基于改进Canny算法的列车车轮踏面损伤边缘提取

针对高速列车车轮踏面擦伤、剥离的人工巡检方法效率较低且容易出现漏检等问题,设计一种高速列车车轮踏面损伤的动态检测系统,提出一种擦伤、剥离的特征提取方法。该方法在现有Canny算法的基础上加入45°方向和135°方向梯度模板来计算梯度幅值,用线性插值法对梯度幅值进行非极大值抑制,再使用优化后的迭代阈值算法求得高阈值和低阈值。试验结果表明,该算法可以有效地抑制噪声和干扰,最大限度地保留高速列车车轮踏面的真实边缘,为列车车轮踏面损伤自动巡检提供技术支持。

Edge Extraction of Train Wheel Tread Damage Based on Improved Canny Algorithm

In view of the high-speed train wheel tread scratch,the stripping of artificial inspection method is less efficient and prone to miss inspection. This paper designs a dynamic detection system for wheel tread damage and a feature extraction method for scratch and peeling is proposed. This method adds45° and 135° gradient templates on the basis of the existing Canny algorithm when calculating the gradient amplitude. Linear interpolation method is used to suppress the non-maximum value of the gradient amplitude,and uses the optimized iterative algorithm to find the high and low thresholds. The experimental results show that the algorithm can effectively suppress the noise and interference,and maximize the real edge of the high-speed train wheel tread, which provides technical support for automatic inspection of train tread damage.