论文部分内容阅读
为了提升岩体结构面参数提取的自动化程度以及准确性,结合钻孔图像中岩体结构面的特性,开展了适用于结构面图像预处理和结构面参数提取的方法研究。首先,采用自适应中值滤波法对钻孔图像进行去噪处理,通过对梯度算子法和最大类间方差法的图像分割进行比较,提出了更适用于实际钻孔图像分割的改进方差法,即结合梯度算子与最大类间方差法;然后对分割后的图像进行Canny算子边缘检测;最后,通过多项式曲线拟合获得结构面的正弦曲线,从而计算出岩体结构面的参数——倾向、倾角和隙宽。通过将提取方法与传统的手动识别结果进行对比,其结果表明:提取方法获取的参数较为精确。从而证明了该结构面参数提取方法具有可行性和准确性,且提取效率高于传统的手动识别。
In order to improve the degree of automation and accuracy of parameter extraction of rock mass structural plane, combining with the characteristics of rock mass structural plane in borehole images, the methods suitable for pretreatment of structural plane image and extraction of structural plane parameters are studied. Firstly, the adaptive median filter method is used to denoise the borehole image. By comparing the gradient operator method with the image classification method of maximum variance method, an improved variance method is proposed which is more suitable for the actual borehole image segmentation , Which combines the gradient operator with the maximum between-class variance method. Then the edge of the image is detected by Canny operator. Finally, the sinusoid of the structural plane is obtained by polynomial curve fitting, - Propensity, dip and gap width. By comparing the extraction method with the traditional manual recognition results, the results show that the parameters obtained by the extraction method are more accurate. It proves that the extraction method of structural plane parameters is feasible and accurate, and the extraction efficiency is higher than the traditional manual identification.