← All updates

vision

Sentinel Hits 92% on Crowd Scenes

Our edge person detector now holds 92% accuracy on dense airport and stadium footage — in a 19MB ONNX package with a live browser demo.

Innomium Vision Team · July 2, 2026

Sentinel is Innomium's person-detection skill for mission environments where generic models fail — overlapping crowds, variable lighting, and tight latency budgets.

What changed

We combined test-time augmentation, adaptive confidence calibration, and scene-aware distillation to lift accuracy on held-out crowd splits while keeping the model at 19MB ONNX.

Where teams deploy it

  • Airport concourses and security lanes
  • Stadium ingress and egress monitoring
  • Dense retail floors during peak hours

Try it today

The live Hugging Face Space runs entirely in-browser. For production, pull weights from innomium/person-detection and integrate with your existing VMS or edge gateway.

Want production AI shipped on your timeline?

Talk with Innomium about vision models, long-context LLMs, or builder challenges.