Innovation That Matters

Shark spotting drone | Photo source Jakob Owens on Unsplash

Shark spotting drones alert swimmers of nearby danger

Work & Lifestyle

In Australia drones have been powered by artificial intelligence and embedded with loudspeakers to warn those at risk of shark attacks.

While Jaws may be a work of fiction, the danger sharks pose in some areas of the world is very much real. Australian company Little Ripper Group has created the Little Ripper Lifesaver drone as a warning system to those in the path of a nearby shark. The drones are fitted with loudspeakers to project the warnings as loudly as possible. The private company has been working with Professor Michael Blumenstein, the Head of the School of Software in the Faculty of Engineering and Information Technology, University of Technology Sydney (UTS), and his team to develop an algorithm to automatically detect sharks using the video footage streamed from the drones.

The aim is to initially conduct shark detection in real time from the downlinked video from the UAVs and then to move to shark detection in real time on the UAVs themselves, with only detections downlinked to the UAV pilots and operators. The team is using aerial videos of sharks from publicly available sources to train the algorithms, a sophisticated Deep Learning Framework (machine learning) as the backbone for the shark detection and recognition algorithm using a Region based-Convolution Neural Network (RCNN) for accurate object detection and recognition, and objects such as sharks, swimmers, and surfboards from the available video footage for testing and checking the preliminary approach. The drones can also be used for a multitude of other purposes such as finding people lost at sea and finding those in need in the event of a natural disaster.

Drones have helped serve a number of purposes this year, acting as a surveillance service in Dubai and as a delivery offering between hospitals in Switzerland. How could UAVs impact your business operations?




Download PDF