Intelligent Mining Road Object Detection Based on Multiscale Feature Fusion in Multi-UAV Networks

In complex mining environments, driverless trucks are required to cooperate with multiple intelligent systems. They must perform obstacle avoidance based on factors such as the site road width, type, vehicle body movement state, and ground concavity-convexity. Targeting open-pit area, this paper proposes an object detection (IMOD) model developed using a 5G-multi-UAV deep learning approach. The IMOD employs data sensors monitor surface in real time within multisystem collaborative 5G network. transmits various systems edge devices time, unmanned card constructs driving area fly. utilizes convolutional neural network identify obstacles front of optimizing control truck scheduling data. Multiple maneuver around obstacles, including avoiding static standing lying dummies, empty oil drums, vehicles; continuously obstacles; dynamic walking people moving vehicles. For study, we independently collected constructed image dataset specific experimental tests analyses reveal that maintains smooth route stable attitude, ensuring safety well personnel equipment area. ablation robustness experiments demonstrate outperforms unmodified YOLOv5 model, average improvement approximately 9.4% across performance measures. Additionally, compared other algorithms, shows significant improvements.