Imaging company FLIR Systems has launched what it says is “the industry’s first” deep learning camera for applications ranging from industrial inspection to autonomous driving and others.
FLIR says the Firefly DL enables systems designers to build neural networks that are capable of decision-making at the edge.
FLIR is believed to be the world’s largest commercial company specializing in the design and production of thermal imaging cameras, components and imaging sensors.
The new camera is one of the first to integrate deep learning, which is described as “a powerful too for system designers to quickly automate complex and subjective decision making and deliver higher quality products and improved productivity”.
The Firefly DL is said to be capable of facial recognition and determining the quality of products such as a solar panel. It also integrates the Intel Movidius Myriad 2 VPU to enable deep neural networks for on-camera inference.
James Cannon, president and CEO of FLIR, says: “Automated analysis of images captured by machines is a key part of our day-to-day lives that few of us think about.
“The quality, affordability, and speed-to-market of items like our smartphones or the food on our tables are made possible by systems using cameras doing both inspection and automated production.”
FLIR says system designers can deploy their trained neural network to the FLIR Firefly DL with Neuro technology and reduce system cost and complexity by making decisions on-camera without host PC.
The company adds that, with its very small size – 27x27x14mm, low weight – 20 grams, and low power consumption, the Firefly DL camera is “ideal for embedding into mobile, desktop, and handheld systems”.