Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Design Guide—Virtualized Computer Vision for Smart Transportation with Genetec
Introduction Architecture concepts and requirements Solution Architecture Validation Sizing the solution Backup and restore operations Monitoring the solution Troubleshooting recommendations Summary and conclusions
Summary and conclusions
References

Summary and conclusions

Home > Workload Solutions > Computer Vision > Guides > Design Guide—Virtualized Computer Vision for Smart Transportation with Genetec > Summary and conclusions

Summary and conclusions

  • We found that the VxRail with VMware provided a reliable and scalable Dell Validated Design platform for hosting VMS and CV applications from different vendors.

    Together with three market-leading VMS and CV vendors, Dell Technologies has designed an integrated solution running on a common platform that is easy to install, easy to operate, and easy to grow.

    The results of our HA testing show that virtualized instances of Genetec Security Center for video management together with CV applications from both BriefCam and Ipsotek provide native high availability (HA) features and scale-out performance that are critical in an enterprise-class solution. The VxRail HCI system with VMware virtualization plus Nvidia A40 server-class GPUs with vGPU provides additional features for managing high availability and scale-out needs that can complement the CV and VMS application's native features.

    All of these products were installed on a single VxRail 5-node cluster for full system integration testing. Storage for the video management archive was provided by Dell PowerScale scale-out NAS storage. All video streams used for testing were provided by camera simulation software reading from prerecorded local video files in a continuous loop. We tested a maximum of 675 simulated camera streams being archived to the VMS together with each CV application performing real-time analytics on 75 camera streams each. We also found that a single VM with one Nvidia A40 GPU could process real-time analytics from 30 camera streams reliably.