Detection on the Cameras Security Center Already Records
No Security Center connector is prebuilt. The connection would be to the stream, on the RTSP path that already carries Axis, Hanwha and Verkada, and Genetec is one of the platforms that path has been exercised against, so an engagement scopes configuration and verification rather than development. Security Center unifies video, access control and licence plate recognition on one platform, and it would keep doing all of that. AI Live Insight would read streams alongside it.
How it connects
Streams would be consumed over RTSP, from the cameras or republished by Security Center, with each source added by address, port, stream path and credentials. ONVIF profiles S and T cover discovery, stream URL retrieval and PTZ. Encoding would stay where it is: the existing H.264 or H.265 bitstream is read as emitted and the codec detected per source, so no re-encode happens and no encoder load is added to the archiver.
The flow would be inbound only. Detections would become a timed metadata track beside each recorded segment, and the clip around an event would be filed in the library under one Recording Folder organized by camera, under the same access control, retention and chain of custody as everything else in it. Classes, thresholds, severity, zone rules and clip length would be configured per camera in the portal.
Nothing would flow back. Camera control, access control, licence plate configuration, Security Center's own metadata and its user management would stay with Genetec. Analysis reads the live stream, so it would run on a GPU server on the same network rather than in a cloud region, which is what keeps an alert useful.
What you can do together
- Add detection to cameras Security Center already records, without replacing a camera or changing how the archiver works.
- Keep the clip around an event in the library under retention and a custody record, while the continuous archive stays with Genetec.
- Configure per camera, so a car park and a secure door are not held to one threshold.
- Run the analysis on site, so the alert reaches an operator in seconds.
A scenario
- ScopingThe engagement would confirm which cameras cover the doors, how their streams are reached, and what should count as an alert.
- SetupA GPU server would sit on the hospital network, and the corridor cameras would be added with their stream details.
- ConfigurationA zone rule would cover each doorway, with the seconds kept either side of a detection set so the clip shows what happened before it.
- An afternoonA door left open would raise an alert on the dashboard, and the clip would be filed in the library under the estates folder with its custody record.
- ReviewThe safety lead would pull the week's clips from the library. Security Center would go on holding the full archive and running access control.
What stays where
Security Center remains the platform
Video, access control and licence plate recognition stay there, along with camera control, its own metadata and its users.
The stream is the whole of the connection
Inbound only, with nothing written back, and Genetec's own alerting continuing as it does now.
Evidence lands in the library
Clips around events carry access control, retention and chain of custody; the continuous archive is unaffected.
Processing would run on site
A GPU server on the same network is what keeps alert latency low, and it is the deployment this work is projected for.
Products and solutions
Next step
See it on your own Genetec Security Center instance. We will show the connection made, the data moving and the output, then size it for your deployment.
Request a demonstration or write to sales@vidizmo.ai
sales@vidizmo.ai · vidizmo.ai/integrations/catalog/genetec-security-center