摘要
传统的缺陷图像识别方法易受到环境噪声的影响,难以实现精准识别。为了高效识别均压环缺陷,设计了一种架空输电线路均压环缺陷图像的智能识别方法。分析均压环断裂原因,依据图像智能识别原理构建输电巡检影像样本标准库,在标注与转换数据后,对图像实施预处理与特征提取,获取图像不变矩特征矢量,从而避免环境噪声的影响。基于此,识别与分析均压环缺陷图像断裂程度。由实验结果可知,该方法的识别结果与实际均压环缺陷线路一致,证明了该方法具有较高的可行性。
Traditional defect image recognition methods are susceptible to environmental noise and difficult to realize accurate recognition. In order to identify the defects of the equalizing ring efficiently,an intelligent identification method for the defects of the equalizing ring on overhead transmission lines is designed. The reasons for the fracture of the equalizing ring were analyzed,and the standard library of transmission inspection image samples was built according to the principle of intelligent image recognition.After marking and converting the data,image preprocessing and feature extraction were carried out to obtain the image moment-invariant feature vector,so as to avoid the influence of environmental noise.Based on this,the fracture degree of the defect image of the equalizing ring is identified and analyzed.The experimental results show that the identification results of this method are consistent with the actual equal-pressure ring defect circuit,which proves that this method is highly feasible.
作者
刘琦
翟瑞聪
曾群生
王鹏凯
LIU Qi;ZHAI Ruicong;ZENG Qunsheng;WANG Pengkai(Guangdong Power Grid Co.,Ltd.,Guangzhou 510000,China;Machine Patrol Management Center of Guangdong Power Grid Co.,Ltd.,Guangzhou 510000,China;Digital Grid Research Institute Co.,Ltd.,China Southern Power Grid,Guangzhou 510000,China)
出处
《电子设计工程》
2022年第6期170-173,178,共5页
Electronic Design Engineering
关键词
架空输电线路
均压环裂缝
图像识别
样本标准库
不变矩
overhead transmission lines
fracture of equalizing ring
image recognition
sample standard library
invariant moment
