The heavy requirements of real-time vision processing have continuously pushed computing towards the edge where accelerated decision-making capabilities have created exciting opportunities for intelligent solutions. Intel’s Openvino toolkit accelerates development, enabling quick integrations of pretrained models (e.g. Tensorflow, Caffe, etc.) for object recognition, classification and facial recognition in vision-based solutions.

Lanner’s modular approach to network appliances provides a clear path for engineers looking to optimise their neural processing workloads using Intel’s Vision processing units integrated through standard mini-PCIe expansion slots. This form-factor improves hardware-software integration and resilience in rugged, embedded and mobile applications where protruding dongles are less than ideal.

“Intel’s Myriad X VPU and Openvino software development toolkit for accelerated vision AI simplify the creation of low-power, real-time video analysis. Lanner’s expertise in creating effective purpose-built hardware platforms is leveraged here to provide a full-package hardware solution that tackles the specific requirements of vision-based edge systems,” said Attilio Belenchia, Director Business Development of LEI Technology, a division of Lanner Electronics. “Creating reliable edge solutions for existing vision-based systems/cameras has never been easier— Intersections, traffic-stops, checkpoints, parking lots, entrances and remote stations can all harness edge vision processing for automation, optimization and assisted remote management."