基于GBVS模型和引导滤波的遥感图像融合

Remote Sensing Image Fusion Method Based on GBVS Model and Guided Filtering

针对全色和多光谱图像融合问题,提出了一种利用基于图形的视觉显著性(GBVS)模型和引导滤波的遥感图像融合方法。首先,对多光谱图像进行亮度?色度?饱和度(IHS)变换,利用简化GBVS模型对显著图比较,得到初始权重图;然后,采用引导滤波优化初始权重图,分别融合2种图像的平滑信息和细节信息;最后,经IHS逆变换后得到最终的融合结果。试验结果表明,与5种遥感图像融合方法相比,该方法得到的融合结果在主观视觉效果及客观定量评价指标上优于其他方法,且运行时间至少缩短了50%。

Aimed at the fusion problem of the panchromatic and multi-spectral images,a remote sensing image fusion method on the basis of graph-based visual saliency(GBVS)model and guided filtering is proposed.Firstly,intensity,hue and saturation(IHS)transform is performed on the multi-spectral image.The saliency maps are compared with the simplified GBVS model,and the initial weighted maps are achieved.Then,the guided filtering is adopted to optimize initial weighted maps.The smoothing information and the detail information of the two kinds of images are respectively fused.Finally,the final fusion result is ultimately achieved with an inverse IHS transform.Experimental results show that it is superior to the other five remote sensing image fusion methods in subjective visual effect and objective quantitative evaluation index.The elapsed time is reduced at least half.