基于智能图像处理的线路覆冰厚度检测技术研究

Research on Line Icing Thickness Detection Technology Based on Intelligent Image Processing

摘要:

针对雨雪天气严重影响线路覆冰图像质量与标准覆冰厚度计算的问题，提出一种基于智能图像处理的线路覆冰厚度检测方法，并在实验室对导线进行人工覆冰并模拟人工冷雾，采集有雾和无雾条件下的覆冰图像，用所提方法检测导线覆冰厚度。对采集的图像通过去雾、灰度化、直方图均衡化和空间滤波进行预处理，采用多种算子对处理后的图像进行边缘检测，计算出覆冰厚度。结果表明，覆冰图像去雾处理后采用直方图均衡化和空间滤波可较好地改善图像质量，配合使用Canny算法进行导线覆冰图像边缘检测时更具优势，即使在有雾的情况下，也可以得到较为准确的覆冰厚度检测结果。

Abstract:

In order to solve the problem that rain and snow weather seriously affect the quality of line icing image and the calculation of standard icing thickness, a line icing thickness detection method based on intelligent image processing is proposed. The wire is manually iced and simulated in the laboratory, and artificial cold fog is simulated. The icing images under foggy and fog free conditions are collected, and the proposed method is used to detect the wire icing thickness. The pre processing for these collected images is carried out through defogging, grayscale processing, histogram equalization and spatial filtering, and the edge detection of the processed images is also carried out by a variety of operators to calculate the icing thickness. The results show that histogram equalization and spatial filtering can improve the image quality after defogging icing images, and Canny algorithm is proven to have more advatages to detect the edges of icing images, which can obtain more accurate detection results of icing thickness even in foggy conditions.