19 February 2018 Infrared and visible images fusion based on visual saliency map and NSCT
Author Affiliations +
Proceedings Volume 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis; 106070K (2018) https://doi.org/10.1117/12.2283432
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China
Abstract
A fusion algorithm of infrared and visible images based on visual saliency map (VSM) and nonsubsampled contourlet transform (NSCT) was proposed. Usually, the visual salient region of infrared image is directed towards the targets which interpret the most important information in the image. For the given registered infrared and visible images, firstly, the frequency-tuned (FT) saliency detection algorithm is used to calculate the visual saliency map of infrared and visible images. Then the size of each salient region is obtained by maximizing entropy. In order to capture the details of the infrared and visible images, the low and high frequency fusion coefficients of nonsubsampled contourlet transform (NSCT) are selected based on region saliency, region energy (RE) and region sharpness (RS). Four different data sets from TNO, Human Factors are employed, and experimental results indicate that the proposed method can achieve a superior performance compared with other fusion methods in both subjective and objective assessments.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yanfei Chen, Yanfei Chen, Min Cao, Min Cao, Wenxiang Li, Wenxiang Li, } "Infrared and visible images fusion based on visual saliency map and NSCT", Proc. SPIE 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis, 106070K (19 February 2018); doi: 10.1117/12.2283432; https://doi.org/10.1117/12.2283432
PROCEEDINGS
8 PAGES


SHARE
Back to Top