01 / 04
Item hidden in a bag
A shopper puts an item into a bag or backpack instead of a cart or basket.
- Hand moves from the shelf to a bag
- The item does not come back out
- The bag stays with the shopper
FOR RETAIL CHAINS
Every camera in every store, watched for theft.
Omicent turns the cameras you already run into chain-wide shoplifting detection. Store teams get the clip in under a minute. Your LP team sees which stores, aisles and hours lose the most.
Omicent · All stores · This week
Live · 8 stores
StoreAlerts
#0142 · Dallas, TX14
#0087 · Phoenix, AZ11
#0311 · Atlanta, GA9
#0256 · Denver, CO8
#0198 · Chicago, IL6
#0421 · Miami, FL5
#0077 · Boston, MA4
#0029 · Seattle, WA3
Incidents by hourSample data
Watching every store
This week 60
Built for loss prevention
Act in the store. See the pattern across the chain.
One system for the associate on the floor and the LP director reporting to the CFO.
Store-level response
The store manager’s phone buzzes with the clip while the shopper is usually still inside.
- Alerts in 30 to 60 seconds
- Routed per store, shift or role
- Your intervention policy, applied consistently
Chain-level intelligence
Every incident is saved with its store, camera, behavior and time, so patterns surface on their own.
- Weekly reports by store, aisle and hour
- Compare stores, districts and regions
- Spot hot aisles before the count does
Evidence your investigators can use
Short clips centered on the shopper, starting just before the moment, ready to share.
- Export for case files and police reports
- Searchable by store, camera, behavior and date
- Retention set by your policy
Enterprise-ready
Deploys on the infrastructure you have, under the controls your security team expects.
- SSO and role-based access
- Webhooks and API into your systems
- Encrypted in transit and at rest
What it catches
Named behaviors, not vague “suspicious activity”.
Each alert is a clear yes or no for your team. These are real store clips, faces blurred, with the body points Omicent reads drawn on top.
02 / 04
Item hidden under clothing
An item goes under a shirt or inside a jacket.
- Hand moves under the shirt or jacket
- The item goes out of sight on the body
- Often while facing the shelf
03 / 04
Item tucked into a waistband
A small item goes into a waistband or a pocket.
- Both hands move to the waist
- Small items that fit in a hand
- Standing close to the shelf
04 / 04
Shoppers working together
One shopper hides an item on another, or in the other person’s bag.
- Two shoppers close together
- An item passes between them
- It ends up hidden on the second
How it works
One body-level model on every camera, in every store.
Omicent follows each shopper, reads 17 body points per frame and flags the moment an item is hidden. Here it is on a real footwear store camera.
Rollout
From pilot to chain without a big-bang cutover.
Start where you lose the most, prove it, then roll out region by region.
Week 1
Pick pilot stores
Five to ten stores and the aisles where losses are highest. We check every camera view.
Week 1 to 2
Connect
Cloud connect to your NVRs, or an Omicent box for large stores. No change to your VMS.
Weeks 2 to 6
Live alerts
Store teams get real alerts. LP gets weekly reports by store, aisle and hour.
After the pilot
Roll out
Review the results together, then expand region by region on the same setup.
Setup
Cloud, on-site, or both.
Choose per store. Small formats connect over the cloud with no hardware; large stores can keep full video on site with an Omicent box.
01
Connect your recorder
We connect to your NVR or IP cameras over a secure RTSP link to the Omicent cloud. Works with most recorders, including Hikvision, Axis, Hanwha and Avigilon.
02
Mark the store
Together we mark the checkout, the exits and the aisles with high-theft items, and choose who gets alerts.
03
Alerts go live
Clips start reaching the phones you chose. Every incident is saved for your weekly report.
Privacy built in
It watches movement, not identity.
No face recognition
Omicent does not identify anyone. It reads how hands and bodies move.
Temporary IDs
Each shopper gets an ID that resets when they leave the camera.
No tracking across visits
Nobody is followed across visits or across stores.
Only flagged clips are kept
Short clips of flagged moments, nothing else, retained on your policy.
Encrypted in transit and at rest
Video and clips are protected with TLS in transit and AES-256 at rest.
You control access
You decide who sees alerts and clips, store by store.
The business case
Model the shoplifting line across your chain.
Estimate what shoplifting costs across your stores today. A pilot then measures what Omicent keeps on your shelves, store by store, so the rollout case writes itself.
Shoplifting cost · estimator● live
Lost to shoplifting / yr$3.36M
Kept on your shelves / yr$1.01M
1.6% is the US average shrink rate (NRF National Retail Security Survey 2023). The share stopped is your assumption. A pilot measures the real number on your own stores.
A Dragonfruit AI company
Built on video AI already running at 15,000+ sites.
Omicent is a Dragonfruit AI company. Dragonfruit’s video AI runs in production for retailers and enterprises across the US, Latin America, Europe, the Middle East and Asia, and was one of ten vendors highlighted in Gartner’s 2024 Hype Cycle for Computer Vision.
About OmicentDragonfruit AI customers include
Canadian TireTractor SupplySmart & FinallululemonAmerican EagleBlue NileDaniel’s JewelersCity BeachBob’s Discount FurnitureGoodwill
FAQ
What LP and operations leaders ask us first.
Yes. Most chains start with a pilot in five to ten stores, chosen where losses are highest. You get real alerts from your own cameras and a report by store, aisle and hour before deciding where to roll out.
No. Cloud connect reads your existing NVRs over a secure RTSP link with no hardware. For large stores, or where you want full video to stay on site, an Omicent box handles 20 to 30 cameras each. You can mix both across the chain.
Alerts go to store phones and email, and can be pushed into your security, case management or incident systems through webhooks and an API. Clips export for investigations and police reports.
Access is role-based: store managers see their store, district and regional managers see their region, and LP sees the whole chain. Single sign-on is supported.
Omicent does not use facial recognition and does not identify anyone. Shoppers get temporary IDs that reset, nobody is tracked across visits or stores, and only short clips of flagged moments are kept, on your retention policy.
A pilot store is usually live within days of getting camera access. Rollouts then move region by region, with no change to your store teams’ existing tools beyond the alert app.
Ready when you areStart with the stores
Start with the stores
that lose the most.
Book a 15-minute demo and we’ll scope a pilot in five to ten of your stores.
Book a demo