Sensor Fusion for Aircraft Detection at Airport Ramps Using Conditional Random Fields

Lee, Soomok; Seo, Seung‐Woo

doi:10.1109/tits.2022.3157809

Cited by 7 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim C. H. et al [ 20 ] designed a semi-automated Unpiloted GSE for bird detection and expulsion at airports, but this system requires manual definition of waypoints for patrolling. Lee S. et al [ 21 ] proposed a sensor fusion-based aircraft detection framework using camera and Lidar sensors; however, this framework only provides object detection results for aircraft.…”

Section: Related Workmentioning

confidence: 99%

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

Zhang,

Zhu

2023

Sensors

View full text Add to dashboard Cite

The rapid advancement in Unpiloted Robotic Vehicle technology has significantly influenced ground support operations at airports, marking a critical shift towards future development. This study presents a novel Unpiloted Ground Support Equipment (GSE) detection and control framework, comprising virtual channel delineation, boundary line detection, object detection, and navigation and docking control, to facilitate automated aircraft docking within the aircraft stand. Firstly, we developed a bespoke virtual channel layout for Unpiloted GSE, aligning with operational regulations and accommodating a wide spectrum of aircraft types. This layout employs turning induction markers to define essential navigation points, thereby streamlining GSE movement. Secondly, we integrated cameras and Lidar sensors to enable rapid and precise pose adjustments during docking. The introduction of a boundary line detection system, along with an optimized, lightweight YOLO algorithm, ensures swift and accurate identification of boundaries, obstacles, and docking sites. Finally, we formulated a unique control algorithm for effective obstacle avoidance and docking in varied apron conditions, guaranteeing meticulous management of vehicle pose and speed. Our experimental findings reveal an 89% detection accuracy for the virtual channel boundary line, a 95% accuracy for guiding markers, and an F1-Score of 0.845 for the YOLO object detection algorithm. The GSE achieved an average docking error of less than 3 cm and an angular deviation under 5 degrees, corroborating the efficacy and advanced nature of our proposed approach in Unpiloted GSE detection and aircraft docking.

show abstract

Section: Related Workmentioning

confidence: 99%