摘要
针对绝缘子的自爆缺陷故障,基于图像识别技术,设计并实现了一套无人机输电线路绝缘子故障检测方法。该方法依次进行图像色彩转换、图像载入和预处理、OTSU或最大熵值分割法分割以及绝缘子轮廓检测工作,实现了对绝缘子间无明显重叠和有明显重叠图像的前景提取与识别功能;采用基于空间序列关系建立的特征检测算法,实现对图像中部无明显重叠绝缘子的自爆缺陷故障检测和定位工作。经测试,自爆缺陷故障检测和定位准确率较高,速度较快,具有一定的应用价值,并能为类似绝缘子故障的检测研究提供参考。
Aiming at the fault caused by spontaneous explosion defect of the insulator,an insulator fault detection method for transmission line of unmanned aerial vehicle(UVA)was designed and implemented based on the image recognition technology.The operations of image color conversion,image loading and pretreatment,OTSU or segmentation with maximum entropy segmentation method,and insulator contour detection are performed in the method successively to realize the foreground extraction and recognition functions of the images with unobvious overlap and obvious overlap in the intervals of the insulators.The feature detection algorithm established on the basis of the spatial series relation is used to realize the spontaneous explosion defect′s fault detection and location for the insulators without obvious overlap in the image.The test results show that the method has high accuracy and fast speed of the fault detection and location for the spontaneous explosion defect,which has a certain application value,and can provide a reference for the detection and research of the similar insulator faults.
出处
《现代电子技术》
北大核心
2017年第22期179-181,186,共4页
Modern Electronics Technique
关键词
图像识别
无人机
输电线路
绝缘子故障检测
image recognition
unmanned aerial vehicle
transmission line
insulator fault detection
