An improved arrow target detection method for airport navigation based on YOLOv11

With the development of air transportation industry, the intelligent recognition of airport navigation signs is of great significance to improve the efficiency of airport operation and ensure flight safety. Aiming at the problems of low recognition accuracy and poor real-time performance of traditional target detection algorithms for navigation arrows (up, down, left, right) in complex airport environments, this paper proposes an improved target detection method for airport navigation arrows based on YOLOv11. Based on the original structure of YOLOv11, the method adopts the lightweight MobileNetV3 network to replace the original Backbone, in order to reduce the number of model parameters and improve the computational speed; at the same time, it introduces the ECA (Efficient Channel Attention) channel attention mechanism, which effectively strengthens the dependency relationship between the feature channels, and thus improves the model's perception of the arrowhead target. The model's ability to perceive the arrowhead target is improved. The experiments are carried out on the self-constructed airport arrowhead dataset, and the results show that the improved model proposed in this paper significantly improves the inference speed and generalization performance of the model while maintaining high detection accuracy, which verifies the effectiveness and practicality of the proposed method.