Dashcam with vision algorithms developed to reconstruct road accidents

Share this on social media:

Electronics engineering consultancy, Roke Manor Research, has developed a dashboard camera to provide precise 3D reconstruction of road accidents.

The UK-based company fitted the camera to an autonomous Toyota Prius to demonstrate how data captured via vision processing technology could be used to reconstruct the scene following a road incident.

The company thinks the technology will give insurers, drivers and, in the case of autonomous vehicles, manufacturers independent evidence of what happened in an accident.

Dr James Revell, consultant engineer at Roke, said: ‘Unlike current dashcams, the technology we tested today uses computer vision algorithms to enable the precise position and orientation of any vehicle – car, bike, lorry or autonomous vehicle. This allows for near-perfect 3D reconstruction of any accident to be created even if the vehicle loses complete control.’

Early iterations of this technology were first developed by Roke for soldiers in research undertaken for the UK government’s Defence Science and Technology Laboratory (Dstl). Over the past year, Roke has been developing and miniaturising the technology with the help of funding from Innovate UK.

David Cole, managing Director of Roke, said: ‘The funding from Innovate UK is essential in helping Roke remain at the forefront of autonomous and sensing technology. With 60 years of research under our belt, the money invested has the benefit of world-class engineers with experience across the defence, commercial and national security sectors.’

With further investment, the technology is not just limited to accident reconstruction but could also prove useful for sports coaching or meet wider needs in the transport industry.

Further information:

Roke Manor Research

Recent News

25 May 2021

The face recognition imager consumes 10,000 times less energy than a typical camera and processor. CEA-Leti is working with STMicroelectronics on the imager

06 May 2021

The GTOF0503 sensor features a 5µm three-tap iToF pixel, incorporating an array with a resolution of 640 x 480 pixels

30 April 2021

The algorithm can deduce the shape, size and layout of a room by measuring the time it takes for sound from speakers to return to the phone's microphone

20 April 2021

The Kria K26 SOM is built on top of the Zynq UltraScale+ MPSoC architecture. It has 4GB of DDR4 memory and 245 IOs for connecting sensors