A Study on Airport Runway Detection Based on an Improved YOLOv11 Algorithm

With the development of remote sensing technology and artificial intelligence, automatic detection of airport runways has important application value in aviation safety, drone navigation, and other fields. Addressing the issues of low detection accuracy and insufficient feature extraction in traditional target detection algorithms for single-class small target detection, this paper proposes two improvements based on the YOLO v11 model: first, the introduction of the EMA (Efficient Multi-scale Attention) attention mechanism to enhance the feature expression capability of key areas; secondly, the ASFF (Adaptively Spatial Feature Fusion) module is introduced to achieve adaptive fusion of multi-scale feature maps, thereby improving the accuracy and robustness of object detection. This paper uses self-collected airport runway images to construct a dataset, conducts experiments on this dataset, and compares the results with the original YOLO v11 and mainstream detection models. The experimental results show that the proposed improved model outperforms the comparison methods in terms of accuracy (mAP), recall rate, and detection speed, validating its effectiveness and practical value in airport runway detection tasks.