Research on decomposition and fusion of color and polarization image based on SCM

Meng Lv; Jin Duan; Suxin Mo; Wentao Zhu; Yong Zhu

doi:10.1117/12.2589699

18 March 2021 Research on decomposition and fusion of color and polarization image based on SCM

Meng Lv, Jin Duan, Suxin Mo, Wentao Zhu, Yong Zhu

Proceedings Volume 11780, Global Intelligent Industry Conference 2020; 117800N (2021) https://doi.org/10.1117/12.2589699
Event: Global Intelligent Industry Conference 2020, 2020, Guangzhou, China

Abstract

The traditional fusion method for polarization image and color image is difficult to be satisfied in practice, so the method based on SCM in the fusion of polarization image and color image is designed and combined with HSV color field adaptive enhancement, so as to achieve the effect of distinguishing objects under shadow or reflection. Using the multi-scale decomposition of guided filter and Gaussian filter, different fusion schemes are proposed for different scale information: the average energy fusion method is used for the low-frequency coefficients, and the SCM with the edge energy (EOE) as the stimulation is used to replace the traditional high-frequency fusion rules, so as to enhance the spatial information expression. Finally, the parameters are corrected by the consistency test. Experiments show that this method not only has a good color expression ability, but also effectively adds the polarization information of the target object, and achieves good performance in objective and supervisor evaluation.

Citation Download Citation

Meng Lv, Jin Duan, Suxin Mo, Wentao Zhu, and Yong Zhu "Research on decomposition and fusion of color and polarization image based on SCM", Proc. SPIE 11780, Global Intelligent Industry Conference 2020, 117800N (18 March 2021); https://doi.org/10.1117/12.2589699

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