The Russian invasion of Ukraine has further exacerbated the shortage of chips that is affecting the entire hardware and software industry.
Russia produces almost half of the global supply of Palladium, as Neon, Helium and Scandium are now also coming under threat of constrained supply and higher prices. These materials are critical for semiconductors, smartphones and servers.
Shortage of chips and other raw materials
The shortage of chips and other raw materials required for hardware production directly affects the software industry. Implementing on-premises software solutions requires servers that are often not immediately available.
This causes a delay in the adoption of advanced software solutions, especially AI applications, such as facial recognition and video analytics that require extensive and fast processing capability. As a direct result, hardware manufacturers are now pushed to deliver thin and efficient dedicated devices that make use of the minimum components required to support a specific application.
Oosto Vision AI Appliance
Oosto has announced the launch of the Oosto Vision AI Appliance, a near-edge device
Globally renowned video analytics and facial recognition firm, Oosto has announced the launch of the Oosto Vision AI Appliance, a near-edge device that delivers the power of Vision AI in a palm-sized device, allowing organisations to perform facial recognition and video analytics more affordably, while reducing IT complexity.
The Vision AI Appliance is based on NVIDIA Jetson system on module and equipped with Oosto’s neural network models optimised to support low-power devices.
Savings in hardware, power, cooling, and failover costs
Dieter Joecker, the Chief Technology Officer (CTO) at Oosto, said “When organisations 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.”
Dieter Joecker adds, “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.”