In order to set up a fully comprehensive embedded edge vision system, companies today are subject to complex integration processes that require expert knowledge of hardware, software and cloud services. The resulting system is often geared towards a specific application and is often not flexible enough to accommodate new use cases. Therefore, industrial companies need a reduction in technical complexity and the flexibility of a vision-based platform that can be customized for different AI/ML models.

Basler's AI platform for machine vision bridges the gap between cloud services and local machine vision. It integrates vision hardware and edge computing with cloud services to provide end-to-end machine learning solutions. With the integration of the AWS Panorama Device SDK, the Basler platform enables the use of a unified architecture to address different application areas.

Basler's AI platform for machine vision includes a 5 MP Basler ace camera with GigE interface. The edge computing unit will be equipped with the NVIDIA Jetson TX2NX module, which offers 1.33 TFLOPs of AI performance. The machine vision platform integrates Basler's pylon Camera Software Suite, which is compatible with the AWS Panorama SDK. The integration of AWS Panorama enables the implementation and execution of AI/ML applications on edge devices and also offers the possibility to constantly check the quality of inference through centralized device management. Different use cases can also be addressed flexibly through the use of ML models. With Amazon Lookout for Vision, for example, customers can create machine learning models to visually detect anomalies such as product defects and automate quality checks. More details on the product and further possible applications will be published in the third quarter of 2021.