Research on conflict detection model for taxi‐in process on the apron based on aircraft wingtip keypoint detection

Apron safety is critical to aviation operations and aprons are prone wingtip scraping accidents. However, few studies have been conducted on conflicts. In this paper, a class of aircraft conflict detection models based keypoint devised solve the problem that may occur during taxi-in process apron. Firstly, concise camera calibration technique designed for conversion between pixel coordinate airport actual coordinate, which allows acquisition high accuracy activity posture within Secondly, static dynamic protection zone delineation methods given, taking apron standard operating procedures kinematic model into consideration. Then, corresponding algorithms possible vehicle wingtips Finally, HRNet selected detect by comparison, algorithm validation carried out physical sandbox. The verification results indicate strong real-time performance.