Region of interest detection on the complex sea scenes based on visual saliency

Junqi Liu; Zhi Li; Xueyang Zhang; Pengju Li; Yiqiao Xu

doi:10.1117/12.2553205

31 January 2020 Region of interest detection on the complex sea scenes based on visual saliency

Junqi Liu, Zhi Li, Xueyang Zhang, Pengju Li, Yiqiao Xu

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114274C (2020) https://doi.org/10.1117/12.2553205
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

Abstract

The ship detection technology has important civil and military value. Aiming at the problem of low accuracy of ship detection in complex sea scenes, a candidate region detection algorithm of maritime ship based on FT and Scharr is proposed. The FT saliency model can effectively suppress the background noise and highlight the central region of the target, but the detection effect of small target is poor. Scharr edge detection operator can highlight the edges of all salient targets, but it is easy to introduce background noise. The saliency maps obtained by FT and Scharr is fused by gaussian mixture function, so as to highlight the salient target and suppress the background noise. Finally, the region of interest is obtained by region extraction method. The detection results show that the fusion model can effectively suppress the background noise of the sea surface, and highlight the ship targets of all sizes, and has good effect in different complex sea scenes.

Citation Download Citation

Junqi Liu, Zhi Li, Xueyang Zhang, Pengju Li, and Yiqiao Xu "Region of interest detection on the complex sea scenes based on visual saliency", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114274C (31 January 2020); https://doi.org/10.1117/12.2553205

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