Oosto says its Vision AI platform optimizes neural networks for smart cameras, proximity devices and access control systems.
NEW YORK – Oosto announces the latest release of its Vision AI software platform, which provides significant video analytics enhancements for video surveillance equipment and access control systems.
The release coincides with the introduction of the company’s own proprietary device, the new OnPoint touchless reader tablet.
This result will enable security teams to further reduce organizational risks associated with outdated physical security systems, better manage controlled access and identify security threats, the company said.
“It was only a matter of time before real-time video surveillance and access control systems harnessed the power of the border,” says Dieter Joker, chief technology officer at Oost. “With our latest enhancements to our Vision AI platform, Oosto is moving computing workloads off expensive servers, but perhaps more importantly, we’re doing it without sacrificing recognition accuracy, security and performance in real-world scenarios. Expanding the system’s physical footprint.”
Oosto Vision AI Modernizes Security Systems
According to the New York-based company, its new Vision AI 2.6 software platform maximizes the power of edge computing, AI and facial recognition to take physical security systems to a new level.
The Oosto 2.6 update provides a number of benefits, including improved response times, a smaller physical footprint (because fewer servers are required to process video), improved scalability, and even built-in failover, so edge devices can continue to work continuously if the network fails.
With its latest enhancement, the company’s Vision AI platform uses state-of-the-art Kubernetes technologies to secure its algorithms by containerizing the application (as opposed to running neural networks directly on edge devices).
Explaining the workings of Vision AI, Oosto suggests that its neural networks are optimized to support low-power edge devices, while offering high performance and recognition accuracy. Based on internal benchmarks, Oosto’s algorithms are now seven times more efficient in terms of watts per video stream than competing products.
Oosto notes that organizations are moving critical processes from central servers to various edge devices, and its adoption is growing across industries. Backing up this statement, the company cites data that the global PC market is expected to grow to $155.9 billion (US$) by 2030, an annual growth rate of 38.9% (source: Research and Markets, September 2022).
This shift continues as Oosto continues, enabling peripheral devices such as smart cameras, gates and access control systems with local decision-making to open gates for authorized personnel or send real-time alerts to security teams when a person of interest enters a commercial space.
Summarizing the benefits of the newly announced Vision AI 2.6 update, the Oosto platform offers these features:
Optimized Neural Networks: Ooston’s neural networks are optimized to work on a variety of peripheral and near-field devices. Historically, video graphics required computationally intensive GPU servers. Today, Oosto’s neural networks for watchlist alerting can support very large datasets (which are often required for smart cities and other related use cases) and allow image-rich watchlists to be automatically pushed to mobile workers in the field.
OnPoint Reader: The new Oosto OnPoint reader is a versatile device that can operate autonomously and provide access to employees and guests even in the event of a network failure. OnPoint readers use facial biometrics and edge computing to quickly and accurately recognize authorized personnel, even when faces are blurred. OnPoint’s contactless reader eliminates surface contact and includes 3D motion detection to prevent spoofing (where a guest uses a photo or video of an authorized employee to bypass security).
Near-Edge Processing: Oosto is launching an updated next-gen device (such as the NVIDIA Jetson) that operates with a smaller physical footprint and is equipped with state-of-the-art neural network models for video analytics. Although the latest version of the Vision AI platform still requires a central server, it can now handle a number of advanced GPU-less mini-servers.
Smart camera integration: Oosto introduces the concept of “camera as sensor” by embedding its neural networks (SDK) into the latest AI-enabled CCTV cameras. Since image processing and surface vectorization are done in-camera, these smart cameras reduce server-side computing requirements and enable powerful features such as watchlist alerting, frictionless access control, lag detection/prevention, and other video analytics capabilities.
Genetec VMS integration: Oosto’s latest release provides Genetec VMS customers with a single pane of glass to view real-time security threat alerts by accurately identifying people of interest in real-time, even under adverse conditions. The Oosto integration provides surveillance operators with a complete history of all POI detections (video playbacks) within Genetec Omnicast VMS to facilitate and speed up investigations.