Computer vision model for real-time traffic signal detection achieving mAP@50 of 0.936. Trained on custom dataset with data augmentation pipeline.
Traffic Signal Detection (YOLOv8)
Computer vision model for real-time traffic signal detection achieving mAP@50 of 0.936. Trained on custom dataset with data augmentation pipeline.
Tech stack
PythonYOLOv8OpenCVPyTorchONNX
Key metrics
mAP@50: 0.936
30 FPS inference
12 signal classes