01 / 03
TEKNOFEST · AI & 5G2026
- Python
- YOLOv11
- Computer Vision
- 5G
Road accidents are a data problem before they are a hardware problem. We asked what a camera could prevent if it never blinked — and never lagged.
- Role
- Project Coordinator & AI/ML Engineer
- Team
- 5Genç
- Stage
- In Development (TEKNOFEST 2026)
01Challenge
Assisted and autonomous driving systems need to see hazards — vehicles, pedestrians, unexpected obstacles — in real time, and a detection that arrives late is a detection that never happened. The system had to combine low-latency 5G transport with vision models fast enough to matter at road speed.
02Approach
We built the perception layer on YOLO-family models (YOLOv8, then YOLOv11), trained and iterated in Python on scenario-specific datasets. 5G network integration carries detections with minimal latency, so alerts can reach vehicles and infrastructure while they are still actionable. As coordinator, I own the architecture end to end — from model training loops to how the pieces talk over the network.
03Outcome
Active development is ongoing, focusing on training models and integrating low-latency 5G pipelines for the TEKNOFEST 2026 season. We are continuously testing new road scenarios to improve real-time detection accuracy.
Next project