基于Otsu分割与边缘检测的钢丝绳缺陷检测方法研究  

Wire Rope Defect-Detection Method Based on Otsu Segmentation and Edge Detection

作　　者：戴若辰 赵明富[1] 汤斌[1] 代理勇 巫涛江 蒋上海 Dai Ruochen;Zhao Mingfu;Tang Bin;Dai Liyong;Wu Taojiang;Jiang Shanghai(Intelligent Fiber Sensing Technology of Chongqing Municipal Engineering Research Center of Institution of Higher Education,Chongqing Key Laboratory of Fiber Optic Sensor and Photodetector,Chongqing University of Technology,Chongqing 400054,China;Tielian Operation and Maintenance of Chongqing Municipal Engineering Research Center of Institution of Higher Education,Chongqing 402260,China)

机构地区：[1]重庆理工大学智能光纤感知技术重庆市高校工程研究中心,重庆市光纤传感与光电检测重点实验室,重庆400054 [2]电梯智能运维重庆市高校工程中心,重庆402260

出　　处：《激光与光电子学进展》2021年第16期558-565,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金青年基金项目(61805029);重庆市教委科研基金项目(KJQN201905605)。

摘　　要：电梯钢丝绳是承载轿厢重量的关键部件,针对钢丝绳断丝无法在线检测的问题,提出一种采用高光谱图像处理识别断丝的方法。选取样本与背景图像差异较大的特殊波段图像,将Otsu自适应阈值分割与Hough变换相结合,根据钢丝绳图像中直径所包含的像素数判断钢丝绳断丝程度是否达到报废要求。实验表明,此方法的均方误差、峰值信噪比和结构相似度分别达到650.9、19.9957和0.9404,Otsu阈值分割与Hough变换结合对于电梯钢丝绳图像处理是有效的,可以实现对电梯钢丝绳断丝的检测,为钢丝绳快速缺陷检测提供了新的解决方法。An elevator wire rope is a key component for carrying the weight of carriages.To address the problem that wire rope defects cannot be detected online,a method to identify broken wires using hyperspectral image processing is proposed.First,the spectral band image with the greatest difference between the sample and background was selected.Then,Otsu adaptive threshold segmentation combined with the Hough transform was used.The number of pixels in the diameter of the wire rope in the image was used to determine whether the extent of breakage meets the scrapping requirement.The mean square error,peak signal-to-noise ratio,and structural similarity values experimentally obtained using this method were 650.9,19.9957,and 0.9404,respectively.Results indicate that combining Otsu threshold segmentation and the Hough transform to process images of elevator wire ropes is effective,providing a new method for the rapid detection of wire rope defects.

关 键 词：光谱学 钢丝绳 高光谱图像 Otsu阈值分割 边缘检测 

分 类 号：O436[机械工程—光学工程]