吉林大学学报（理学版）2025，Vol.63Issue(2)：479-491,13.DOI:10.13413/j.cnki.jdxblxb.2023387
基于复合域多尺度分解的红外偏振图像融合方法
Infrared Polarization Image Fusion Method Based on Composite Domain Multi-scale Decomposition
摘要
Abstract
Aiming at the problems of poor image quality,lack of polarization information,and inadequate target texture details in current infrared polarization image fusion,we proposed an infrared polarization image fusion method based on composite domain multi-scale decomposition.Firstly,in the spatial domain,a two-scale decomposition of the source image was performed by using a bootstrap filter to obtain the detail and base layers,in the frequency domain,a multi-scale multi-directional decomposition of the base layer image was performed by using a non-subsampled shear-wave transform to obtain the low-frequency sub-band image and high-frequency sub-band image.Secondly,the principal component analysis-adaptive pulse coupled neural network fusion rule was used for high-frequency sub-band,an improved convolutional sparse representation was used for coefficient merging for the low-frequency sub-bands,and local energy weighting and selective fusion rules based on pixel similarity were used for detail layed fusion.Finally,the fused image was reconstructed by using an inverse transformation in the composite domain.Experimental results show that the proposed method outperforms other comparative fusion methods in subjective visual performance and eight objective evaluation metrics,indicating that the method has many advantages in infrared polarization image fusion and can effectively enhance the quality of fused images.关键词
红外偏振图像融合/非下采样剪切波变换/自适应脉冲耦合神经网络/卷积稀疏表示Key words
infrared polarization image fusion/non-subsampled shear-wave transform/adaptive pulse coupled neural network/convolutional sparse representation分类
信息技术与安全科学引用本文复制引用
陈广秋,魏洲,段锦,黄丹丹..基于复合域多尺度分解的红外偏振图像融合方法[J].吉林大学学报（理学版）,2025,63(2):479-491,13.基金项目
国家自然科学基金重大仪器专项基金(批准号:62127813)和吉林省科技发展计划项目(批准号:20210203181SF). （批准号:62127813）
