People counting with existing CCTV camerasCount people entering and leaving stores, branches, facilities or zones using existing CCTV. In/out counts, footfall trends and occupancy inputs, without identifying individuals.
Accurate in/out counts for entrances and zones, using cameras you already have.
Camera-based people counting detects and tracks people crossing a virtual line at an entrance or zone boundary and counts them in each direction, providing footfall and occupancy data.

The problem
Footfall data is the basis for conversion rates, staffing and space planning — but dedicated counters at every door are costly, and manual counts do not scale.
How it works
Existing IP cameras / NVR
RTSP / ONVIF streams
Edge device on-site
AI models + rules; video stays local
Events
Time, camera, zone, evidence frame
Dashboard, alerts, API
Notifications, relays, REST/webhook
- 1 A counting line is defined at each entrance or zone boundary.
- 2 People are detected and tracked across the line.
- 3 Directional counts are aggregated per hour, day and location.
- 4 Counts feed occupancy calculations and reports.
What can be detected
- Entries and exits per door
- Footfall by hour and day
- Zone-to-zone movement counts
- Inputs for occupancy limits
Typical scenarios
- Store and branch entrances
- Hotel lobbies and restaurants
- Factory gates and canteens
- Event and exhibition areas
Deployment options
On-premise / edge
Analysis runs on hardware inside your network. Video does not leave the site; only events and metrics are stored or shared.
Cloud
Suitable for distributed, low-camera-count sites where central management matters more than keeping video on-site.
Hybrid
Video is processed on-site, while events, dashboards and multi-site reporting are managed centrally.
Working with existing cameras
- Overhead or steep angled views at entrances give the most reliable counts.
- Existing security cameras may need a different angle for doorway counting.
- Most IP cameras and NVRs that provide RTSP or ONVIF streams can be connected, regardless of brand.
- Before a pilot, sample footage from each candidate camera is reviewed for resolution, angle, distance and lighting.
- Where a view is not suitable, the recommendation is usually to reposition the camera or add one — not to replace the whole system.
Integration
- Dashboard and exports
- REST API to POS, BI or building systems
Privacy and security
- No face recognition is used in safety and operations analytics; events describe what happened, not who.
- On-premise processing keeps video inside your network.
- Evidence clips, retention periods and user access are configurable and should follow your GDPR/KVKK policies.
- Workplace monitoring should be introduced with clear employee information and, where applicable, consultation with employee representatives.
Limitations
- Groups walking very close together can reduce accuracy; this is validated against manual counts.
- No identification of individuals is performed.
How a pilot works
Frequently asked questions
Often yes, if the camera covers the entrance at a usable angle. If not, repositioning or adding a camera at the door is recommended.
Counting does not require identifying anyone. Retention of video and event data is configured with your data-protection requirements.
Related solutions
Industries
Further reading
Start with the cameras you already have
Send us a few frames from your cameras and the problem you want to solve. We will tell you honestly what is feasible.
Frequently asked questions
Can we use our security cameras for counting?
Often yes, if the camera covers the entrance at a usable angle. If not, repositioning or adding a camera at the door is recommended.
Does it store personal data?
Counting does not require identifying anyone. Retention of video and event data is configured with your data-protection requirements.
What can AI detect in your factory?
Let's review together which safety, quality and production analytics your existing security cameras can deliver.
- Free 15-minute technical call
- Camera infrastructure pre-assessment
- Feasible AI scenarios