Wednesday, March 23rd 2022

Oosto Launches Edge-Based Vision AI Appliance to Revolutionize the TCO Calculus of Video Analytics

Oosto announced today the launch of the Oosto Vision AI Appliance, a revolutionary near-edge device that delivers the power and security of Vision AI in a palm-sized device, allowing organizations to protect people, customers and assets more affordably while reducing IT complexity. The Vision AI Appliance is based on the NVIDIA Jetson Xavier NX system on module and is equipped with Oosto's state-of-the-art neural network models for video analytics that are optimized to support low-power devices. Significantly, this was achieved without compromising on superior performance, security or recognition accuracy which historically required compute-intensive GPU processing servers.

This announcement is part of Oosto's ongoing commitment to edge computing. In 2021, the company embedded its Vision AI algorithms on Ambarella's CV2x family of edge AI vision SoCs. Moving the workload to the chip level and to near-edge devices enables organizations to perform real-time video analysis. Significant processing power is required to analyze every frame of a video feed and perform a variety of instant computations to determine if the person entering a building is an authorized employee or on a watchlist (e.g., a VIP or security threat).
"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," said 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 emerging edge ecosystem has garnered considerable attention - the on-device data processing and computing power now available on edge devices was once reserved exclusively for the cloud. In fact, Gartner predicts that by 2025, 75% of enterprise-generated data will be created and processed at the edge, outside of traditional centralized data centers or the cloud.

Oosto, a NVIDIA Metropolis partner, is pioneering Vision AI and optimizing neural networks to run on small near-edge appliances while maintaining top performance and recognition accuracy.

Oosto's Vision AI Appliance delivers powerful benefits, including:
  • Dramatic TCO (Total Cost of Ownership) Savings: By pushing more analytic capabilities closer to where data is collected, customers are achieving greater responsiveness, efficiency, and TCO savings with a small, low-power, near-edge appliance. Oosto's online TCO Calculator demonstrates the amount of cost savings that can be realized by switching to the Vision AI Appliance.
  • Superior Accuracy: The Oosto Vision AI Appliance runs the company's industry-leading neural networks for video analytics which are trained in the toughest conditions on low-quality images.
  • Scalability: When new video streams are added, IT administrators can simply add more Vision AI Appliances without taking the entire system down, improving overall uptime.
  • IT Simplicity: The Vision AI Appliance, which can fit into the palm of a hand, does not take up space in a rack, consume much power, or place a burden on cooling systems. Having a "ruggedized" device without fans or moving parts allows the appliances to obtain a much longer operating life, leading to fewer failures and an overall reduction in cost, and channel redundancy.
  • Enterprise-Class Failover: If an appliance fails, the Oosto Vision AI Appliance provides real-time failover to a secondary, low-cost appliance that can easily absorb the payload of the failed appliance. In larger installations with many cameras, near-edge appliances can form an "edge cluster" which allows for redundancy and load balancing between the appliances.
  • Data Security: The Vision AI Appliance is a purpose-built closed box for video processing. This means the surface area for attacks on the appliance is significantly less than traditional servers.
The Vision AI Appliance launch coincides with the latest release of Oosto's Vision AI software (v2.5) which includes improved functionality for inquiry investigations, more granular search capabilities, system integrator support, and updated integrations with VMS systems (e.g., Genetec, Milestone and Honeywell).
Source: Oosto
Add your own comment

3 Comments on Oosto Launches Edge-Based Vision AI Appliance to Revolutionize the TCO Calculus of Video Analytics

#1
zlobby
Cool! Does it feed off the HDMI input?
Posted on Reply
#2
TheLostSwede
News Editor
zlobbyCool! Does it feed off the HDMI input?
That's most likely an output, so I would say that's a no.
Very few Arm based boards have proper HDMI inputs that can be used for video encoding or AI inference.
Posted on Reply
May 21st, 2024 11:27 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts