Foxconn,  Socionext and Hailo have combined to pursue video analytics at the edge. 

Foxconn’s 24-core miniserver BOXiedge has been combined with Socionext’s parallel processor SynQuacer SC2A11 and the Hailo-8 deep learning processor.

The combination delivers standalone AI inference nodes.

The product is capable of processing and analysing over 20 streaming camera input feeds in real-time, all at the edge.

The result is a high-density, low-power, complete local VMS server, ensuring top performance for video analytics and privacy, including image classification, detection, pose estimation, and various other AI-powered applications – all in real time.

Foxconn has already deployed several in-house developed AI solutions on different production lines, leading to an improvement in reporting accuracy from 95% to 99% and a reduction of at least one third of the operating costs for appearance defect inspection projects. 

The Hailo-8 deep learning processor delivers up to 26TOPS. The chip is built with an architecture that enables edge devices to run deep learning applications that could previously only run in the cloud.

The BOXiedge AI computing solution is equipped with applications for a broader market relying on low latency, a high data rate, high reliability, and quick processing at the edge.

Smart retail and smart cities, for instance, require hundreds of cameras – either in-store or in traffic monitoring – to generate video streams that need to be processed locally, quickly, and efficiently with minimal latency.

Similarly, for industrial IoT, where every split-second counts, data acquiring, processing, inferencing, and presenting on the production floor rather than in the cloud translates into significant cost savings along with more efficient processing for tasks such as inspection and quality assurance.