AI cameras to detect violence on Sydney trains

CCTV cameras on Sydney’s heavy rail network will be augmented with artificial intelligence over the next six months to automatically detect and report suspicious and violent incidents.

Transport for NSW plans to trial the technology to analyse footage captured by the cameras, as part of a new initiative to improve safety for women travelling on public transport at night.

It is just one of four winning ideas from the Safety After Dark Innovation Challenge, which offered applicants equity-free seed funding and support through TfNSW's digital accelerator.

Researchers from the University of Wollongong’s SMART Infrastructure Facility pitched the AI software, which can automatically analyse real-time camera feeds and alert operators.

“The AI will be trained to detect incidents such as people fighting, a group of agitated persons, people following someone else, and arguments or other abnormal behaviour,” SMART lecturer and team lead Johan Barthelemy said.

“It can also identify an unsafe environment, such as where there is a lack of lighting.The system will then alert a human operator who can quickly react if there is an issue.”

PhD student Yan Qian, who will be assisting Barthelemy on the project, said open source code will be used to “estimate the poses of a human being and predict if there’s a fight”. 

“The incident will then be reviewed by a human controller who will accept or reject the suggestion made by the AI,” Qian said.

“In this way, the program will become smarter, learning in a similar way to a human being.

“As far as we know, nothing like this has been attempted globally. We are pushing the limits of the technology.”

Other winning projects include a project pitched by data sharing platform She’s a Crowd to use datasets and algorithms to create public transport routing that prioritises safety.

A new platform for public safety and assistance, pitched by safety technology experts Guardian LifeStream and Cardno/UNSW, will also be trialled. 

Transport Minister Andrew Constance said the “winners were chosen for their potential to meaningfully address real safety issues” using “creative and sophisticated new technologies”.

“We want all our customers to feel safe on the network and it is not good enough that 9 out of 10 Australian women experience harassment on the street and modify their behaviour in response,” he said.

“We’re excited to be working with entrepreneurs and universities to implement innovative technology solutions to keep women safe.”