A camouflage generation algorithm based on modified K-means clustering

Yinsong Kong; Congwei Liao; Shengxiang Huang; Leilei Qiu; Lianwen Deng

doi:10.1117/12.2685733

15 August 2023 A camouflage generation algorithm based on modified K-means clustering

Yinsong Kong, Congwei Liao, Shengxiang Huang, Leilei Qiu, Lianwen Deng

Proceedings Volume 12719, Second International Conference on Electronic Information Technology (EIT 2023); 127194V (2023) https://doi.org/10.1117/12.2685733
Event: Second International Conference on Electronic Information Technology (EIT 2023), 2023, Wuhan, China

Abstract

The advent of high-tech means of detection posed a huge challenge to traditional camouflage imaging. It is important to develop a more efficient and better performing digital camouflage algorithm to improve the poor camouflage effects. The performance of camouflage generation is mainly affected by the camouflage color and camouflage texture. In this paper, we propose a novel design of digital camouflage based on he K-means clustering optimized by genetic algorithm. First, we randomly call the plaque of the target neighborhood to retain texture details, and then smooth the removal of abrupt boundaries. Then, we extract primary colors from the background and precisely reduce the influence of randomization of the initial cluster center using a clustering method. By comparing with the other reported camouflage patterns, we find that the output camouflage patterns generated by our proposed method greatly match the background and have good camouflage effect.

Citation Download Citation

Yinsong Kong, Congwei Liao, Shengxiang Huang, Leilei Qiu, and Lianwen Deng "A camouflage generation algorithm based on modified K-means clustering", Proc. SPIE 12719, Second International Conference on Electronic Information Technology (EIT 2023), 127194V (15 August 2023); https://doi.org/10.1117/12.2685733

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