An effective recognition algorithm for multiple targets under sea surface background

Jian-dong Wang; Biao Zhang

doi:10.1117/12.902307

8 September 2011 An effective recognition algorithm for multiple targets under sea surface background

Jian-dong Wang, Biao Zhang

Proceedings Volume 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications; 81934N (2011) https://doi.org/10.1117/12.902307
Event: International Symposium on Photoelectronic Detection and Imaging 2011, 2011, Beijing, China

Abstract

This paper describes an effective multiple targets recognition algorithm under the circumstances that the targets are with a sea surface background. The proposed algorithm relies on three steps. Firstly, an improved canny operator was adopted to get the edge characteristics of the image templates of airplanes, naval ships and islands , compared to the classical canny operator, the proposed canny operator can generate more accurate edges because of the anisotropic Gaussian filtering and the self-adaptive threshold estimate method it used. Secondly, to calculate the valid objects' positions and generate their edge binary images in the current image, region grown algorithm and improved canny algorithm were adopted. Finally, a hausdorff distance based categorizer was implemented to classify the objects already been located. Experimental results show that the approach performs well in multiple targets recognition in images with sea surface background , the proposed algorithm has strong pertinency and high efficiency to similar problems.

Citation Download Citation

Jian-dong Wang and Biao Zhang "An effective recognition algorithm for multiple targets under sea surface background", Proc. SPIE 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, 81934N (8 September 2011); https://doi.org/10.1117/12.902307

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