This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important reg...This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important regions and background regions. Each feature of the regions is used to determine the region’s degree of membership in the multiresolution representation, and then to achieve multiresolution representation of the fusion result. The final image fusion result can be obtained by using the inverse multiresolution transform. Experiments showed that the proposed image fusion method can have better performance than existing image fusion methods.展开更多
为了进一步提升红外与可见光图像融合方法的性能,本文提出了一种基于多尺度局部极值分解与深度学习网络ResNet152的红外与可见光图像融合方法。首先,利用多尺度局部极值分解(multiscale local extrema decomposition,MLED)方法将源图像...为了进一步提升红外与可见光图像融合方法的性能,本文提出了一种基于多尺度局部极值分解与深度学习网络ResNet152的红外与可见光图像融合方法。首先,利用多尺度局部极值分解(multiscale local extrema decomposition,MLED)方法将源图像分解为近似图像和细节图像,分离出源图像中重叠的重要特征信息。然后采用残差网络ResNet152深度提取源图像的多维显著特征,以l_(1)-范数作为活性测度生成显著特征图,对近似图像进行加权平均融合,以保持能量和残留细节信息不丢失。在细节图像中,利用“系数绝对值取大”规则获得初始决策图,源图像作为引导图像,初始决策图作为输入图像进行引导滤波处理,得到优化决策图,计算加权局部能量得到能量显著图,对细节图像进行加权平均融合,使融合图像具有丰富的纹理细节和良好的视觉边缘感知。最后,对近似融合图像和细节融合图像进行重构,得到融合图像。实验结果表明,与现有的典型融合方法相比,本文所提出的融合方法在客观评价和视觉感受方面都取得了最好的效果。展开更多
基金Project supported by the National Natural Science Foundation of China (No. 60375008), China Aviation Science Foundation (No.02D57003), China Ph.D Discipline Special Foundation (No.20020248029), and Shanghai Key Scientific Project (No.02DZ15001), China
文摘This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important regions and background regions. Each feature of the regions is used to determine the region’s degree of membership in the multiresolution representation, and then to achieve multiresolution representation of the fusion result. The final image fusion result can be obtained by using the inverse multiresolution transform. Experiments showed that the proposed image fusion method can have better performance than existing image fusion methods.
文摘为了进一步提升红外与可见光图像融合方法的性能,本文提出了一种基于多尺度局部极值分解与深度学习网络ResNet152的红外与可见光图像融合方法。首先,利用多尺度局部极值分解(multiscale local extrema decomposition,MLED)方法将源图像分解为近似图像和细节图像,分离出源图像中重叠的重要特征信息。然后采用残差网络ResNet152深度提取源图像的多维显著特征,以l_(1)-范数作为活性测度生成显著特征图,对近似图像进行加权平均融合,以保持能量和残留细节信息不丢失。在细节图像中,利用“系数绝对值取大”规则获得初始决策图,源图像作为引导图像,初始决策图作为输入图像进行引导滤波处理,得到优化决策图,计算加权局部能量得到能量显著图,对细节图像进行加权平均融合,使融合图像具有丰富的纹理细节和良好的视觉边缘感知。最后,对近似融合图像和细节融合图像进行重构,得到融合图像。实验结果表明,与现有的典型融合方法相比,本文所提出的融合方法在客观评价和视觉感受方面都取得了最好的效果。
