Aug 2026
ODE-Net: Occluded traffic sign detection and occlusion percentage estimation via frequency-aware feature fusion
This paper proposes ODE-Net, an advanced YOLOv11-based detection framework with three key contributions, which achieves 94.4% occlusion-prediction accuracy while maintaining a compact size and low computational cost, thereby achieving a superior accuracy-efficiency balance.
Jia-Cai Liao, Le Luo, Lin Hu et al.
· Proceedings of the Instituti... · 0 citations