Box body sorting method and system based on RGB-D camera

Abstract

The invention provides a box body sorting system based on an RGB-D camera, which comprises a conveyor belt for conveying the box bodies, a RGB-D camera, a mechanical arm, a photoelectric sensor for detecting whether an object is in place, and an industrial personal computer; the industrial personal computer is in signal connection with a control cabinet of the mechanical arm and the RGB-D camera,and the control cabinet of the mechanical arm is in signal connection with the photoelectric sensor; the industrial personal computer comprises the following modules: a two-camera conversion relationacquisition module, a hand-eye calibration module, an image acquisition module, a target object pose estimation module, a mechanical arm grabbing pose module and a position visual servo module. According to the method, the RGB-D camera is used for collecting the color image and the depth image of the target box body on the conveying belt, the target three-dimensional point cloud is obtained, and the advantages of the color image and the three-dimensional point cloud image can be integrated in combination with target box body pose estimation of the color image and the three-dimensional point cloud image. And finally, based on the position visual servo principle, the overall precision of the system is improved, and interference of some common external factors is eliminated.

Description

technical field [0001] The invention belongs to the field of three-dimensional visual perception of robots, and in particular relates to a box sorting method and system based on an RGB-D camera. Background technique [0002] In the era of Industry 4.0 and the era of the Internet, the logistics industry has developed rapidly in recent years, and the output and labor costs have continued to increase. For example, the express delivery industry has also undergone transformation and upgrading, and gradually began to build unmanned warehouses. Through the combination of artificial intelligence and vision, even if there are no workers in the warehouse, the rapid sorting and shipment of the warehouse can be realized. [0003] For objects in the shape of boxes, the original manual sorting method is gradually transformed into automatic sorting. Automatic sorting adopts a vision-based robot grasping solution. A typical scenario is to sort objects on a conveyor belt to a designated are...

AI Technical Summary

Problems solved by technology

[0007] At present, the results obtained by some methods based on RGB-D cameras do not take into account the interference caused by various external factors, such as the inaccurate calibration results above, the execution deviation of the actuator (gripper), etc., resulting in the final pose estimation accuracy poor

Images