Analysing V2V & V2I Collision Warning Systems at Intersections Under LOS/NLOS Conditions Analysing V2V & V2I Collision Warning Systems at Intersections Under LOS/NLOS Conditions
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636901
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: Cooperative Safety, ICRW, ITS, Line-of-Sight (LOS), LSTM, Non-Line-of-Sight (NLOS), Trajectory Prediction, Unsignalized Intersections, V2I, V2V, V2X, VRU
- Marmara Üniversitesi Adresli: Evet
Özet
Unsignalized intersections pose high collision risks in Intelligent Transportation Systems. This study compares three trajectory prediction methods (mathematical, map-based mathematical, and map-based LSTM/WaleNet) for V2V and V2I collision warning systems (ICRW/CWI). Evaluated under LOS/NLOS conditions, results show the map-based mathematical model provides the best balance of accuracy and real-time efficiency, making it highly suitable for lightweight edge-based warning systems.