ADLINK Launches NVIDIA Jetson Xavier NX-based Industrial 4-channel PoE AI Vision System

By Tiera Oliver

Associate Editor

Embedded Computing Design

March 23, 2022


ADLINK Launches NVIDIA Jetson Xavier NX-based Industrial 4-channel PoE AI Vision System

ADLINK Technology launched the new 4-channel GigE NVIDIA Jetson XavierTM NX-based Edge AI Vision Inference System, EOS-JNX series, featuring Smart PoE (Power over Ethernet) and PoE loss detection, dedicated GigE bandwidth, and 100m GigE cable non-drop frame capture

The solution designed for PoE camera-based applications with high image quality, offering management and maintenance. The EOS-JNX series is a hassle-free, compact, reliable, and fully integrated vision system for all Edge AI applications, processing real-time visual intelligence at the edge with ideal hardware design and ready-to-deploy, EVA SDK software tools.

The EOS-JNX series line-up now includes the EOS-JNX-I and EOS-JNX-G models supporting Onvif and GigE protocols. The EOS-JNX-I can be integrated into existing surveillance systems with its embedded Uplink port enabling edge AI safety capabilities with minimal change and investment. ADLINK is now also partnering with surveillance camera providers to bring AI surveillance starter kits to the smart city market segment. The EOS-JNX-G’s dedicated GigE bandwidth allocated capability can help AI developers upgrade their Automated Optical Inspection (AOI) solution into an AI based solution. The EOS-JNX-G serves industry applications including industrial inspection and food and beverage classification.

Moreover, with 100m cable validation, the EOS-JNX series is designed to eliminate compatibility and reliability issues. This allows AI developers to apply AI inferencing with their image source, whether from surveillance cameras or industrial GigE cameras. 

The exclusive ADLINK Edge Vision Analytics SDK (EVA SDK) offers five essential manufacturing scenarios and AI software partner-friendly integration architecture for future-proof AI-based vision applications across industrial safety, food and beverage, and smart manufacturing industries. Per the company, AI developers, even newcomers to AI, can focus on applications and training, and build a proof-ofconcept (PoC) in as little as two weeks.

From March 21-25, at this year’s 2022 GTC conference, ADLINK will be sharing top design considerations for Edge AI solutions, and tips on deploying proof-of-concept AI models with tools like EVA SDK.

For more information, visit:

Tiera Oliver, Associate Editor for Embedded Computing Design, is responsible for web content edits, product news, and constructing stories. She also assists with newsletter updates as well as contributing and editing content for ECD podcasts and the ECD YouTube channel. Before working at ECD, Tiera graduated from Northern Arizona University where she received her B.S. in journalism and political science and worked as a news reporter for the university’s student led newspaper, The Lumberjack.

More from Tiera