What question did this study set out to answer?

This study aims to improve the accuracy of UAV trajectory prediction using advanced technology.

April 20, 2026Open Access

Construction of UAV trajectory prediction model based on 5G communication and image recognition technology

Key Points

This study aims to improve the accuracy of UAV trajectory prediction using advanced technology.
Developed a 'perception-computation-decision' architecture.
Implemented enhanced YOLOv11 for better small-target detection.
Utilized a JPTrack module to reduce identity switches.
Employed an LSTM-Attention model for trajectory prediction.
Conducted tests across 30 km² urban areas.
Achieved 93.5% detection recall and 82.3% MOTA.
Reduced identity switches to fewer than 15 per 10 minutes.
Noted trajectory prediction errors of 0.8 m (1 s) and 5.3 m (10 s).
Showed a 46.7%-56.3% improvement over conventional methods.
Maintained an end-to-end latency under 5 seconds.

Abstract

Accurate drone trajectory prediction is essential for low-altitude safety amid rapid industry growth.Current systems face challenges like poor small-target detection and tracking accuracy.This study presents a complete technical solution featuring a 'perception-computation-decision' architecture, with 25 5G-A ISAC base stations and 46 HD sensors covering 50 km 2 .Algorithm improvements include enhanced YOLOv11 for small targets, a JPTrack module to minimise identity switches, and an LSTM-Attention prediction model.In 30 km 2 urban tests, the system achieved 93.5% detection recall, 82.3% MOTA, and fewer than 15 identity switches per 10 minutes.Trajectory prediction errors were 0.8 m (1 s), 2.1 m (3 s), and 5.3 m (10 s), representing a 46.7%-56.3%improvement over conventional methods.End-to-end latency remained under 5 seconds with efficient resource use.

KI fragen

Bookmark

View Full Paper