Ship detection based on spatial partial features

Hong-hu Wang; Fu-gen Zhou; Ting Jin

doi:10.1117/12.2034060

11 September 2013 Ship detection based on spatial partial features

Hong-hu Wang, Fu-gen Zhou, Ting Jin

Proceedings Volume 8907, International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications; 89073M (2013) https://doi.org/10.1117/12.2034060
Event: ISPDI 2013 - Fifth International Symposium on Photoelectronic Detection and Imaging, 2013, Beijing, China

Abstract

This paper mainly studies how to detect a wide variety of ships from the ship-borne infrared images in order to implement sea monitoring. Different types of ships have significant differences in their appearance. The traditional detection method which uses the global texture features of the object is not suitable to detect varied ships. This paper presents a novel detection algorithm which extracts spatial partial texture features trained by Adaboost to establish the ship model for detection. We first extract all the partial regions of the object through random traversal, and then extract the texture features by using the “Uniform LBP” operator. Compared to the traditional way, we save each partial feature individually as one feature vector, which not only reduces the vector dimension but also highlights the key regions when the partial regions with strong generality are selected by Adaboost at the second step. Finally, the selected partial features are boosted with weights to establish ship model for the ship detection. The proposed approach is efficient and robust in the infrared ship detection.

Citation Download Citation

Hong-hu Wang, Fu-gen Zhou, and Ting Jin "Ship detection based on spatial partial features", Proc. SPIE 8907, International Symposium on Photoelectronic Detection and Imaging 2013: Infrared Imaging and Applications, 89073M (11 September 2013); https://doi.org/10.1117/12.2034060

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