发表机构
Korea Aerospace Research Institute; Korea Aerospace University（韩国航空宇宙研究院; 韩国航空大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究训练视觉Transformer模型，以雷达图像及补充的飞机状态变量为输入，回归空中交通的四个内在复杂度分量，验证了雷达图像可作为深度学习建模空中交通复杂度的可行输入格式。
AI 中文摘要
空中交通管制员通过雷达显示屏感知交通复杂度，这表明基于相同图像运行的计算机视觉模型可能成为建模管制员感知复杂度的自然架构；然而，雷达图像是否是深度学习视觉模型的可行输入格式仍不明确。与自然图像不同，雷达图像极为稀疏且自相似，主要由黑色背景和少量视觉相同的飞机斑点组成，而飞机位置的微小变化会显著改变扇区级复杂度。为测试视觉模型是否能捕捉这些操作上重要的差异，我们将每个交通状况编码为位置图像，并补充五个代表飞机状态变量的通道，包括航向、速度和高度，训练一个视觉Transformer（ViT）来回归从飞机间成对几何关系推导的四个内在复杂度分量。该模型对所有四个分量的决定系数R²均大于0.96，且一项移除一架飞机的扰动研究显示，其响应变化与被移除飞机对扇区复杂度的贡献成比例，而非将每次移除视为等价。这些结果表明，尽管雷达图像具有非典型视觉特征，但它仍是空中交通复杂度建模的可行输入格式。
英文摘要
Air traffic controllers perceive traffic complexity through the radar display, suggesting that a computer vision model operating on the same imagery may provide a natural architecture for modeling controller-perceived complexity; however, whether radar imagery is a viable input format for deep learning vision models remains unclear. Unlike natural images, radar images are extremely sparse and self-similar, consisting primarily of a black background and a few visually identical aircraft blobs, while small changes in aircraft positions can substantially alter sector-level complexity. To test whether a vision model can capture these operationally important differences, we encode each traffic situation as a position image supplemented by five channels representing aircraft state variables, including heading, speed, and altitude, and train a Vision Transformer (ViT) to regress four intrinsic complexity components derived from pairwise geometric relations among aircraft. The model achieves $R^2 > 0.96$ for all four components, and a one-aircraft-removal perturbation study shows that its response changes proportionally to how much the removed aircraft contributed to sector complexity rather than treating every removal as equivalent. These results demonstrate that, despite its atypical visual characteristics, radar imagery is a viable input format for air traffic complexity modeling.
Comments12 pages, 6 figures. Submitted to Elsevier
