Vision AI solution from HPE, NVIDIA, and IronYun

IronYun Vaidio® AI Vision Platform provides AI-enabled video search and analytics for security, health, safety, and operations. Powered by HPE ProLiant DL320 Gen11 Server and up to four NVIDIA L4 Tensor Core GPUs with a unique compact design, purpose-built for fast, efficient, and accurate AI video processing.

Computer vision is a broad field of artificial intelligence (AI) and computer science that focuses on interpreting visual data. Today, computer vision is used in a range of applications, from object recognition and autonomous vehicles to navigation and security. AI and machine learning (ML) technologies are crucial in powering computer vision technology. AI enables computer vision to understand, recognize, and analyze all types of visual data. AI models consume, absorb, and learn from the huge amount of labeled and unlabeled visual data.

How Vision AI is automating our spaces

Vision AI is a type of computer vision technology that leverages AI algorithms and deep learning models to analyze images and draw insights based on a set of criteria. Analyzing IoT sensors requires a lot of data input, and in order to manage both the camera’s input and the AI workflows there’s an important need for robust infrastructure to capture, store and processing the data in timely manner.

This technology has a tremendous benefits: improved operational efficiency, ability to react instantly to concerns, and provide public and worker safety.

Vaidio AI Vision Platform by IronYun

The Vaidio AI Vision Platform from IronYun uses advanced AI to deliver three key functions: active real-time monitoring for accurate alerting; intelligent, accelerated video search or incident investigation; and rich video metadata for business intelligence. Vaidio gives enterprise personnel reliable, real-time situational information, faster response and search times, and valuable operational data. Vaidio can quickly and cost effectively improve the security and safety posture of any enterprise.

Vaidio AI Video Analytics applications

Sample deployment

Small deployment 30 IP cameras	Medium deployment 200 IP cameras	Large deployment 1,000 IP cameras
30 Vaidio analytics licenses	200 Vaidio analytics licenses	1,000 Vaidio analytics licenses
1 Server	4 Servers	20 Servers 1 Command Center server

Accelerator-optimized compute — HPE ProLiant DL320 Gen11 Server with NVIDIA L4 Tensor Core GPU

The HPE ProLiant DL320 Gen11 Server is a 1U 1P server with a unique compact design purpose-built for computing at the edge and the data center delivering exceptional performance for computer vision with up to four single-wide (NVIDIA L4 Tensor Core GPU) or two double-wide GPU accelerators. The HPE ProLiant Gen11 advantage has the latest breakthrough advances in performance with fourth-generation CPU, PCIe Gen5, DDR5 memory, and NVMe storage.

The NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture delivers universal, energy-efficient acceleration for video, AI, visual computing, graphics, virtualization, and more. Packaged in a low-profile form factor, L4 is a cost-effective, energy-efficient solution for high throughput and low latency in every server, from the edge to the data center to the cloud.

With fourth-generation Tensor Cores and 1.5x larger GPU memory, NVIDIA L4 GPUs paired with the CV-CUDA library take video-content understanding to a new level. In a recent benchmark, the L4 delivered up to 120x¹ higher AI video performance than CPU-based solutions, letting enterprises gain real-time insights and implement smart-space solutions.

Trusted security by design

HPE ProLiant Gen11 servers are engineered with a fundamental security approach to defend against increasingly complex threats through an uncompromising focus on state-of-the-art security innovations built into our DNA.

• HPE exclusive immutable digital fingerprint with the silicon root of trust from HPE validates the lowest level of firmware to BIOS and software to help ensure the system is secure and in a known good state before the server even boots.
• Protect your infrastructure, workloads, and data from threats to hardware, and risks from third-party software, with a trusted edge-to-cloud security posture built on an HPE compute core hardened through a proven zero trust approach to security.

Modernize your compute management experience

Seamlessly monitor, manage, and gain visibility of your distributed compute environment.

• Unified compute management — streamline compute management operations with a centralized, cloud experience. With real-time access to servers, you can quickly gain visibility to your distributed environment, identify issues, and update servers in a few clicks.
• Simplify and automate tasks — save time and money with agile server lifecycle management that reduces manual efforts, drives better efficiency of server deployments and updates, gives visibility into server health status, and alerts you to critical hardware failures.
• Secure compute operations — take a zero trust approach incorporating multi-factor authentication, security certificates, and industry-leading security innovation of HPE ProLiant — so you can easily establish governance and compliance controls across the entire environment.

HPE and NVIDIA solution for IronYun Vaidio AI Video Analytics

Feature	Specifications
GPU support (front loaded)	Front loaded — up to four NVIDIA L4 Tensor Core GPUs (Up to 4 SW or 2 DW — front loaded)
Processor	4th Generation Intel® Xeon® Scalable processors
Memory	Up to 2 TB of DDR5 up to 4800 MT/s
Drive count	Up to 4 SFF NVMe/SAS/SATA or up to 8 EDSFF E3.S 1T NVMe SSD
Boot options	Optional internal RAID 1 M.2 NVMe (hot-pluggable) 2x SATA/NVMe M.2 connector (onboard)
I/O	Embedded 2x1GbE networking ports Up to 2 x16 PCIe Gen5 Up to 1 x16 OCP slot
Storage controller	HPE ProLiant Gen11 controllers (PCIe and OCP) + VROC NVMe/SATA
Management	HPE iLO 6
Chassis depth (GPU front end)	30.4″ / 772 mm