INFERENCE BUILT FOR PHONE FOOTAGE
Raw practice film in, biomechanical telemetry out. The stack is engineered so a coach never does more than a two-tap upload, while GPU-accelerated inference returns branded reports inside the SLA window.
Ingestion & Pipeline
Direct S3 / Supabase Storage uploads via signed URLs — no coach-side tooling required.
Celery/Redis or AWS SQS handling asynchronous video processing at academy scale.
Python microservice on MediaPipe / YOLOv8-pose tracking release time, shooting arc, elbow extension angle and lateral plant speed.
Fastify (Node.js) or FastAPI paired with Supabase — PostgreSQL plus multi-tenant auth.
Stripe Connect (Express/Custom) for automated split fees: 1% platform fee plus SaaS billing.
NVIDIA Acceleration Stack
Converts PyTorch/ONNX pose models into high-performance inference engines: 3x–5x latency reduction, 60-second clips processed in under 2 seconds.
Multi-stream pipeline handling hardware video decode, NvDCF tracking and coordinate rendering.
NVIDIA L4 / A10G GPUs on RunPod or AWS. Zero hardware on-site; pure smartphone/tablet upload at $0.50–$0.90/hr.
NVIDIA Jetson Orin Nano / AGX Orin leased to flagship academies at $499–$999/mo for real-time court feedback.