Enhancing industrial safety AI with synthetic data on Amazon SageMaker AI
What Happened
The article describes an endâtoâend synthetic data augmentation pipeline on Amazon SageMaker AI that uses a diffusion model (QwenâImageâEditâ2509) to insert synthetic people into real industrial scene images and then automatically labels them with Amazon Rekognition DetectLabels. Experiments showed up to 160âŻ% improvement in personâdetection mAP50 without manual annotation or hazardous photography sessions.
Why It Matters
Enterprise architects can reduce dataâcollection costs and accelerate model training for safetyâcritical edge deployments, improving reliability of personâdetection in highârisk scenarios. The approach also mitigates class imbalance and domainâgap issues, potentially lowering maintenance overhead for model updates.
The Limitation
The reported performance gains are based on a specific diffusion model and may not generalize to all industrial environments or equipment types.
What You Can Do
Implement a pilot syntheticâdata pipeline on SageMaker AI to generate and label training images for your existing safetyâvision models.