用视频自动提取飞机4D轨迹，替代缺失的飞行数据记录器信息
Automated extraction of 4D aircraft trajectories from video recordings
- 基于摄影测量法，利用MicMac软件自动化处理航拍或地面视频
- 可恢复三维位置、姿态角和平均速度等4维轨迹数据
- 适用于事故调查中无飞行数据记录器的情况，节省人工分析时间
法国民用航空安全调查局（BEA）需分析涉及各类飞机的机上或地面摄像头事故视频，此前均依赖人工且耗时。本研究旨在探索摄影测量技术的应用，实现从视频中自动化提取4D轨迹。基于法国国家地理院（IGN）的MicMac软件，开发了适用于各种飞行构型的算法，并在实际场景中测试。自动化结果旨在替代有时缺失的飞行数据记录器（如FDR或CVR）信息。BEA关注的关键数据包括：带时间戳的三维位置、飞机三轴姿态角（俯仰、滚转、偏航）及平均速度（含爬升率）。
原文摘要 · Abstract (English)
The Bureau d'Enqu{ê}tes et d'Analyses pour la S{é}curit{é} de l'Aviation Civile (BEA) has to analyze accident videos from on-board or ground cameras involving all types of aircraft. Until now, this analysis has been manual and time-consuming. The aim of this study is to identify the applications of photogrammetry and to automate the extraction of 4D trajectories from these videos. Taking into account all potential flight configurations, photogrammetric algorithms are being developed on the basis of IGN's MicMac software and tested in the field. The results of these automated processes are intended to replace flight data from recorders such as FDRs or CVRs, which are sometimes missing. The information of interest to the BEA includes: three-dimensional position with the associated time component, the orientations of the aircraft's three axes (pitch, roll and yaw navigation angles) and average speeds (including rate of climb).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。