The iG500 offers machine learning at the edge. The system is designed based on NVidia TX2 SoM (System on Module). Jetson TX2 is the fastest, most power-efficient embedded AI computing device. This 7.5-watt supercomputer on a module brings true AI computing at the edge. It’s built around an NVIDIA Pascal™ family GPU and loaded with 8 GB of memory and 59.7 GB/s of memory bandwidth.

iG500 ingest signals from cameras, LIDARs, ultrasonic, RF or analog to digital converters. It then decode and apply machine learning algorithm such as Caffe, Torch, TensorRT or TensorFlow. After completing machine learning algorithm, it displays the image processing or provide signal to an actuator or connect to other systems. It fits perfectly within NybSys IoT product portfolio.

It can be used in mass public transit system, farming and agriculture system, smart city and traffic control system. In manufacturing it can be used for industrial automation and manufacturing flow control. In retail and warehousing it can help in theft detection, object classification and movement detection.

iG500 offers unique opportunities to apply already trained models at the edge to perform inference at the edge. It can be used for Image recognition and classification, objection and localization, segmentation and free space visualization, complex event processing. The iG500 have industrial standard DIN rail enclosure with 6 Port ethernet switch for connecting sensors and cameras and 2 SFP module for uplinks. Failover DC power supply units are provided for high availability.