Industry’s First Deep Learning-Enabled Machine Vision Camera

Posted Dec 04, 2018 by FLIR Systems, Inc.

FLIR Systems recently introduced the industry’s first deep learning inference-enabled machine vision camera, the FLIR Firefly. It integrates the Intel Movidius Myriad 2 Vision Processing Unit (VPU) and is designed for image analysis professionals using deep learning for more accurate decisions, and faster, easier system development.

Whereas traditional rules-based software is ideal for straightforward tasks such as barcode reading or checking a manufactured part against specifications, the FLIR Firefly combines a new, affordable machine vision platform with the power of deep learning to address complex and subjective problems such as classifying the quality of a solar panel or recognizing faces. It leverages Intel’s advanced capabilities in a 27 mm x 27 mm x 14 mm, 20 gram and low 1.5 W power camera, ideal for embedded and handheld systems.

The camera family uses the Intel Movidius Myriad 2 VPU’s advanced capabilities, ideal for embedded and handheld systems. Machine makers can load their trained neural networks directly onto the Firefly’s integrated VPU. Additionally, Intel Movidius Neural Compute Stick users can easily deploy their existing networks directly onto the Firefly. This unique design reduces system size and improves speed, reliability, power efficiency, and security.