风电场无人机巡检红外叶片图像拼接算法  

Infrared Blade Image Stitching Algorithm for Wind Farm UAV Inspection

作　　者：周登科 郭星辰 史凯特 汤鹏 郑开元 马鹏阁[2] ZHOU Dengke;GUO Xingchen;SHI Kaite;TANG Peng;ZHENG Kaiyuan;MA Pengge(China Three Gorges Corporation Research Institute,Beijing 100038,China;Zhengzhou University of Aeronautics,Zhengzhou 450015,China)

机构地区：[1]中国长江三峡集团有限公司科学技术研究院,北京100038 [2]郑州航空工业管理学院智能工程学院,河南郑州450015

出　　处：《红外技术》2023年第11期1161-1168,共8页Infrared Technology

基　　金：国家自然科学基金民航联合基金重点项目(U1833203);中国长江三峡集团有限公司企业科研项目“海上风电无人机光电巡检系统技术研究及应用示范”(202003035);河南省科技攻关(202102210330);河南省科技攻关(222102210136);郑州航空工业管理学院研究生教育创新计划基金(2021CX48)。

摘　　要：针对无人机拍摄叶片红外图像背景冗余信息较多、拼接精度不高等问题,本文提出一种基于形态学改进Chan-Vese分割与局部特征匹配的红外风机叶片图像拼接算法,首先,对图像进行中值滤波降噪,使用形态学运算改进基于Chan-Vese模型的水平集算法,生成表达主体的掩膜。基于掩膜去除冗余背景提取局部Harris特征点;对掩膜进行二次形态学腐蚀处理,抑制边界锯齿像素上的伪特征点;最后,使用暴力匹配及随机抽样一致(Random Sample Consensus,RANSAC)算法筛选出有效匹配点对,计算单应性矩阵实现匹配拼接。与传统图像分割下Harris拼接算法相比,本文改进后的算法拼接精度有明显提高,在不同的测试场景下显示出较强鲁棒性。Aiming at more redundant background information and low stitching accuracy of the infrared images of the blades taken by UAV(Unmanned Aerial Vehicle),In this study,we proposed a stitching algorithm for infrared wind turbine blade images combining the Chan-Vese model and morphology.First,we subjected the image to median filtering and noise reduction,and a morphological operation improved a level-set algorithm based on the Chan-Vese model to generate the mask of the expression subject.We extracted Harris feature points by removing redundant backgrounds based on the mask.We performed morphological etching on the mask to suppress the pseudo-feature points on the boundary-jagged pixels.We used violent matching and the RANSAC algorithm to screen out effective matching point pairs and calculate the homography matrix to realize matching and splicing.Compared with the Harris stitching algorithm under traditional image segmentation,the stitching accuracy of the improved algorithm significantly improved,and it showed strong robustness in different test scenarios.

关 键 词：风力发电机叶片 红外图像拼接 水平集 形态学运算 Harris特征点 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]