earth Resources and Environmental Remote Sensing/GIS Applications VIII, 104280A (5 October 2017); https://doi.org/10.1117/12.2277941

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