基于ASIFT算法的绝缘子视频图像的识别与定位  

Identification and location of insulator video images based on ASIFT algorithm

作　　者：苑津莎[1] 崔克彬[2] 李宝树[3] 

机构地区：[1]华北电力大学电子与通信工程系,河北保定071003 [2]华北电力大学计算机系,河北保定071003 [3]华北电力大学电力工程系,河北保定071003

出　　处：《电测与仪表》2015年第7期106-112,共7页Electrical Measurement & Instrumentation

基　　金：中央高校基本科研业务费专项资金项目(2014MS134)

摘　　要：为了实现智能提取直升机巡检视频中的绝缘子图像,基于ASIFT原理的图像处理技术和数据库技术,提出了一种新的绝缘子图像识别与定位方法。该方法首先建立标准的绝缘子图库,通过改进UL-PCNN红外图像分割算法提取绝缘子特征值,然后将输电线路视频与标准图库中的绝缘子图片利用ASIFT算法进行匹配,进而识别和定位视频中的绝缘子。实验结果表明,ASIFT方法具备良好的抗绝缘子图像仿射变形性能,可以在少量人工辅助的条件下对图像进行处理,提高了架空输电线路绝缘子故障检测的自动化处理程度。A new insulator image identification and location method based on the principle of ASIFT was proposed in this paper to achieve intelligent extraction of insulator images from helicopter patrol videos. Firstly, astandard insula- tor gallery is established and the characteristics values are extracted by improved UL-PCNN infrared image segmenta- tion algorithm, then the transmission line video and the images in the established gallery are matched by ASIFT, final- ly, identification and location of insulators can be done. Experimental results show that ASIFT method has good anti - affine deformation properties, it can process the images with less human involvement and improve the automation of fault detection of the insulators on overhead transmission line.

关 键 词：绝缘子 航拍视频图像 ASIFT算法 识别与定位 

分 类 号：TM93[电气工程—电力电子与电力传动]