Drone-Assisted QR Code Recognition Method for Warehouse Management

In response to the increasing complexity of inventory management in large-scale warehouses, we present a drone-assisted quick response (QR) code recognition technology for warehouse management. It combines panoramic stitching and image preprocessing for QR code recognition. The experiments are conducted and performed in two phases. First, we compare three basic QR code recognition methods based on Pyzbar, OpenCV, and dynamsoft barcode reader (DBR), with experimental results indicating that DBR performs the best. Second, building on the DBR method, we compare the recognition effects of different image preprocessing techniques, namely the method proposed in this paper, geometric correction, sharpening (SH) and adaptive histogram equalization (AHE), and the median filter algorithm. The results show that the proposed method excels in average processing time per batch (τ), stitching success rate (ŋ), and the number of recognized QR codes (ξ). The average processing time per batch is 3.13 seconds, the stitching success rate (ŋ) is 63.43%, and totally 746 QR codes are recognized. It approaches the performance of geometric correction methods with its advantage in processing speed. It provides significant practical value and innovative solutions for enhancing efficiency in modern warehouse management.