3D position estimation of drone and object based on QR code segmentation model for inventory management automation

Abstract

Recently, drones have been used more in various fields such as safety, security, and rescue. Drones have the advantage of being able to explore in a wide range through the camera mounted on the drone. In the field of inventory management automation, research was conducted to utilize it. For inventory management automation in a large warehouse, a camera mounted on the drone scan pre-displayed ground QR (Quick Response) code to explore the path. The drone runs along the navigated path and manages the inventory of the warehouse by scanning the barcode or QR code attached to the product. However, unlike warehouses, which have well-defined grids or shelves, the location where products are stored in a yard is not fixed but flexible. Thus, for efficient inventory management in the storage yard, it is also necessary to estimate the position of the QR codes attached to the product. Therefore, in this paper, we propose a position estimation method for drones and products based on the QR code segmentation model. The segmentation model is used to detect the region of perspective distortion QR code caused by the angle difference between the camera and the QR code. Subsequently, shape correction and decoding of the detected QR code region are performed to determine whether it is a ground QR code or not, and the position of the drone is estimated. Finally, the 3D coordinates of the QR code attached to the product, not the ground QR code, are calculated from images taken by drones from two different viewpoints. Consequently, the 3D position coordinates of the drones and QR codes attached to the products will be estimated using the ground QR codes, and efficient inventory management in the storage yard will be achieved in this way.