风机叶片无人机红外热图像拼接方法  

Infrared image stitch method of wind turbine blade based on UAV

作　　者：何赟泽 张帆[1] 刘昊 李杰 虞俊锋 侯岳骏 王洪金 He Yunze;Zhang Fan;Liu Hao;Li Jie;Yu Junfeng;Hou Yuejun;Wang Hongjin(College of Electrical and Information Engineering,Hunan University,Changsha 410082,China;PowerChina Zhongnan Engineering Corporation Limited,Changsha 410014,China)

机构地区：[1]湖南大学电气与信息工程学院,长沙410082 [2]中国电建中南勘测设计研究院有限公司,长沙410014

出　　处：《电子测量与仪器学报》2022年第7期44-53,共10页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金委员会与英国皇家学会合作交流项目(61811530331);三维随机编码激励空间欠采样红外热成像缺陷层析机理(61901167)项目资助。

摘　　要：针对风机叶片红外图像拼接困难的问题,提出了一种基于无人机速度信息的风机叶片红外图像拼接方法。首先,利用U-net网络预测获得叶片掩膜图像,从而去除冗余的背景信息;其次,计算平移、旋转、缩放参数使拼接图像配准;最后,使用Multiband Blend算法对拼接图像进行融合,消除视场与光照变化引起的拼缝。实验结果表明,本文提出的方法在拼接处x梯度方向上的RMSE小于SURF等传统图像拼接方法,拼接成功率达97.8%,并成功获取风机叶片红外全景图。将Multiband Blend算法应用于叶片红外图像融合,结果表明融合后图像拼接处RMSE显著降低,过渡更加平滑。A wind turbine blade infrared image stitch method based on UAV speed information is proposed for the difficulties in wind turbine blade infrared image stitch.Firstly,the blade mask image is predicted by U-net network to remove the redundant background information.Secondly,the parameters of translation,rotation and scaling are calculated to register the stitched image.Finally,the multiband blend algorithm is used to fuse the stitched images to eliminate the stitching caused by the change of field of view and illumination.The experimental results show that the RMSE of the proposed method in the x gradient direction of the splicing area is less than that of traditional image stitching methods,the stitching success rate is 98.26%,and the infrared panorama of wind turbine blade is successfully obtained.The multiband blend algorithm is applied to wind turbine blade infrared image fusion,and the results show that the RMSE at the image mosaic is significantly reduced and the transition is smoother.

关 键 词：风力发电机叶片 红外图像拼接 U-net Multiband Blend算法 无人机 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TH89[自动化与计算机技术—计算机科学与技术]