Partnership to develop self-drive computer vision

A new partnership between Australian data innovation group CSIRO’s Data61 and Chinese self-driving technology company ZongMu Technology aims to avoid pedestrian and vehicle collisions by using computer vision.

Data61 says one of the largest technical challenges in autonomous driving is giving vehicles ‘human’ sight,

The Smart Vision Systems Group at Data61, led by Dr Nick Barnes, will work with ZongMu to develop algorithms to estimate the space between objects according to the vehicle’s motion and predict the potential hazards of moving objects.

The self-driving vehicle market is expected to rise from US$42 billion (NZ$57b) in 2025 to nearly US$77 billion (NZ$104b) by 2035, as more organisations compete to develop a truly autonomous Level 5 vehicle that can do all tasks.

“Computer vision is the technology that allows autonomous vehicles to determine the difference between what is pavement and what is a drivable road,” Barnes says.

“Unlike laser sensors which rely on a series of points to identify hazards, computer vision offers richer information and a deeper understanding of road scenes through 3D image analysis, enabling safer automated driving.”

The technology will allow autonomous vehicles to quickly react to any hazards about 10 metres or further away to avoid collisions, Data61 senior research scientist Dr Shaodi You says.

“The laser sensors used by the majority of companies are prohibitively expensive.

“On the other hand, the computer vision algorithms we’re developing with ZongMu cost one-tenth the amount and will allow commercial and truly autonomous cars to reach the road in a much shorter time frame.”

Data61 will work with ZongMu from research through to development, with the final product available to the company’s customers in China and internationally, including OEMs and partners in the mobility service industry.