Advantech Launches its Comprehensive AIR Edge AI Inference Systems for AI and Vision Analytics Applications
Taipei, May, 2020 – Advantech (stock code: 2395), a global leader in IoT, launches its comprehensive AIR series AI inference systems from light weight to high performance to address various AI applications including retail facial recognition, AOI/vision inspection, robotic, intelligent transportation and more. The offerings include AIR-100, AIR-101, AIR-200 and AIR-300 with different featured designs to fit diverse AI applications. Advantech also provides Edge AI Suite, a software toolkit with easy-to-use graphic user interface (GUI) and pre-trained AI models to help customers enable AI inference on edge devices.
Built for Edge AI: Enable Real-time Intelligence on Diverse Applications
AIR series includes AIR-100, AIR-101 and AIR-200 which integrated Intel Movidius Myriad X VPU, and AIR-300 which supports a PCIe x16 high power graphic card. Powered by Intel® Atom® x7-E3950 CPU and one Intel® Movidius™ Myriad™ X VPU, AIR-100 supports multi-4K display and is suitable for interactive kiosk, white board or other retail applications with facial recognition functions. AIR-101 supports DIN-Rail design and 12V~28V wide-range power input with Intel Atom® E3940 Quad Core processors and two Intel® Movidius™ Myriad™ X VPUs and is perfect for AGV and factory automation applications. For higher computing power needs, AIR-200 is an Intel® Core™ i5 platform with two Intel® Movidius™ Myriad™ X VPUs and supports up to 1080p video encoding, decoding and multi-channel processing suitable for traffic monitoring, license plate recognition and vehicle classification applications. The powerful AIR-300 supports Intel Xeon E3/ 7th & 6th generation Core i series processor and a PCIe x16 high performance graphic card to enable fast inference and on-premises training for robotics and optical inspection applications.
Accelerating AI Deployment with Edge AI Suite
Advantech’s AIR series AI inference systems comes with the Edge AI Suite software toolkit that integrates Intel® OpenVINO™ toolkit R3.1 to enable accelerated deep learning inference on edge devices and monitor real-time device status on the GUI dashboard. The latest Advantech Edge AI Suite v1.2 includes an optimized pre-trained Yolov3 object detection model popular in surveillance applications which delivers 2.8x better performance on VPU than running with OpenVINO™ only. Customers can use Edge AI Suite v1.2 to execute the Yolov3 model with VPU+GPU heterogeneous acceleration to get 5x better AI inference performance than using a single device.