An infared polarization image fusion method based on NSCT and fuzzy C-means clustering segmentation algorithms

Xuelian Yu; Qian Chen; Guohua Gu; Weixian Qian; Mengxi Xu

doi:10.1117/12.2071158

20 November 2014 An infared polarization image fusion method based on NSCT and fuzzy C-means clustering segmentation algorithms

Xuelian Yu, Qian Chen, Guohua Gu, Weixian Qian, Mengxi Xu

Author Affiliations +

Proceedings Volume 9300, International Symposium on Optoelectronic Technology and Application 2014: Infrared Technology and Applications; 93000W (2014) https://doi.org/10.1117/12.2071158
Event: International Symposium on Optoelectronic Technology and Application 2014, 2014, Beijing, China

Abstract

The integration between polarization and intensity images possessing complementary and discriminative information has emerged as a new and important research area. On the basis of the consideration that the resulting image has different clarity and layering requirement for the target and background, we propose a novel fusion method based on non-subsampled Contourlet transform (NSCT) and fuzzy C-means (FCM) segmentation for IR polarization and light intensity images. First, the polarization characteristic image is derived from fusion of the degree of polarization (DOP) and the angle of polarization (AOP) images using local standard variation and abrupt change degree (ACD) combined criteria. Then, the polarization characteristic image is segmented with FCM algorithm. Meanwhile, the two source images are respectively decomposed by NSCT. The regional energy-weighted and similarity measure are adopted to combine the low-frequency sub-band coefficients of the object. The high-frequency sub-band coefficients of the object boundaries are integrated through the maximum selection rule. In addition, the high-frequency sub-band coefficients of internal objects are integrated by utilizing local variation, matching measure and region feature weighting. The weighted average and maximum rules are employed independently in fusing the low-frequency and high-frequency components of the background. Finally, an inverse NSCT operation is accomplished and the final fused image is obtained. The experimental results illustrate that the proposed IR polarization image fusion algorithm can yield an improved performance in terms of the contrast between artificial target and cluttered background and a more detailed representation of the depicted scene.

Citation Download Citation

Xuelian Yu, Qian Chen, Guohua Gu, Weixian Qian, and Mengxi Xu "An infared polarization image fusion method based on NSCT and fuzzy C-means clustering segmentation algorithms", Proc. SPIE 9300, International Symposium on Optoelectronic Technology and Application 2014: Infrared Technology and Applications, 93000W (20 November 2014); https://doi.org/10.1117/12.2071158

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