Method and device for acquiring three-dimensional coordinates of ore based on mining process

An apparatus for acquiring three-dimensional coordinates of ore based on mining process, comprising:

• at least one control processor and a memory for communicating with the at least one control processor, wherein the memory stores instructions executable by the at least one control processor, and the instructions, when executed by the at least one control processor, cause the at least one control processor to perform steps of:
• acquiring an ore image;
• processing the ore image by using a YOLACT algorithm and a NMS algorithm to obtain a prediction mask map;
• drawing a rectangular box according to the prediction mask map and obtaining a two-dimensional coordinate of ore through a center point of the rectangular box;
• acquiring a color map and an infrared depth map;
• transmitting the color map into a pre-training model for recognition to obtain object contours;
• selecting a contour of a target object, calculating the sum of coordinates of X axis and Y axis of all points on the contour, and then dividing the sum of the coordinates by the number of the points on the contour to obtain a gravity center of the target object;
• calculating a distance between the gravity center of the target object and an origin to obtain a polar coordinate of the target object, and aligning a center point of the color map and a center point of the infrared depth map through affine transformation to obtain a scale of the color map in the infrared depth map;
• multiplying a length of the polar coordinate by the scale to obtain a point in the infrared depth map corresponding to a point in the color map, thereby obtaining depth information of the point in the infrared depth map;
• and
• combining the two-dimensional coordinate with the depth information to obtain a three-dimensional coordinate of the ore.

A computer readable storage medium having computer executable instructions stored thereon which, when executed by a computer, cause the computer to perform steps of:

• acquiring an ore image;
• processing the ore image by using a YOLACT algorithm and a NMS algorithm to obtain a prediction mask map;
• drawing a rectangular box according to the prediction mask map and obtaining a two-dimensional coordinate of ore through a center point of the rectangular box;
• acquiring a color map and an infrared depth map;
• transmitting the color map into a pre-training model for recognition to obtain object contours;
• selecting a contour of a target object, calculating the sum of coordinates of X axis and Y axis of all points on the contour, and then dividing the sum of the coordinates by the number of the points on the contour to obtain a gravity center of the target object;
• calculating a distance between the gravity center of the target object and an origin to obtain a polar coordinate of the target object, and aligning a center point of the color map and a center point of the infrared depth map through affine transformation to obtain a scale of the color map in the infrared depth map;
• multiplying a length of the polar coordinate by the scale to obtain a point in the infrared depth map corresponding to a point in the color map, thereby obtaining depth information of the point in the infrared depth map;
• and
• combining the two-dimensional coordinate with the depth information to obtain a three-dimensional coordinate of the ore.