Sea-land-line extraction using weighted optimum neighborhood algorithm

Jinhui Lan; Zengli Jia; Chunhong Wu; Jun Yang

doi:10.1117/12.2038018

19 December 2013 Sea-land-line extraction using weighted optimum neighborhood algorithm

Jinhui Lan, Zengli Jia, Chunhong Wu, Jun Yang

Proceedings Volume 9045, 2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology; 90451M (2013) https://doi.org/10.1117/12.2038018
Event: International Conference on Optical Instruments and Technology (OIT2013), 2013, Beijing, China

Abstract

In the field of automatic target recognition, research on automatic target recognition in water becomes increasingly important due to its value in maritime security and defense. Sea-land-line extraction under complicated sea-land-sky background plays an important role in water surface target recognition. The weighted optimum neighborhood algorithm is proposed by the feature of complicated sea-land-sky background images. Firstly pretreatment operations and Hough transform are taken in the image to find the potential sea-land-lines. There are several false sea-land-lines and a true sealand- line in these sea-land-lines. In the next step, the weighted values of the fitted sea-land lines’ neighborhood are calculated and the fitted line, which has the biggest weighted value, is the correct sea-land-line. The experimental results show that the algorithm can detect the sea-land-line under complicated sea-land-sky background correctly and effectively, and has advantages such as strong robustness, more accurate and high practical value.

Citation Download Citation

Jinhui Lan, Zengli Jia, Chunhong Wu, and Jun Yang "Sea-land-line extraction using weighted optimum neighborhood algorithm", Proc. SPIE 9045, 2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology, 90451M (19 December 2013); https://doi.org/10.1117/12.2038018

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