25 Jul 2024


Smart industrial AI camera is first to use powerful new module

Adlink’s AI smart camera is said to simplify the deployment of edge AI vision and AIoT applications

Adlink Technology, the Taiwanese edge computing specialist, has launched the first smart camera to use a new Nvidia module which is claimed to perform more than ten times better than its widely-used predecessor. The AI-based Neon-2000-JNX camera eliminates the need for complex integration of image sensor modules, cables and PCs. The compact, rugged all-in-one device is designed to simplify the deployment of smart cameras and to speed up time-to-market.

The camera is based on Nvidia’s Jetson Xavier NX system-on-module (SOM) for industrial AI inference which is claimed to be at least ten times more powerful than its earlier Jetson TX2 module. The compact camera is said to simplify the development of AI vision systems for manufacturing, logistics and other edge applications.

“Until now, a typical AI vision solution required a complex integration of the image sensor module, cables and GPU modules,” explains Kevin Hsu, senior product manager of Adlink’s IoT Solutions and Technology business. “This ready-to-develop edge AI smart camera reduces the effort of software/hardware integration and reliability validation, allowing AI vision developers to focus on application development.

He describes the new camera as “a hassle-free, compact, reliable and powerful product for edge AI applications, and also the best match for AI software providers”.

“AI-driven machine vision is reshaping entire industries from robotics and retail to healthcare, manufacturing and more,” adds Murali Gopalakrishna, Nvidia’s head of product management for autonomous machines, and general manager of its robotics business. “With the Adlink smart camera kits powered by the Jetson edge AI platform, developers get an integrated, easy-to-deploy solution for AI vision-based embedded and industrial AIoT applications.”

The camera comes with a new edge vision analytics software kit, called the EVA SDK (Edge Vision Analytics Software Development Kit), creating a platform that is said to cut proof-of-concept (PoC) timescales and to speed time-to-market. Adlink says that even newcomers to AI can focus on the application and build a proof-of-concept in as little as two weeks.

There is a choice of field-ready application plug-ins and AI models said to simplify building AI vision applications, with limited coding being needed. A preview function makes the verification of AI inference flow and results quick and intuitive.

The new camera:
● supports six sensor configurations from 1.2-8 Megapixels to deliver raw data and complete image detail for machine vision;
● uses two new image sensors that reduce CPU loading and allow higher operating temperatures;
● incorporates an image signal processor that provides enhanced and environment-adaptive imaging to improve AI accuracy; and
● tackles common reliability issues including EMC/EDS/vibration/thermal problems, interface compatibility, and image drops caused by faulty camera and OS settings.

AdlinkTwitter  LinkedIn  Facebook