矿坝输送带实时图像探伤方法  

Mine Conveyor Belt Inspection Method of Real-time Image

作　　者：刘凯[1] 牛昱光[1] 

机构地区：[1]太原理工大学信息工程学院,山西太原030024

出　　处：《电视技术》2014年第7期37-39,共3页Video Engineering

基　　金：山西省科技攻关项目(20110321036)

摘　　要：长期工作在艰苦的环境下,钢丝绳芯输送带易发生断裂故障,对运输生产造成影响。提出一种基于模糊聚类算法的图像识别方法对输送带的损伤与接头进行检测,据背景差分法与阈值分割,分离出输送带前景、背景视频图像得到目标。利用Sobel算子检测得到损伤与接头处边缘关系,消除冗余信息,最后用模糊聚类算法对图像分类,从而对输送带是否有损伤作出判断。实验结果用以验证算法的有效性。The wire rope of steel cord conveyor belt is prone to be fractured, due to the long-term work in harsh conditions, affecting transport safety. In this paper,bases on fuzzy clustering algorithm with template matching method to detect damage to the conveyor belt. In order to get the moving target seg- mentation, the conveyor belt prospects are isolated from background video image based on difference method with threshold. Sobel operator edge detection breaks edge relationship, remove redundant information with fuzzy clustering algorithm for pixel classification. Finally, the use of template matching to de- termine the conveyor belt fracture failure. Propose algorithm based on the OpenCV library functions, and the experimental results verify the effectiveness of the proposed algorithm.

关 键 词：SOBEL边缘检测 输送带损伤检测 模糊聚类 模板匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]