Skip to main content

Flir debuts new deep learning Firefly camera

At this year’s Vision show, Flir debuts the world’s first industrial camera supporting on-camera inference. The new Flir Firefly camera combines the best of machine vision with the power of deep learning. At just 27mm x 27mm x 14mm, 20 grammes weight, and 1.5W power consumption, it is ideal for portable devices. Excellent imaging is provided with the latest global shutter CMOS sensors, the company says. And, Flir adds, with its integrated Intel Movidius Myriad 2 vision processing unit (VPU), users deploy th
October 25, 2018 Read time: 1 min
At this year’s Vision show, 6778 Flir debuts the world’s first industrial camera supporting on-camera inference. The new Flir Firefly camera combines the best of machine vision with the power of deep learning. At just 27mm x 27mm x 14mm, 20 grammes weight, and 1.5W power consumption, it is ideal for portable devices. Excellent imaging is provided with the latest global shutter CMOS sensors, the company says. And, Flir adds, with its integrated Intel Movidius Myriad 2 vision processing unit (VPU), users deploy their trained neural network directly onto the camera to achieve inference on the edge.   


Stand: 1B42

For more information on companies in this article

Related Content

  • Flir Academy training courses
    January 7, 2016
    FLIR Traficon Academy is organising a variety of online training in January 2016, including ITS solutions for traffic management and Flir ThermiCam, where participants can learn how its ThermiCam/TrafiSense sensor can be used for pedestrian presence detection, bicycle presence detection, vehicle presence detection, inverse direction detection, and data collection. The company is also offering traffic training on intersections and crossings in May. Visit the Flir website for more information on the ran
  • Getting to the point
    September 4, 2018
    Cars are starting to learn to understand the language of pointing – something that our closest relative, the chimpanzee, cannot do. And such image recognition technology has profound mobility implications, says Nils Lenke Pointing at objects – be it with language, using gaze, gestures or eyes only – is a very human ability. However, recent advances in technology have enabled smart, multimodal assistants - including those found in cars - to action similar pointing capabilities and replicate these human qual
  • GridMatrix goes back to the future in New York City
    September 25, 2023
    Legacy traffic management infrastructure doesn’t have to be a marker of the past: software upgrades can bring it into the present in a cost-effective and timely way, says Gordon Feller
  • World launch by Lector Vision
    February 19, 2018
    Lector Vision, an international specialist in artificial vision that enables a wide range of applications in the traffic and transport sector, will use Intertraffic Amsterdam 2018 for the world launch of two innovative new products – the Cube camera and Traffic Guard, a ground-breaking software analytics development that was funded by the Spanish government. The company’s Cube camera was developed in-house at Lector Vision’s Madrid headquarters and has a wide range of applications, including tolling