2020.10.15

Video Analytics – Fine Tuning for Big Gains

Share:

ALL_news_tech_blog_26A07_xpXErIijiW

Video Analytics – Fine Tuning for Big Gains

AEWIN has been working hard to provide highest performance out of your hardware investments. We’ve been tasked to provide GPU accelerated MEC edge servers for video analytics application. Specifically for accelerated live traffic monitoring, which utilizes NVIDIA T4 to decode live video feeds and perform AI inferencing to detect traffic patterns by different types of vehicles, collisions, traffic violations, license plates, and other useful metrics.

This seems like an easy task for servers to handle. However, not all servers are created equal. Off the shelf servers are typically optimized for various different workloads, making it jack of all trades and master of none. Our MEC servers and engineers have been steadily focused on maximizing GPU acceleration performance. We received customer praise due to our ability to handle 24x full HD live streams compared to their previous system which is only able to process 18 streams utilizing similar setup. Through continued testing and fine tuning, we’ve exceeded the performance of some of the biggest names in the server space and closely matching the benchmark published by NVIDIA.

ResNet-Inference-Test

Table: Resnet-50v1.5 + TensorRT Inference Test
*Test setup: SCB-1921 MEC version + 2x Nvidia T4 vs published numbers by Nvidia and competitors

This is the difference between going with a general purpose server from other manufacturers versus AEWIN. Through personalized collaboration, it enable us to fine tune performance of the servers and GPU for your specific workloads. Our flexible manufacturing, which is located right next to our engineering/headquarters right here in New Taipei City, allows us the flexibility to work with customers from smaller scale projects to large. Our experienced engineers are available and can offer insights and give recommendations for system configs. Make sure to bring your projects to AEWIN before deciding on your next GPU accelerated platform and see how AEWIN can help you get the most performance out of your investment.

SCB-1921
Edge Computing Server

一張含有 電子產品, 螢幕擷取畫面, 機器, 設計 的圖片

AI 產生的內容可能不正確。

  • Support Dual 2nd Gen Intel Xeon Scalable Processors
  • Support 2933MHz System Memory
  • 4x PCIe x8 for Network Expansion Module, plus 4x PCIe x8 or 2x PCIe x16 for GPU or FPGA

 

Related News

Enabling Agentic AI in Cybersecurity with On-Prem Infrastructure
2026.04.08

Enabling Agentic AI in Cybersecurity with On-Prem Infrastructure

Agentic AI in cybersecurity is rapidly transforming traditional defense into an autonomous, real-time defense solution. As security systems gain the ability to independently detect and respond to threats, infrastructure must evolve to support instant data processing and decision-making. This shift is driving the need for on-prem AI infrastructure, positioning edge servers, and network appliances as critical enablers of next-generation cybersecurity.

AEWIN Has Completed 2025 Carbon Footprint Verification
2026.03.18

AEWIN Has Completed 2025 Carbon Footprint Verification

As sustainability becomes a global priority, organizations are expected to better understand and manage their greenhouse gas (GHG) emissions. Carbon footprint verification helps quantify emissions, identify key sources, and support long-term reduction planning. As part of its ESG commitment, AEWIN conducts annual carbon footprint verification to ensure transparent reporting and responsible environmental management.

Scalable Storage Infrastructure for AI-Driven Data Management
2026.03.04

Scalable Storage Infrastructure for AI-Driven Data Management

As data grows exponentially and AI adoption accelerates across enterprise, cloud, and edge environments, massive datasets must be processed, moved, and retained efficiently. Training, inference, and real-time analytics require storage infrastructure that delivers performance consistency, excellent efficiency, and scalability. To support AI-driven data management, storage servers must be architected not only for capacity expansion, but for throughput stability, system resilience, and overall reliability across dynamic data environments.

Inquiry Cart

total 0 items

Compare

total 0 items

Email Subscribe

Verification

Click the numbers from smallest to largest.

We use cookies to allow our website to work properly, personalize content and advertising, provide social media features and analyze traffic. We also share information about your use of our site with our social media, advertising and analytics partners

Manage Cookies

Privacy Settings

We use cookies to allow our website to work properly, personalize content and advertising, provide social media features and analyze traffic. We also share information about your use of our site with our social media, advertising and analytics partners

Privacy Policy

Manage Consent Settings

Essential Cookies

Accept All

The website cannot function without these cookies and you cannot switch them off on your system.

These cookies are typically set only in response to an action you perform (i.e. a service request), such as setting privacy preferences, logging in, or filling in a form.

You can set your browser to block or prompt you for these cookies, but this may prevent some site features from working.