基于MSR和BCI的变电站巡检图像融合方法

Substation Inspection Image Fusion Method Based on MSR and BCI

针对变电站巡检红外报警系统中的故障点温度读取与定位、目标设备分割、故障点匹配融合等问题,文章提出了一种基于多尺度Retinex(multi-scale retinex,MSR)和双三次插值(bi-cubic interpolation,BCI)的变电站巡检图像融合方法。首先采用MSR算法增强设备边缘图像;然后,提出改进的单元连接脉冲耦合神经网络(modified unit-linking-pulse coupled neural networks,MUL-PCNN)设置连接强度系数,并由最小均方误差(minimum mean square error,MMSE)完成最佳分割;最后,使用可信的BCI方法将红外图像中的灰度值融合到视觉图像中,完成视觉图像与红外图像的融合,从而实现变电站的安全巡检。实验结果表明,该方法对视觉图像与红外图像的融合具有很好的效果,实现了对变电站设备故障的正确检测。

Aiming at the problem of fault point temperature reading and positioning,target device segmentation,and fault point matching fusion in infrared warning system of substation inspection,a method of substation inspection image fusion based on MSR and BCI is proposed.Firstly,the MSR algorithm is used to enhance the edge image of device.Secondly,the modified unit-linking-pulse coupled neural networks (MUL-PCNN) is proposed to set the connection strength coefficient,and the minimum mean square error (MMSE) is used to achieve the best segmentation.Finally,the credible BCI method is used to fuse the gray value of the infrared image into the visual image to complete the fusion of the visual image and the infrared image,so as to realize the safety inspection of the substation.The experimental results show that the proposed method has a good effect on the fusion of visual image and infrared image,which can realize the correct detection of the substation equipment fault.