ADLINK launched its AVA-RAGX AI-enabled video analytics platform targeting next-generation railway solutions including, passenger security, hazard detection and railroad intrusion detection.
Built on the industrial version of Nvidia’s Jetson AGX Xavier module, the AVA-RAGX provides a compact, rugged AI-enabled solution for both onboard and wayside railway applications that delivers reliability and performance in harsh operating environments. Along with other AVA platforms within ADLINK’s portfolio, the new AVA-RAGX offers rail solution providers a high level of flexibility to select the configuration best suited to their application. Target railway applications include railroad intrusion detection, train station video surveillance, onboard passenger security, and railroad hazard detection.
Eric Kao, general manager of ADLINK’s networking, communication & public sector business unit, said, “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. The introduction of the AVA-RAGX is a significant addition to our rugged, AI-enabled video analytics platform portfolio for the rail industry. 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 said it’s partner status with Nvidia meant it had permission to build chip-down GPU solutions for ruggedized embedded markets. In addition, ADLINK was able to leverage access to advanced processing technologies and technical support, driving open standards-based heterogeneous computing solutions for next-generation AI and machine learning applications.
The AVA-RAGX platform is suited to real-time video and graphics analysis applications in today’s increasingly complex railway operations. With an 8-core Nvidia Carmel CPU and a 512-core NVIDIA Volta GPU, the platform shows ADLINK’s expertise in developing next-generation railway systems. Combining AI, machine learning, edge computing and IoT technologies and certified to EN 50155 specifications, the AVA-RAGX is a rugged, fanless and compact platform designed for flexible deployment in harsh operating environments.
With its compact 288 x 190 x 72 mm dimensions, the AVA-RAGX specifically targets space-restricted environments, making it ideal for edge-type railway applications with small solution enclosures. It provides a full complement of I/O ports, including four M12 Gigabit ports and wireless connectivity (5G/LTE & Wi-Fi), as well as four digital input and four output 24VDC-110VDC with 1.5kV isolation.
When integrated with an advanced camera system, radar, Lidar, GNSSC and AI software stack, the AVA-RAGX system can provide precise information about the train’s surroundings and exact position. A challenge particular to the rail industry is the long braking distance of the train. The AVA RAGX can detect emerging hazards far ahead to increase warning time when connected to appropriate sensors. Also, the hazard detection system can improve operational efficiency and safety and helps prevent accidents, especially when trains run at night or in adverse weather conditions that reduce visibility.
When installed on an inspection train, the trackside equipment fault detection system processes images captured from wayside equipment, such as the pantograph and track, in real-time. Driven by Nvidia’s GPU accelerated computing, the system can effectively identify potential equipment faults at a train speed of up to 75mph (120km/h).
Incorporating AI-at-the-edge into onboard legacy CCTV networks enhances passenger travel conditions. Instead of relying on CCTV playback footage, the AVA-RAGX can perform real-time monitoring. Applications include checking for unattended luggage, seat occupancy, and passenger counting. When deployed in train station surveillance systems, the AVA-RAGX can analyze the real-time video stream received from station platforms to detect suspicious or aggressive human behaviors, crowd movement and even face mask-wearing.
- Meeting the computational needs of real-time AI
- Microsys and Hailo offer new edge-server grade AI platform
- German Bundesliga extends AWS ML to broadcast player efficiency data