Velosyti
Home / Case studies / Security

A security operations team · Tamil Nadu · 2026

Reviewing weeks of gate footage in hours

Face detection on stored CCTV footage, with reports on repeat entries and late exits. The GPU turns itself off.

LiveSecurity
Client
Security operations team
Input
Stored footage from gate cameras
AI
Vizhi and Thedal, on GPU
Search
pgvector
Infra
Lambda, SQS, EC2 g4dn, RDS

The problem

Security teams had hours of gate footage and no practical way to answer simple questions: who entered more than once, who left late, how many different people came in today.

What we did

  • Footage is uploaded to storage and queued. A GPU worker finds and tracks faces in each clip.
  • Faces are stored as numbers (embeddings) and matched against the enrolled directory.
  • Reports show repeat entries, delayed exits and unique faces for the director.
  • The GPU machine starts when there is work and stops when there is none, with a budget alert and an emergency stop.

Footage to report

wakes Gate footageUploaded clips QueueSQS GPU workerFinds and tracks faces Budget guardAuto stop when idle Face vectorspgvector search Enrolled directoryKnown persons ReportsRepeats, late exits
  1. Gate footageUploaded clips
  2. QueueSQS
  3. GPU workerFinds and tracks faces
  4. Budget guardAuto stop when idle
  5. Face vectorspgvector search
  6. Enrolled directoryKnown persons
  7. ReportsRepeats, late exits

What changed

A working review system that runs the expensive GPU only when needed.

1Directory of enrolled persons
0GPU hours when idle
3Standard reports
111Commits to date

Built with

FastifyGraphQLLambda arm64VizhiThedalpgvectorSQSCloudFormation

Have something that needs building?

Answer a few questions and we will suggest the right place to start.