改进Canny算子在列车车轮踏面损伤检测中的应用
Improve the application of the Canny algorithm in the detection of wheel tread damage

高速列车车轮踏面剥离、擦伤等损伤的检测主要以效率低下的人工巡检为主，为了提高检测效率设计一种基于机器视觉的高速列车车轮踏面损伤的动态检测系统，提出使用改进Canny算子对车轮踏面损伤进行边缘检测。改进的Canny算子在平滑图像时采用自适应加权中值滤波算法来代替高斯滤波，采用添加45°和135°方向梯度模板的Sobel算子来计算梯度幅值，以大津法(Otsu法)来确定最佳高低阈值。仿真实验结果表明：基于自适应加权中值滤波和大津法的改进Canny算子可以有效地检测车轮踏面损伤的边缘，同时也实现了自动检测。
The detection of damage such as scratch and stripping of the wheel tread of high-speed train is mainly based on inefficient artificial inspection. In order to improve detection efficiency, a dynamic detection system based on machine vision high-speed train wheel tread damage was designed. This paper put forward the edge detection of wheel tread damage by using improved Canny algorithm. The improved Canny algorithm uses an adaptive weighted median filter algorithm to replace the Gaussian filter in smoothing the image. This method added 45° and 135° gradient templates on the basis of the existing Sobel algorithm when calculating the gradient amplitude, and uses the Otsu method to determine optimal high and low thresholds. The experimental results show that the improved Canny algorithm based on adaptive weighted median filter and Otsu method can effectively detect the edge of wheel tread damage and also achieve automatic detection