首页> 外国专利> MINING PROCESS-BASED METHOD FOR ACQUIRING THREE-DIMENSIONAL COORDINATES OF ORE AND APPARATUS THEREFOR

MINING PROCESS-BASED METHOD FOR ACQUIRING THREE-DIMENSIONAL COORDINATES OF ORE AND APPARATUS THEREFOR

机译:基于过程的基于过程的基于方法,用于获取矿石和装置的三维坐标

摘要

A mining process-based method for acquiring three-dimensional coordinates of ore and an apparatus therefor, the method comprising: acquiring an ore picture (S1a); using a YOLACT algorithm and an NMS algorithm to process the ore picture to obtain a prediction mask map (S1b); drawing a rectangular frame according to the prediction mask map, and obtaining two-dimensional coordinates of the ore by means of the rectangular frame (S1c); acquiring a color map and an infrared depth map (S2a); transferring the color map into a pre-trained model for identification to obtain the contour of an object (S2b); selecting the contour of a target object, calculating the sum of X-axis and Y-axis coordinates of all points on the contour, and then dividing the sum of the coordinates by the number of points on the contour to obtain the center of gravity of the target object (S2c); calculating the distance between the center of gravity of the target object and the point of origin to obtain polar coordinates of the target object, and aligning same by means of affine transformation to obtain the scaling ratio of the color map in the infrared depth map (S2d); multiplying the length of the polar coordinates by the scaling ratio to obtain a point in the infrared depth map corresponding to a point in the color map, thereby obtaining point depth information in the infrared depth map (S2e); and combining the two-dimensional coordinates and the depth information to obtain three-dimensional coordinates of the ore (S3).
机译:一种基于采矿过程的用于获取矿石和装置的三维坐标的方法,该方法包括:获取矿石图片(S1a);使用Yolact算法和NMS算法来处理矿矿图像以获得预测掩码映射(S1B);根据预测掩模图绘制矩形框架,并通过矩形框架获得矿石的二维坐标(S1C);获取彩色图和红外深度​​图(S2A);将彩色图传输到预先训练的模型中,以获得物体的轮廓(S2B);选择目标对象的轮廓,计算轮廓上所有点的x轴和y轴坐标之和,然后将坐标的数量除以轮廓上的点数,以获得重心目标对象(S2C);计算目标对象的重心与原点之间的距离,以获得目标对象的极性坐标,并通过仿射变换对齐,以获得红外深度图中的颜色图的缩放比率(S2D );将极性坐标的长度乘以缩放比率,以获得对应于颜色图中的点的红外深度图中的点,从而获得红外深度图中的点深度信息(S2E);并组合二维坐标和深度信息以获得矿石的三维坐标(S3)。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号