煤矿井下掘锚装备智能化是改善行业采掘失衡问题的关键，而掘锚装备的精确定位是实现其智能化的前提。与其他传统定位方法相比，基于视觉的位姿测量方法以其无接触、无累计误差的优势在煤矿井下得到了初步的应用。针对目前煤矿井下掘进工作面掘锚装备视觉定位方法存在的合作标靶结构复杂、标定繁琐的问题，结合掘进工作面原有激光指向仪特征，提出一种基于单激光束信息的掘锚装备视觉定位方法。该方法通过分析激光指向仪光斑及光束图像特征，提出了一种基于二维反正切函数拟合的激光光斑中心提取方法和基于Hough直线检测的激光束中心线提取方法，构建了基于点线特征的双目视觉位姿解算模型，得出了掘锚装备在巷道中的实时位姿。最后，为了验证提出的特征提取方法和视觉定位方法的可行性和准确性，在实验室模拟掘进工作面工况环境搭建平台进行了试验。结果表明：基于矿用激光指向仪信息的掘锚装备视觉定位方法具有较高的位姿测量精度。在50 m的测试范围内，机身位置在巷道坐标系下沿X轴、Y轴和Z轴的平均测量误差分别为25.44、58.64、31.08 mm，其最大误差分别为55.16、127.39、63.57 mm；机身姿态在巷道坐标系下的俯仰角、偏航角和横滚角的平均测量误差分别为0.22°、0.22°、0.41°，其最大误差分别为0.29°、0.37°、0.58°。满足煤矿井下巷道施工的定位精度要求。

Intelligent digging and anchoring equipment in underground coal mines is the key to improve the mining imbalance problem in the industry, and the precise positioning of digging and anchoring equipment is the prerequisite to realize its intelligence. Compared with other traditional positioning methods, the vision-based pose measurement method has been initially applied in underground coal mines for its advantages of no contact and no cumulative error. Aiming at the problems of complex structure of cooperative target and cumbersome calibration of the current visual positioning method of the digging anchor equipment in the face of the underground coal mine, combining with the characteristics of the original laser pointers in the face of the digging, a visual positioning method of the digging and anchoring equipment based on the information of a single laser beam is proposed. By analyzing the laser pointer spot and beam image features, the method proposes a laser spot center extraction method based on two-dimensional inverse tangent function fitting and a laser beam centerline extraction method based on Hough straight line detection, and constructs a binocular visual position solving model based on the point and line features, which results in the real-time position of the anchor digging equipment in the roadway. Finally, in order to verify the feasibility and accuracy of the proposed feature extraction method and visual positioning method, experiments were conducted in the laboratory by building a platform to simulate the working condition environment of the digging face. The results show that the visual localization method of digging and anchoring equipment based on the information of mining laser pointers has high accuracy of position measurement. Within the test range of 50 m, the average measurement errors of the body position along the X-axis, Y-axis and Z-axis under the roadway coordinate system are 25.44, 58.64 and 31.08 mm, respectively, and the maximum errors are 55.16, 127.39 and 63.57 mm, respectively; and the average measurement errors of the pitch angle, yaw angle and roll angle of the body attitude under the roadway coordinate system are 0.22°, 0.22°, 0.41°, and their maximum errors are 0.29°, 0.37°, 0.58°, respectively. The maximum errors are 0.29°, 0.37° and 0.58°, respectively. It meets the requirement of positioning accuracy for the construction of underground roadway in coal mine.