EOS-J SeriesNVIDIA® Jetson TX2-based Vision System Features • Integrating NVIDIA® Jetson TX2, frame grabber, and industrial I/O • Supports ADLINK GigE, USB3 and other PCIe-based frame grabbers • Industrial isolated 32CH DI/O • 256 core Pascal NVIDIA® GPU supports Deep Learning Inference • ARMv8 (64-bit) multi-processor CPU complex for heterogeneous multi-processing Introduction ADLINK's EOS-J vision system integrates the NVIDIA® Jetson TX2, frame grabber, and industrial DI/O in a compact package, serving machine vision applications at the edge. Addressing problems that can't be solved by other rule-base algorithms, EOS-J is equipped with the NVIDIA® Jetson TX2 and also supports GigE, SUB3 and other PCIe based frame grabbers to solve problems by using Deep Learning. By integrating the Jetson TX2, the EOS-J provides 256 CUDA cores and ARM Cortex-A57 processors, enabling robust Deep Learning inference, empowering defect inspection and object classification requirements in manufacturing environments. A neural model optimized by NVIDIA® tools like Digits or TensorRT can be deployed on the EOS-J directly, easing development of user-specific machine vision solutions. The EOS-J provides an Ethernet port and two communication ports, and a HDMI output for maximum integration in the field. Software Support • Ubuntu • Open GL, CUDA Ordering Information • EOS-J-GigE 4CH GigE vision system with 32CH isolated DI/O • EOS-J-USB3 4CH USB3 vision system with 32CH isolated DI/O

Leading EDGE COMPUTING www.adlinktech.com All products and company name listed are trademarks or trade names of their respective companies. Updated Feb. 22, 2019. ©2019 ADLINK Technology, Inc. All Rights Reserved. All specifications are subject to change without further notice.