Article: Construction of UAV trajectory prediction model based on 5G communication and image recognition technology Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.36 pp.35 - 53 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 km2. Algorithm improvements include enhanced YOLOv11 for small targets, a JPTrack module to minimise identity switches, and an LSTM-Attention prediction model. In 30 km2 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. Inderscience Publishers - linking academia, business and industry through research

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

Authors: Cheng Li

Addresses: School of Public Security, Inner Mongolia Police College, No. 11, Xing'an North Road, 010051, China

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 km². Algorithm improvements include enhanced YOLOv11 for small targets, a JPTrack module to minimise identity switches, and an LSTM-Attention prediction model. In 30 km² 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.

Keywords: 5G-advanced communication and sensing integration; unmanned aerial vehicle; UAV trajectory prediction; YOLOv11; joint path tracking; JPTrack; long short-term memory; LSTM; system implementation; performance evaluation.

DOI: 10.1504/IJICT.2026.153010

International Journal of Information and Communication Technology, 2026 Vol.27 No.36, pp.35 - 53

Received: 13 Nov 2025
Accepted: 08 Dec 2025
Published online: 17 Apr 2026 *

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

Keep up-to-date