The core system is based on deep-learning computer-vision technology and transmits real-time information to monitors in the lifeguard tower, sounding an alarm when swimmers are in danger.
A new artificial intelligence-based (AI) lifeguard system aims to prevent drowning and monitor waterfront and coastal areas.
Sightbit has been developed by Ben-Gurion University of the Negev (BGU) alumni in Israel and aims to help lifeguards monitor thousands of swimmers and identify risky situations and other water hazards.
The system is already being used by the Israel Nature and Parks Authority along five miles of coastline in Palmachim National Park, creating what the developers claim is the first smart beach.
Deep learning computer vision
According to the World Health Organisation, there are an estimated 320,000 annual drowning deaths worldwide. Drowning is the third leading cause of unintentional injury death worldwide, accounting for seven per cent of all injury-related deaths.
The system uses standard cameras that cover a defined area and transmit real-time information on monitors in the lifeguard tower. It sounds alarms when swimmers are in danger. Instead of relying on binoculars, the cameras zoom in for an enhanced view.
The core system is based on deep-learning computer-vision technology with convolutional neural network architectures for object detection, which feature extraction and real-time predictive analytics.
“Our system acts as an additional lifeguard by flagging threats to swimmers and providing an earlier warning so they can act more quickly and save lives”
The system rates sections of a beach according to a risk assessment model with crowd management solutions and weather conditions, and offers estimates on how many lifeguards are needed on a given day to safely monitor swimmers. In addition to real-time alerts and water hazards, Sightbit analytics also enable lifeguards to anticipate risk and take preventative action before swimmers are ever in danger.
Sightbit also monitors certain at-risk populations such as child swimmers. The lifeguards can set the parameters of what warning alerts they see. Different options include dangerous currents, vessels (such as boats and jet-skis) and riptides.
“Sightbit is, in essence, an AI lifeguard and superior to humans which aren’t optimised for tracking hundreds of swimmers with or without binoculars,” said BGU alum Netanel Eliav, Sightbit chief executive officer. “In the case of drowning, every second is critical. Our system acts as an additional lifeguard by flagging threats to swimmers and providing an earlier warning so they can act more quickly and save lives.”
According to Amir Chen, director of Coastal Space and Parks Authority: “Sightbit’s innovative solution is in line with the Nature and Parks Authority’s ambition to ensure as much as possible the safety of travellers and visitors to the national parks and reserves using advanced and innovative technologies, among other things at the beach.”
The Sightbit team plans to expand internationally and has been invited to conduct additional pilots at beaches in the US and Europe.
Original post: https://www.smartcitiesworld.net/news/news/ai-based-lifeguard-system-aims-to-bring-smart-city-tech-to-the-beach-5534