Steel mill reservoir area truck surface target three-dimensional positioning method

Abstract

The invention discloses a steel mill reservoir area truck surface target three-dimensional positioning method, which belongs to the field of mechanical automation, and comprises the following specificsteps: obtaining point clouds of an irregular target and a regular target; obtaining a main direction vector and a central coordinate of each irregular target; obtaining center coordinates of a standard irregular target; obtaining center coordinates of the sorted irregular targets; obtaining position coordinates of the irregular target; obtaining a central coordinate of the regular target point cloud; and obtaining a target position coordinate under a ground coordinate system. The invention is applied to the loading and unloading operation in the iron and steel reservoir area, and the segmentation and positioning accuracy of irregular targets and regular targets on trucks can be improved. A PointCNN segmentation network is adopted to identify and segment a target point cloud block on thesurface of the truck, and finally the positions of an irregular target and a regular target are calculated through a specific positioning algorithm; according to the invention, the problems of irregular target segmentation and positioning in the existing positioning technology are solved, and the applicability and identification efficiency of the positioning system are improved.

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