The safety of people while using public and private spaces, operational efficiency, sustainability, and revenue growth are key goals for organizations that must be constantly monitored and improved in the context of ever-increasing complexity. Operations staff, facilities administrators, and safety personnel are finding that much of the data collected by video cameras can help drive greater customer and employee experiences and better financial outcomes through revenue increases and cost reductions - not just for the primary organization but for all the closely related business entities.
Improving the experience for visitors and employees requires removing barriers to better facilities flow management, more accurate demand forecasting, and more effective monitoring to make the time spent in the facility a positive, friction-free experience.
- Flow restrictions increase the overall time required to complete a task, decreasing the productivity of inhabitants, especially frequent visitors and employees.
- Better forecasting of wait times and occupancy enables operators to keep both staff and visitors better informed, boosting satisfaction for both groups.
- Automated monitoring enables faster response to inquiries and needs, often before the visitor or staff is even aware of an issue. This makes the interaction process smoother by better anticipating and proactively notifying those needing information.
To extract the most value possible from computer vision and related data, organizations across the globe are turning to video analytics and artificial intelligence (AI) capabilities to create a safer and more engaging experience with improved security and advanced safety measures such as touchless entry authorization. Any large facility requires a wide range of business applications, including computer vision and data analytics, that can be installed and managed with minimal time and cost to address these challenges effectively.
Dell defined a vision to create a multipurpose platform using world-class technology that would allow organizations to display and analyze CCTV video using a single integrated platform. The proposed architecture was based on the VxRail HCI system with VMware virtualization plus NVIDIA A40 server-class GPUs. The VxRail HCI system and VMware virtual machine virtualization were the only design components already familiar to many IT and OT (operational technology) professionals.
The initial set of workflows centered on Video Management Systems (VMS) and computer vision applications. The platform was then tested with additional software applications and workflows to show how this common platform supporting VMS and computer vision could also host tools and applications to monitor system security. The common platform approach proved to be a capable and flexible system with the benefits of fast installation, reliable "Day 2" operations, and robust features for managing high availability and scale-out needs that can complement the native features of applications from our partners when all the applications were hosted on VMware virtual machines.
As many providers of computer vision software applications started shifting development to containerized applications, it became apparent that many of the organizations interested in a common platform approach would also need to support containerized applications. Recognizing that while both containers and VMs can help reduce operational complexity and improve the utilization of IT resources, each has its pros and cons. Therefore, many organizations that want to expand their suites of operational workflows leveraging computer vision will need to host both types of virtualization for the foreseeable future.
Container technologies, including orchestration frameworks like Kubernetes, have rapidly changed the virtualization landscape since the release of the Docker container engine in 2013. A container is a standard unit of software that packages up code and all its dependencies, so the application runs quickly and reliably from one computing environment to another. Therefore, while virtual machines allow system administrators the flexibility to run several virtual servers on a single piece of hardware - regardless of the VM's operating systems, containers offer lightweight, high-density application virtualization. Containers also have operational advantages, including starting and stopping container instances and applications in seconds and some security advantages inherent in separating applications in isolated containers.
Recently, computer vision application suppliers transitioned from developing products that can only be virtualized with a dedicated Windows operating system running in a virtual machine to offerings that can be deployed using container technology. Organizations that host multiple applications for computer vision and related operational workflows must address how best to provide infrastructure platforms that can meet the needs of products implemented using container technologies and virtual machine configurations while minimizing the total cost of ownership (TCO).