Analysis and application based on GTF infrared and visible image fusion

From 1997 to 2006, China's railway has undergone six large-scale speed-raising reconstruction, and some of the speed has reached 250KM/h. With the development of train speed, the pantograph-cantenary system becomes more and more important. Since infrared image has light penetration, this paper fuses infrared and visible images to get more information about the pantograph-cantenary so that train drivers can learn more about the pantograph-cantenary situation. Existing fusion methods typically use the same representations and extract the similar characteristics for different source images. However, it may don't work for infrared and visible images. In this paper, we use the fusion algorithm named Gradient Transfer Fusion (GTF), which can keep the thermal radiation and appearance information simultaneously. To prove the effectiveness of the GTF method, it is compared with other 17 fusion algorithms from quantitative aspects. Furthermore, the parameter in the GTF method is analyzed and selected for better fusion results. Finally, color image fusion which is an improvement to the GTF method preserving the color information of the visible image in the fused image is proposed and it is tested on publicly available data sets to prove its availability.