面向高压输电线路的锈蚀缺陷检测
首发时间:2017-11-20
摘要: 随着经济的快速发展,高压输电线路越建越多,且输电线路距离长,可靠性要求高。输电线路由架空导地线、绝缘子、金具、杆塔、基础和接地装置等部件组成,长期暴露在野外,受到各种恶劣环境的侵蚀,使得输电线路金具等部件在腐蚀环境下受到严重的腐蚀破坏,存在巨大的安全隐患。因此,高压输电线路的锈蚀缺陷检测至关重要。本文应用课题实验组提供的无人机航拍图像,对于输电线路不同背景下锈蚀缺陷,分析锈蚀缺陷特点及图像背景,提出了一种改进的半交互式分割算法,对一组相似场景的图像进行了快速准确的前景提取,并在分割后的图像上根据锈蚀特征对彩色图像进行锈蚀检测。实验结果表明,所提出的锈蚀检测算法能够很好地识别输电线路上的锈蚀区域,提高了维护的工作效率。
关键词: 高压输电线路 锈蚀缺陷检测 相似场景 半交互式分割
For information in English, please click here
Detection of Corrosion Defects for High Voltage Transmission Lines
Abstract:With the rapid development of economy, more and more high voltage transmission lines, with long transmission distance, have been built, which requires high reliability. Transmission lines, composed of overhead lines, electrical insulators, metal fittings, tower, foundation and the grounding devices, are exposed for a long time in the wild and eroded by all kinds of severe environments, which has made the transmission lines and component parts suffering serious corrosion. So, there is a huge potential risk left behind. Therefore, the detection of corrosion defects of the high voltage transmission line is of vital importance. In this paper, the author applies the UAV aerial imaDetection of Corrosion Defects for High Voltage Transmission Linesges provided by the project group to observe corrosion defects of the transmission lines under different backgrounds and analyze the features and image backgrounds of the corrosion defects. So, the author puts forward an improved semi-interactive segmentation algorithm, which relates to a quick and precise foreground extraction method applied to a group of images from similar scenario, for detecting the corrosion defects shown on the images according to the characteristics of the corrosion after the segmentation of the images. The experimental results show that the algorithm of corrosion detection proposed by the author can effectively identify the corrosion area on the transmission lines, which has improved the efficiency of maintenance.
Keywords: High voltage transmission line Corrosion defect detection similar scenario semi-interactive segmentation?????
基金:
引用
No.****
同行评议
共计0人参与
勘误表
面向高压输电线路的锈蚀缺陷检测
评论
全部评论