Sightbit augments standard off-the-shelf cameras with software it says is based on deep learning and computer vision technology, with convolutional neural networks for object detection.

Sightbit’s system rates sections of a beach using a risk assessment model that considers how crowded the area is as well as weather conditions and then estimates how many lifeguards are needed on a given day.

The system issues real-time alerts for things like swimmers who appear to be struggling, while predictive analytics can help lifeguards anticipate risk and take preventative actions.

A single camera can be stretched to cover roughly 1,000 feet of shoreline, though an area this size is typically covered by three cameras.

“Sightbit warnings appear as flashing boxes around individuals and hazards,” says Eliav. “The lifeguard can click on the alert, and then the program zooms in … and sees exactly where the alert is.”

Sightbit’s system could fundamentally change lifeguarding practices, with watchtowers and binoculars replaced by screens and automated alerts.

However, the company isn’t pitching its service as a replacement for human lifeguards.

It’s more about augmenting current methods, including the cameras already being used on some beaches.

With Sightbit, lifeguards at a command center can continue monitoring with their naked eye while responding to alerts as they come in on their screen.

“Humans aren’t optimized for sitting in a tower and tracking swimmers,” says Eliav. “Sightbit is simply an assistant to the lifeguard to help them do their jobs even better. No lifeguard can watch all swimmers, all the time — but Sightbit can. And lifeguards cannot always see swimmers far off to the side of the tower. But Sightbit can provide extra vantage points.”

Lifeguards were consulted in the design process, and the system doesn’t require any special training.

A monitor displays a panoramic view of the water and the beach, similar to a security camera display, while a dashboard is superimposed over the video feed, and multiple views are available on a single screen.

Additional data can also be displayed, such as the number of people, weather conditions, and whether there are rip currents.

Each lifeguard can control which alerts and hazards they wish to see.

The technology could also help safeguard beaches when fewer lifeguards are available or could be used on stretches of coast that have no lifeguard service.

“Our software can pinpoint and track a swimmer’s location, and when necessary we can bring rescue tubes to swimmers in distress via small drones,” says Eliav.

Sightbit recently launched its first commercial pilot program at Israel’s Palmachim Beach, which claims more than a million visitors during the summer season, and is currently being used alongside five lifeguards.

While Sightbit’s technology could be deployed anywhere swimmers can be found — including pools — the company is initially targeting beaches, and is planning additional pilots on beaches across the U.S and Europe.

“Sightbit is focused on early detection of dangerous situations that can lead to drowning,” Eliav says. “The system will be able to detect these situations to 99.9% accuracy.”

Read more in VentureBeat >>