Vision-Based Cooperative Infrastructure Perception
Multi-camera fusion + detection + tracking for intersection safety and collision forecasting.
Highlights
- Engineered multi-camera fusion using homography to create a unified top-down grid for situational awareness.
- Optimized YOLOv8 inference with TensorRT FP16 to reduce latency while maintaining high-accuracy detection.
- Integrated EKF + Hungarian for multi-object tracking; reduced compute overhead by 20% via efficient prediction and association.
Demo
Next: embed a Hugging Face Space here (or custom inference UI).