Metavision from Prophesee is a machine vision system that uses event-based vision to capture and record movement.


  • Increased efficiency
  • Continuous data collection
  • Reduced energy use
  • Operable in poor and variable lighting


  • Machine learning
  • Autonomous driving
  • IOT devices

UN Sustainable Development Goals Addressed

  • Goal 9: Industry Innovation & Infrastructure

The Challenge

The conventional video camera takes an arbitrary number of frames per second, regardless of what motion it is trying to capture. When displayed rapidly, the images create an illusion of continuous motion, but between each individual frame, the camera is blind. Additionally, the camera repeatedly records background objects, creating an excessive amount of irrelevant data.

Innovation Details

Metavision® is a sensor that utilizes event-based vision to capture a continuous stream of information. If the camera is looking at a static scene it will generate no events, but if there is a burst of action, the camera adapts automatically to capture it instantly, similarly to the human visual processing system. Each pixel is recorded independently and is only recorded when it senses a change or movement. This makes it easier and more cost effective to acquire and analyze very fast motion, even if it is interleaved with times or areas in which motion is absent.

video thumbnail

Biological Model

The photoreceptors in our eyes only report back to the brain when they detect a change in some feature of the visual scene, such as its contrast or luminance. Evolutionarily, it is far more important for us to be able to concentrate on the movement of a predator within a scene than to take repeated, indiscriminate inventories of the scene’s every detail. This process allows human vision to collect all the information it needs, without wasting time and energy reprocessing images of the unchanging parts of the scene.