A camera system that uses artificial intelligence may be able to help bus drivers avoid hitting cyclists and pedestrians in their blind spot.
The camera system is called Intent Prediction technology and is being readied for public bus routes.
The Evening Standard reports that Human Autonomy’s technology is able to spot hazards two seconds faster than the human brain and that it can ‘predict’ random manoeuvres and what crowds of rush-hour cyclists and pedestrians might do next.
Scientists are said to have programmed deep-learning software, a branch of AI, to spend two years studying tens of thousands of hours of human reactions from dashcam videos as well as test vehicle footage from the West End, Shoreditch and Outer London.
According to the Evening Standard the driver assistance software, programmed using the Linux operating system, works inside the bus’s existing video cameras that monitor the outside of the vehicle.
Every person that the cameras sees is assigned a ‘risk index’ as pedestrians and cyclists are classified as ‘vulnerable road users’. Another movement category that would be flagged to the driver is ‘intention to cross’, with an alert to take evasive action coming from illuminated dashboard icons.
Raunaq Bose, Human Autonomy’s co-founder, told the Evening Standard, ‘Intent prediction shows not only where the cyclist is but if they are likely to move in front of your path. It helps with blind spots and people coming out into the road at random times.’
‘We’re able to tell if someone is aware of the vehicle or not, if they’re distracted, whereas current systems can just look at their position in the road. It pays attention to the subtle, nuanced motion and body language of pedestrians and cyclists.’
‘Tests found that in central London, where there are many more pedestrians and cyclists on the street, they are less likely to listen to the rules,’ concluded Bose.