Real-time realization of infrared ship detection with an attention mechanism

Nanzhi Zeng; Yuehuan Wang; Tianxu Zhang

doi:10.1117/12.441416

25 September 2001 Real-time realization of infrared ship detection with an attention mechanism

Nanzhi Zeng, Yuehuan Wang, Tianxu Zhang

Proceedings Volume 4548, Multispectral and Hyperspectral Image Acquisition and Processing; (2001) https://doi.org/10.1117/12.441416
Event: Multispectral Image Processing and Pattern Recognition, 2001, Wuhan, China

Abstract

With the help of attention mechanism, small target pre-detection can improve the efficiency of detection, and along with the waterline detection, the judgment of whether IR ship targets exist can be made. In this paper, the ability of parallel computation of pre-detection is analyzed. Starting from two points: the balance between communication cost and parallel computation and the efficiency of utilization of the system resources, how to divide the computation task is under consideration, so as to be adapted to pipeline structure and parallel structure to get the best performance. Also, the performance of the algorithm in different size images is investigated. At the end of the paper, experiments are used to prove that the analysis in this paper can provide guidelines of the real-time realization of the algorithm.

Citation Download Citation

Nanzhi Zeng, Yuehuan Wang, and Tianxu Zhang "Real-time realization of infrared ship detection with an attention mechanism", Proc. SPIE 4548, Multispectral and Hyperspectral Image Acquisition and Processing, (25 September 2001); https://doi.org/10.1117/12.441416

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