New Oosto appliance brings facial recognition, video AI to edge for lower TCO
Oosto has launched a new appliance for edge-based video analytics and facial recognition to transform the total cost of ownership for the artificial intelligence capabilities.
The new Oosto Vision AI Appliance features the company’s advanced neural network models for video analytics, optimized to run on low-power devices. The device is based on the Nvidia Jetson Xavier NX system-on-module, according to the announcement, and provides Oosto’s algorithms for high accuracy analytics even in tough conditions with low-quality images, on a simple, ‘ruggedized’ device, according to the announcement. The company has also launched a TCO Calculator to help customers estimate their potential cost savings from moving their AI analytics to the network edge.
The appliance provides a smaller attack surface for enhanced data security, and enables IT administrators to scale their video analytics systems by simply adding more Vision AI Appliances while the system continues running.
“The drop in total cost of ownership, software and hardware, allows smaller and local organizations to deploy quicker and use Vision AI applications for a wide range of use cases,” explains Professor Mario Savvides, head of Carnegie Mellon University CyLab’s biometrics lab. “From counting people and analyzing queues in commercial spaces, through facial recognition for security and access control purposes, to advanced analysis of situations and contexts to identify safety threats and violence. Together with Oosto we are developing a wide range of machine vision applications in parallel with the increase in demand from organizations that wouldn’t be your first guess for implementing forefront technology like local stores, elementary schools and bars. The significant reduction in hardware cost in Oosto’s AI edge solution can now enable a wide range of application use cases in our everyday environment”
Savvides is highly respected in the biometrics research community for his work on biometrics challenges like identification of people in motion and images with facial occlusions, and his research center announced a partnership with Oosto when the company just as it was rebranding from AnyVision in 2021.
Moving facial recognition and other visual AI capabilities to the edge is a major strategic focus for Oosto, and edge computing was also identified as a key growth area for the biometrics industry by Savvides in a recent webinar panel discussion.
“When organizations add more camera channels to their visual analytics operations, they immediately discover the headaches and high costs associated with scaling their existing infrastructure to accommodate the extra video channels,” states Dieter Joecker, Oosto’s CTO. “The Oosto Vision AI Appliance streamlines these expansions by effectively shifting the compute load associated with computer vision from on-premise servers to these low-power efficient appliances–saving significant hardware, power, cooling, and failover costs.”
The Oosto Vision AI Appliance will be on display at ISC West in Las Vegas, which runs from Wednesday to Friday this week.