A three-dimensional positioning method for surface targets of trucks in warehouse areas of steel mills

Abstract

The invention discloses a three-dimensional positioning method for a surface target of a truck in a warehouse area of ​​a steel factory, which belongs to the field of mechanical automation. The specific steps are: obtaining point clouds of irregular targets and regular targets; obtaining the main direction vector and center coordinates of each irregular target; Get the center coordinates of the standardized irregular targets; get the center coordinates of the sorted irregular targets; get the position coordinates of the irregular targets; get the center coordinates of the regular target point cloud; get the target position coordinates in the ground coordinate system. The invention is applied to loading and unloading trucks in the iron and steel storage area, and can improve the segmentation and positioning accuracy of irregular targets and regular targets on the truck. Use PointCNN segmentation network to identify and segment the target point cloud blocks on the surface of the truck, and finally calculate the positions of irregular targets and regular targets by a specific positioning algorithm; the invention solves the segmentation and positioning of irregular targets in the existing positioning technology Problems, improve the applicability and recognition efficiency of the positioning system.

Description

technical field [0001] The invention belongs to the field of mechanical automation, and relates to a three-dimensional positioning method for a truck surface target in a warehouse area of ​​a steel plant; in particular, it relates to a positioning method for an unmanned driving system of a steel plant based on a deep learning algorithm. Background technique [0002] With the development of automation technology, fully automated loading and unloading in steel plant storage areas has become an important trend. In order to realize the automation of loading and unloading, the core task is to be able to accurately locate the position of the materials and stacks on the truck. [0003] The traditional automatic positioning method based on 3D laser is the current research hotspot of loading and unloading positioning. However, this method can only identify regular steel coils and stacks, or can only locate truck compartments of specific shapes and specifications, and does not have th...

AI Technical Summary

Problems solved by technology

Taking the common irregular wooden stacks in steel mills as an example, due to long-term use, the wooden stacks are often severely worn, and there is no regular geometric model corresponding to them, and it is difficult for conventional feature recognition algorithms to accurately segment the wooden stacks

Images