基于遗传算法的OTSU煤矿井筒裂缝快速识别方法  

A method of mine shaft crack recognition based on genetic algorithm and OTSU

作　　者：岳国伟[1] 卢秀山[1] 贾红果[1] 刘如飞[1] 

机构地区：[1]山东科技大学,山东省青岛市266590

出　　处：《中国煤炭》2016年第4期71-75,85,共6页China Coal

摘　　要：井筒巡检仪采集的井筒序列影像,占用存储空间达90G以上,数据量大,分析处理费时费力。最大类间方差法作为一种典型的图像自适应阈值分割方法,在进行图像分割时,存在计算复杂度高、时间消耗多、分割精度低等问题。为提高裂缝识别效率,提出了一种基于遗传算法的OTSU煤矿井筒裂缝快速识别方法,遗传算法用来提高迭代求解速度和计算效率。实验结果表明,本文方法不仅能缩短运算时间30%以上,而且能够快速准确识别井筒裂缝病害,提高井筒巡检的自动化程度。The sequence images collected by the mine shaft inspection instrument take up more than 90 G of storage space.The data is very large and the analysis is time-consuming and laborious.OTSU is a typical image adaptive threshold segmentation method.There are many problems such as high computational complexity,high time consumption and low accuracy of segmentation when it is carrying on the image segmentation,in order to improve the efficiency of crack recognition,a new method of mine shaft crack recognition based on genetic algorithm is proposed.Genetic algorithm is used to improve the speed and efficiency.The experimental results show that this method can not only shorten the operation time of 30%,but also can quickly and accurately recognize the crack disease,which will improve the degree of automation of mine shaft inspection.

关 键 词：遗传算法 最大类间方差法 井筒巡检 裂缝识别 

分 类 号：TD535[矿业工程—矿山机电]