Vizi-AI LEC-AL-E3940-AI-4G-32G/US ADLINK Technology

Datasheet ADLINK Edge Vizi-AI An industrial standard form factor SMARC2.0 - developer kit with on-board industrial software to make machine vision simple. Create your Machine Vision AI Solution in minutes. Add your Intel OpenVINO model or use one of the pre-packaged options. Use ADLINK Edge software to manage remotely for demos/solutions in the field. Supported by the goto50.ai community for knowledge sharing, ideas and problems. Come and join us. ModelName Vizi-AI System Specification CPU Intel Atom x5-E3940 SOC VPU Intel Movidius VPU Myriad-X Memory 4GB LPDDR4 Storage 1 x MicroSD for external storage Video/Audio HDMI 1x HDMI LVDS/eDP Optional single channel on flat cable Network Ethernet 1x Gb Ethernet full speed RJ-45 I/O USB USB 3.0 x2, USB 2.0 x2, USB 2.0 Client x1 MRAA compliant 40 pin connector GPIO, PWM, 12C, RS232,SPI Power Standard input 12V (110/220V 2.5A adapter for US or EMEA) Software Operating System Linux (Debian 9.9) ADLINK ADLINK Edge Vision Software Stack Vizi-AI Power Adapter US/EU Included in thebox Micro SD Card with Vizi-AI Software GOTO50.ai community Image on Debian Linux website for info and support *Software download requires internet connection *Camera not included ADLINK COPYRIGHT Last updated: September 2020Datasheet ADLINK Edge Vizi-AI ADLINK Edge Software Suite Apps Profile Builder The ADLINK Edge Profile Builder manages the deployment and operation of the Vizi-AI solution. Stream Viewer Receives video frames and inference results from the Data River and combines them into a single video stream that can be viewed with the Profile Builder or an RTSP Viewer Frame Streamer Streams video from an attached camera e.g. USB web cam or from an on- device video file Intel OpenVINO Inference Engine Reads live video frames from the ADLINK Data River passing them through the user-defined AI inference model and publishes the results back into the Data River in real-time Model Manager Facilitates AI inference model deployment by storing models locally for Intel OpenVINO inference engine to load via the ADLINK Data River. Models can be uploaded to the Model Manager via the Profile Builder application. Training Streamer Facilitates the capturing of images for the purposes of training AI models. Images can be captured to a local file system and/or can be uploaded to an FTP/SFTP server. Node-RED Reads inference results from the ADLINK Data River and takes action in real- time based on what the user graphically modelled using the Node-RED framework ADLINK COPYRIGHT Last updated: September 2020