Ground-breaking artificial intelligence (AI) technology being developed in Scotland will soon enhance Police Scotland’s use of drones to find missing and vulnerable people.
The technology, thought to be the first of its kind used by police forces in the UK, is a form of machine learning that provides real-time image analysis for identifying humans in rural areas. It has been developed by a consortium of partners comprising of Thales UK, the University of the West of Scotland, CENSIS, and Police Scotland.
With core AI development work complete and trials of the new system already underway, the project team expects the remotely piloted aircraft systems (RPAS) technology to be deployed in searches for missing and vulnerable people in Scotland in the near future.
Computers with very large amounts of data processing power were previously required to run similar technology, rendering it immobile. However, the specifically designed algorithms developed in this project can be used on a smartphone or tablet connected to an RPAS.
Trained with hundreds of hours of footage of officers in different clothing, positions, and situations at police premises, the AI scours an image and can locate a person within seconds at a distance of up to 150 metres. The system is twice as fast as other state-of-the-art algorithms and its ability to recognise a human is enhanced the more it is used.
The RPAS is operated by a specially trained officer on the ground, while another officer receives a real-time video feed from the RPAS cameras on a smartphone. The incorporation of the AI technology will help Police Scotland cover large areas of ground in the search for a missing person, reducing the need for lengthy and meticulous checks from teams of officers on the ground.
Although initially being employed in the search for missing and vulnerable people, the technology could potentially be used in a variety of other applications, including monitoring wildlife on land and at sea.
Inspector Nicholas Whyte, Police Scotland Air Support Unit, said: “The use of Remotely Piloted Aircraft Systems in an operational policing environment is still a relatively new field and this collaboration presents a unique opportunity for Police Scotland to be involved in the development of new technology which will enhance the service delivered to the people of Scotland.”
Prof. Carl Schaschke, Dean of the School of Computing, Engineering & Physical Sciences at UWS, said: “UWS is proud in leading this exciting project to address a real-world challenge through a ground-breaking solution for the national public safety. The UWS team led by Professors Jose Alcaraz Calero and Qi Wang has showed their expertise as well as passion in delivering first-class research to help society. Through collaboration with a group of prominent partners including Thales UK, Police Scotland, and CENSIS, this high-profile UWS project will have a significant impact on the research in this field and contribute to the university’s research and enterprise strategies.”
Barry Connor, Technology and Innovation Manager at Thales, said: “Thales is happy to support this project as it demonstrates the benefits of AI and machine learning in saving people’s lives. We have previously been part of a CENSIS/UWS project and this current project has strengthened our links and enabled us to work with other academics. Collaborations like these enable Thales to develop new capabilities and improved product functionality.”
Craig Fleming, Senior Business Development Manager at CENSIS, said: “The project is pushing the boundaries of machine learning. It’s testament to the depth of technical skills and knowledge in Scotland’s academic institutions and businesses that this pioneering technology is being developed here. Once commercialised, the system has huge potential in a wide variety of sectors. This is another example of how Scotland is becoming hub of exciting developments in the use of AI in imaging, with a range of academic and industry partnerships developing new capabilities and products.”
