Adlink has expanded its artificial intelligence (AI)-enabled Video Analytics (AVA) platform portfolio of edge solutions with the addition of AVA-RAGX.
The new platform is built on the latest industrial version of Nvidia’s Jetson AGX Xavier module and comes with rugged capabilities for both onboard and wayside railway deployment.
Adlink is targeting AVA-RAGX for use in edge-type railway applications such as railroad hazard detection, onboard passenger security, railroad intrusion detection, and train station video surveillance.
“AI is accelerating the digital transformation of the railway industry to improve operational efficiency, deliver smarter and safer customer services, and create new business opportunities,” explained Eric Kao, General Manager of Adlink’s Networking, Communication & Public Sector business unit.
From a technical standpoint, the new solution measures just 288 x 190 x 72 mm and features an 8-core Nvidia Carmel CPU and a 512-core Nvidia Volta GPU, together with four M12 Gigabit ports, wireless connectivity (5G/LTE & Wi-Fi), four digital input, and four output 24VDC-110VDC with 1.5kV isolation.
AVA-RAGX can be integrated within advanced camera systems, radar and Lidar systems, GNSSC, and AI software stacks to provide precise information about the train’s surroundings and exact position, including the long braking distance of the train.
In these cases, the solution’s hazard detection capabilities can improve operational efficiency and safety and help prevent accidents, particularly when trains run at night or in adverse weather conditions with reduced visibility.
“Adlink is at the forefront of AI computing solutions that help railway companies focus on differentiating and transforming their end applications,” Kao added.
The AVA-RAGX can also be on an inspection train, with its trackside equipment fault detection system automatically processing images captured in real-time from wayside equipment, such as the pantograph and track.
Thanks to Nvidia’s GPU accelerated computing, the system can reportedly identify potential equipment faults at a train speed of up to 75mph (120km/h).
According to Adlink, integrating AVA-RAGX’s AI-at-the-edge into onboard legacy CCTV networks not only enhances passenger travel conditions, but also safety, thanks to its real-time video analysis of suspicious or aggressive human behaviors, crowd movement, and face mask-wearing capabilities.
“The introduction of the AVA-RAGX is a significant addition to our rugged, AI-enabled Video Analytics platform portfolio for the rail industry,” Kao said.
“More importantly, it demonstrates how Adlink’s Elite partnership with Nvidia can accelerate our product development with the unique access to Nvidia’s latest GPU technologies and the highest level of technical support.”
Adlink is an Nvidia Quadro Embedded Partner, OEM Preferred Partner, and Jetson Elite Partner. Before AVA-RAGX, the companies jointly released a MEC edge server in October 2020. More recently, Adlink joined the O-RAN ALLIANCE as a Community Member.
ADLINK | edge AI | industrial edge | Nvidia | railway | transportation safety