Seeing Machines, based in Canberra, Australia, is a company of experts in human-machine interaction and the artificial intelligence (AI) technologies which enable machines to see, understand and assist the people who are using them—see their demo video.
Seeing Machines’ approach is not to read driver posture or keep track of hands-on-wheel, but to understand diver attention, to virtually look into the driver’s mind.
Their FOVIO Driver Monitoring (FDM) processor employs computer vision algorithms that have been developed over more than 20 years of applied research. The FDM processor sits at the heart of an infrared camera-based DMS (Driver Monitoring System). It offers qualitative measurement of all the levels of driver impairment and engagement, with algorithms that have been calibrated against diverse population studies, examining the ability of drivers to safely control vehicles in complex road environments when in known mental states.
The camera’s dynamic sensor and illumination are controlled by the FDM monitoring algorithms. This tight coupling between algorithm and optics enables the DMS system to track a person’s eyelids and pupils through sunglasses under every imaginable real-world driving condition.
“As vehicles become more automated and until they are capable of handling the driving task 100% of the time, there will always be a requirement for the vehicle to initiate handover back to the driver,” says Seeing Machines CEO Paul McGlone. “In order for that handover to be conducted effectively, the vehicle must be able to register the attention state of the driver and react accordingly.”
They say a camera-based DMS enables visual attention—the best current available predictor of driver engagement—to be measured, and it can measure this continually, without requiring the driver to perform any unnatural movements unrelated to the driving task.
