基于远程监控图像的绝缘子覆冰检测算法

An Image-based Algorithm for Icing Detection of Insulator

提出一种基于远程监控图像的绝缘子覆冰情况检测算法。本文算法充分利用边缘检测方法和其他图像处理方法,对覆冰绝缘子侧面冰棱的边缘情况进行精确的检测。本文算法还引入了摄像头的标定参数,使其能更加准确地估计覆冰绝缘子侧面的冰棱长度。当摄像头因为外力或其他因素而产生角度偏移时,本文算法能及时地对摄像头标定参数做出修正,并利用新的标定参数重新估计绝缘子的覆冰情况。实验结果表明,本文算法对绝缘子侧面冰棱边缘检测效果显著,满足实时监控和预警报警的要求。

In this paper, an algorithm based on edge detection for icing detection of insulator was proposed. It took full advantage of the edge detection algorithm and other image processing method to make more specific and accurate detection of icing insulator. Also, it introduced the camera calibration to estimate the length and thickness of swing ice on the side of insulators. What＇ s more, when the settled angle of camera shifted due to some outside force or other reason, this algorithm was able to revise the camera calibration parameters in time and use them to estimate the length and thickness of ice again. The experimental results show that the detection of icing insulator edge is pretty good and the estimation of the length and thickness of ice is accurate, which definitely meet the requirement of real-time monitoring and early warnings.