অক্ষি OKKHI

On-premise vision AI

000Loading

Loading OKKHI

SOLUTIONS / OKKHI SENTINEL / SEN-16

SEN-16

Suspicious Entry & Unusual Activity

Flags the entry that doesn't look right — covered faces, helmets indoors, loitering, out-of-hours presence — before anything happens.

OKKHI SENTINEL · SURVEILLANCE THAT UNDERSTANDS.
Suspicious Entry & Unusual Activity — annotated camera view

Watches entry points and interiors for the patterns that precede incidents: a face covered at the door, a motorcycle helmet worn inside a booth, someone lingering far past a normal visit, presence during closed hours.

Rules are per-site and per-hour, and every alert is voted across frames before it reaches a human — so guards see the entries worth watching, not a feed of false alarms.

TYPICAL DEPLOYMENT
CamerasExisting CCTV (RTSP)
ComputeEdge GPU (shared)
Alert< seconds, voted
OutputControl-room alert · clip · journal
The problem

The incidents that make the news are preceded by minutes of visibly unusual behavior that nobody was watching — a covered face at the door, a visit that lasts far too long, an entry at 2 AM.

Who it's for

Banks and facilities screening entries around the clock

The outcome

The entry that doesn't look right gets human eyes on it in seconds — before it becomes an incident report.

How it works
STEP 1Capture

Entrance and interior cameras stream continuously.

STEP 2Detect

People, face coverage, headwear, and dwell are read per visitor.

STEP 3Pattern check

Site rules — hours, dwell limits, coverage — vote across frames.

STEP 4Escalate

Confirmed unusual entries alert the control room with the clip.

See it in action
Where it's used
1ATM booth entry screening
2Branch and office after-hours watch
3Loitering at gates and lobbies
4Covered-face and helmet-indoors alerts
Related solutions
Request a pilot for SEN-16 Fixed scope · weeks not months · your cameras, your product
Free 2-week pilot · you keep the report Let's Talk

Proof beats promises.
See it on your own cameras.

We run a two-week pilot on your footage, with your incidents, measured against your numbers. If the results don't convince you, you keep the full report and owe nothing.

Book a live demo

For teams deploying vision AI

Field notes from real deployments.

Once a month: what we learned shipping AI monitoring on factory floors and branch networks in Bangladesh — what worked, what broke, what we'd do differently. No product pitches.

No spam. Unsubscribe any time.