Applying daytime colors to night-time imagery with an efficient color transfer method

Guangxin Li; Ke Wang

doi:10.1117/12.720787

27 April 2007 Applying daytime colors to night-time imagery with an efficient color transfer method

Guangxin Li, Ke Wang

Proceedings Volume 6559, Enhanced and Synthetic Vision 2007; 65590L (2007) https://doi.org/10.1117/12.720787
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

Abstract

We propose a color transfer method to give fused multiband nighttime imagery a natural daytime color appearance in a simple and efficient way. Instead of using traditional _&rhookl;&agr;_&bgr; space, the proposed method transfers the color distribution of the target image (daylight color image) to the source image (fused multiband nighttime imagery) in a linear color space named IUV. The transformation between RGB and IUV spaces is simpler than that between RGB and _&rhookl;&agr;_&bgr; spaces, moreover, the IUV space is more suitable for image fusion. The IUV transform can be extended into a general formalism. We prove that color spaces conforming to this general IUV framework can produce same recoloring results as IUV space. Our experiments on infrared and visual images show that the IUV based color transfer method works surprisingly well for transferring natural color characteristics of daylight color images to false color fused multiband nighttime imagery. We also demonstrate that this method can be successfully applied to a variety of images. The images generated indicate the potential utility of IUV space in color image processing domains.

Citation Download Citation

Guangxin Li and Ke Wang "Applying daytime colors to night-time imagery with an efficient color transfer method", Proc. SPIE 6559, Enhanced and Synthetic Vision 2007, 65590L (27 April 2007); https://doi.org/10.1117/12.720787

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