Abstract
With the rapid development and increasing demands of civil aviation, the accurate detection of key aircraft components and staff on airport aprons is of great significance for ensuring the safety of flights and improving the operational efficiency of airports. However, the existing detection models for airport aprons are relatively scarce, and their accuracy is insufficient. Based on YOLOv5, we propose an improved object detection algorithm, called DT-YOLO, to address these issues. We first built a dataset called AAD-dataset for airport apron scenes by randomly sampling and capturing surveillance videos taken from the real world to support our research. We then introduced a novel module named D-CTR in the backbone, which integrates the global feature extraction capability of Transformers with the limited receptive field of convolutional neural networks (CNNs) to enhance the feature representation ability and overall performance. A dropout layer was introduced to reduce redundant and noisy features, prevent overfitting, and improve the model's generalization ability. In addition, we utilized deformable convolutions in CNNs to extract features from multi-scale and deformed objects, further enhancing the model's adaptability and detection accuracy. In terms of loss function design, we modified GIoULoss to address its discontinuities and instability in certain scenes, which effectively mitigated gradient explosion and improved the stability of the model. Finally, experiments were conducted on the self-built AAD-dataset. The results demonstrated that DT-YOLO significantly improved the mean average precision (mAP). Specifically, the mAP increased by 2.6 on the AAD-dataset; moreover, other metrics also showed a certain degree of improvement, including detection speed, AP50, AP75, and so on, which comprehensively proves that DT-YOLO can be applied for real-time object detection in airport aprons, ensuring the safe operation of aircraft and efficient management of airports.