Case study
Smart Detection for gas stations
AI cameras that watch the pumps, the forecourt and the shop in real time: fewer incidents, shorter queues, privacy built in.
- Industry
- Energy and retail
- Technology
- PythonReactGraphQLPostgreSQLAWSEdge computing
Illustrative image
At a glance
The problem
The stations faced fuel theft, shoplifting and vandalism, and staff had to monitor several areas by hand, so incidents were handled late.
What we built
- 01Queue monitoring
- 02Vehicle and plate recognition
- 03Fuelling fraud detection
- 04Security and surveillance
- 05Customer behavior insights
What changed
- 40% fewer security incidents
- 20% higher operational efficiency
- 30% faster customer flow
- Privacy by design
The full story
The problem
A gas station has to be fast, safe and pleasant to use, all at once. Staff watch the pumps, the forecourt and the shop at the same time, and problems are usually noticed after they happen. Smart Detection is our AI camera system that watches those areas in real time, warns staff as something happens and shows where time and money are lost, without compromising customers' privacy.
Queues at the pumps and the shop entrance frustrated customers, and fuel dispensed without payment led to disputes over transactions. Any camera solution also had to respect data privacy rules.
What we built
We connected the stations' cameras to AI models that watch the whole site in real time. Detection runs on an edge AI device at the station, linked to the cameras, an alarm light and the fuel dispensers.
The system measures queues at the pumps and estimates waiting times, recognizes vehicle types and license plates, and spots suspicious behavior such as fuel dispensed without payment. Staff and security get an alert as it happens, not at the end of the shift.
The same cameras show how customers move through the shop, which helps with product placement and store layout. Faces and vehicles are blurred in processing, so the system supports GDPR compliance from the start.
- Queue monitoring
- Cameras measure queues at the pumps, estimate waiting times and help balance lane use.
- Vehicle and plate recognition
- Vehicles are detected and classified, and license plates recognized for registered customers.
- Fuelling fraud detection
- Unauthorized dispensing and non-payment trigger a real-time alert to staff.
- Security and surveillance
- Continuous monitoring of the site, with alerts for unauthorized access or suspicious activity.
- Customer behavior insights
- Movement patterns in the shop inform product placement and layout.
What changed
- 40% fewer security incidents
- Real-time monitoring and alerts strengthened security and loss prevention.
- 20% higher operational efficiency
- Staff spend their time on customers instead of watching screens.
- 30% faster customer flow
- Queue management and shorter fuelling times move more customers through.
- Privacy by design
- Full vehicle blurring and face anonymization support GDPR compliance.
Contact
Tell us what you want to solve.
Need a technology assessment, a software delivery partner, an AI pilot or more engineering capacity? Tell us the challenge. We will help define a practical next step.
- 01Tell us the challengeBy call or message, in your own words.
- 02We talk it throughWith consultants and engineers who build what they advise.
- 03You get a practical next stepAn assessment, a pilot, a delivery plan or a team.