Multi-Scale Fusion Algorithm Based on Structure Similarity Index Constraint for Infrared Polarization and Intensity Images

Lei Zhang, Fengbao Yang, Linna JiIEEE Access 2017 · DOI

Abstract

At present, infrared polarization and intensity image fusion algorithms often cause fused images to appear fuzzy, making the fused image unable to be processed further. In this paper, a new infrared polarization and intensity image fusion algorithm is proposed, and the fused image is divided into base layer image and detail layer image. The infrared intensity image is used as the base layer image, and the infrared polarization image is decomposed by a multi-scale Gaussian filter and residual method. Next, a structural similarity index is introduced as the constraint of the multi-scale decomposition layers, and the detail layer image is obtained by summing of feature images of infrared polarization image. Finally, the fused image is obtained by the superimposition of the base layer image and detail layer image. The fused image retains all the features of the infrared intensity image and the majority of the polarization image features. The experimental results demonstrated that the fused image obtained by the proposed method performed better in both subjective and objective qualities.
BibTeX
@inproceedings{zhang2017multi,
  author = {Lei Zhang and Fengbao Yang and Linna Ji},
  title = {{Multi-Scale Fusion Algorithm Based on Structure Similarity Index Constraint for Infrared Polarization and Intensity Images}},
  booktitle = {IEEE Access},
  year = {2017},
  doi = {10.1109/access.2017.2764101},
}

Loading related content...

Figure