QinetiQ has received Centre for Defence Enterprise (CDE) funding to find ways to extract open-source imagery to construct 3D point cloud models which could help with navigation without using global positioning systems (GPS).
QinetiQ has developed a tool chain that shows that open source data from ‘non-iconic’ locations is, on average, 580 times less dense than the highly curated datasets. Open-source data has a very low proportion of data with geo-reference information: on average 6% compared to 60% in curated test sets.
As open-source imagery and videography increase in this social media age, this technology would allow more detailed information to be extracted and put to use in a military environment. An example would be the ability to track the change of terrain over a period of time.
In the future this technology and technique of retrieving geo-location could provide significant advantages as an alternative location method especially when GPS is unavailable.
The potential development routes include: providing denser mapping from combinations of video and image data from more sources of open source data and satellite/aerial data; filtering out unusable data; modifying the geo-location algorithm to make it more resilient to GPS outliers; and a focus on alternative uses for the tool chain such as open source image analysis to improve on image data which lacks metadata.
QinetiQ is a British defence, science and technology organisation. Founded in 2001 it has its headquarters in Farnborough, Hampshire and has approximately 9000 employees worldwide.
View the pitch presentation slides.
CDE funds novel, high-risk, high-potential-benefit research. We work with the broadest possible range of science and technology providers, including academia and small companies, to develop cost-effective capabilities for UK armed forces and national security.
CDE is part of Dstl.