Product

Analysis

Detection

Decision

Action

Continuous analysis of all videos streams in parallel

Detection of gestures associated with shoplifting

Transmission to a human of a video sequence highlighting the gesture

Confirmation of shoplifting and intervention of security agents

Mobile Version

Product

Analysis

Continuous analysis of all videos streams in parallel

Detection

Detection of gestures associated with shoplifting

Decision

Transmission to a human of a video sequence highlighting the gesture

Action

Confirmation of shoplifting and intervention of security agents

Real-time demo

Our deep learning algorithm continuously analyses the content of security cameras.

It automatically detects gestures associated with shoplifting in real-time.

It sends a video alert to a human operator who confirms the theft and takes action.

Active learning

The neural network never stops improving after implementation. It gradually learns from new shoplifting data.

This is called “Active Learning”. the more stores we equip, the more data the algorithm is fed with, the better the performance.

Adapted alerts system

We send video alerts on different devices (monitors, smartphones, tablets) so that all security staff is able to take action.