Journal of Multimedia Technology & Recent Advancements · Vol. 13, No. 2 (2026)
Traffic AI, Autonomous Driving and AR Crowdsourcing: Journal of Multimedia Technology & Recent Advancements 13(2)
By STM Journals ·
This issue of the Journal of Multimedia Technology and Recent Advancements brings together papers on AI for road transport, augmented reality and big data analytics. Two focus on road transport: an attention-enhanced YOLO detector for autonomous driving and a deep learning framework for traffic monitoring and signal control. A third paper reviews how crowdsourcing and augmented reality can work together for real-time information sharing, and a fourth proposes a framework for big data analytics.
What's in this issue
-
Attention-Enhanced YOLO Framework for Robust Real-Time Object Detection in Autonomous Driving Environments
Small or partly hidden objects remain hard for self-driving systems to detect. This paper presents an attention-enhanced YOLO framework that adds spatial and channel attention mechanisms to the detection architecture to improve feature representation and detection reliability for autonomous driving.
-
AI-Driven Real-Time Traffic Monitoring and Intelligent Control System: A Unified Deep Learning Framework for Smart Urban Mobility Management
Fixed-cycle traffic signals struggle with changing urban flows. The authors present TrafficNet-DRL, which combines traffic-flow prediction, vehicle detection, anomaly detection and reinforcement-learning signal control in one deep learning system for real-time traffic monitoring.
-
Crowdsourced Real-Time Response with AR Assistance
What happens when many people share live information and an app overlays it on the real world? This paper looks at combining crowdsourcing and augmented reality for real-time, context-aware information sharing and decision-making.
-
Intelligent Big Data Processing: Optimizing Analytics Pipelines Through Ensemble Machine Learning, Distributed Computing, and Adaptive AI Architectures
Traditional analytics struggle with ever-growing data. The authors propose ADAI, a layered framework that pairs distributed computing with an ensemble of machine learning models and adaptive AI, aimed at handling big data at scale.