论文部分内容阅读
数字全景钻孔摄像技术在实际工程上得到了广泛的应用,获得大量的高精度实测钻孔图像。这些钻孔图像准确记录了地质特征信息,特别是结构面的几何形态特征。然而,这些特征信息的获取通常是由人工完成的,工作量大,人为因素较多。针对该问题,提出一种针对全景钻孔图像的结构面全自动识别方法。该方法首先提出用图像灰度梯度合成信号在钻孔深度方向的投影的方法来划分结构面所在区域及其产状范围;然后提出用标准模板正弦函数迭代匹配结构面特征量的方法来搜寻区域内结构面的所有可能正弦曲线,并从中筛选出最优的正弦曲线作为结构面的特征曲线;最后结合区域划分和模板函数匹配的结果,分析特征曲线参数,并进行再匹配和转换,最终得到工程所需的结构面位置、倾向、倾角和隙宽等参数,从而实现钻孔图像结构面的全自动识别。结果表明该方法能够连续快速地全自动识别整个钻孔图像内的结构面,并获得对应的高精度几何参数,算法稳定可靠、结构面识别率高。与传统方法相比,该方法首次实现了整个钻孔图像中结构面的全自动识别与几何参数提取,极大地提高了工作效率,为钻孔图像的后期处理与信息获取提供一种实际可行的有效方法。
Digital panoramic borehole camera technology has been widely used in practical engineering, to obtain a large number of high-precision measured borehole images. These borehole images accurately record the geological features, especially the geometrical features of the structural plane. However, the acquisition of these characteristic information is usually done manually, with heavy workload and more human factors. Aimed at this problem, a method of automatic recognition of the structural plane of panoramic borehole image is proposed. In this method, the method of projecting the signal in the depth direction of the borehole using the gray gradient of the image is first proposed to classify the area where the structure plane is located and the range of its occurrence. Then, a method of searching the area by iteratively matching the features of the structure surface with the sine of the standard template All the possible sinusoids of the inner structure plane, and select the optimal sine curve as the characteristic curve of the structural plane. Finally, according to the result of the region division and template function matching, the characteristic curve parameters are analyzed and remapped and converted finally The structural plane position, inclination, dip angle and gap width required by the project can be used to realize the automatic recognition of the borehole image structure plane. The results show that this method can automatically and quickly recognize the structural plane of the entire borehole image and obtain corresponding high-precision geometrical parameters. The algorithm is stable and reliable, and the recognition rate of structural plane is high. Compared with the traditional method, this method can realize the automatic recognition and geometric parameter extraction of the structural plane in the entire borehole image for the first time, which greatly improves the working efficiency and provides a practical feasible method for the post-processing and information acquisition of the borehole image Useful ways.