AI technology repairs distorted and obscured images in real time

Machine vision systems have progressed rapidly in recent years, however performance can quickly deteriorate if a view is obscured by rain, smoke, dirt or other obstructions. This has serious implications for real world applications where image quality can be degraded by environmental factors or damage to camera-based systems.

DeepRay learns what real world scenes and objects look like and also how they appear with various image distortions applied. When presented with a distorted image it has never seen before, the technology can then form a real time judgement of the ‘true’ scene behind the distortion. Having this 'mind’s eye' ability means that DeepRay will outperform humans and existing machine vision approaches in reconstructing clear images under difficult conditions.

Tim Ensor, Commercial Director for Artificial Intelligence at Cambridge Consultants said: “This is the first time that a new technology has enabled machines to interpret real-world scenes the way humans can - and DeepRay can potentially outperform the human eye. This takes us into a new era of image sensing and will give flight to applications in many industries, including automotive, agritech and healthcare.

"The ability to construct a clear view of the world from live video, in the presence of continually changing distortion such as rain, mist or smoke, is transformational. We’re excited to be at the leading edge of developments in AI. DeepRay shows us making the leap from the art of the possible, to delivering breakthrough innovation with significant impact on our client’s businesses.”

DeepRay is the latest technology to emerge from Cambridge Consultants’ Digital Greenhouse, a unique experimental environment where data scientists and engineers explore and cultivate deep learning techniques. Leveraging this capability to deliver world-changing commercial applications led to Cambridge Consultants being named the first NVIDIA preferred deep learning delivery partner in the EMEA region.

DeepRay uses unique extensions of the Generative Adversarial Network (GAN) architecture. Training requires six neural networks to compete against each in teams, inventing difficult scenes and attempting to remove distortion. Effective end-to-end training of so many networks together has only been possible in the last two years but is yielding radical new capabilities.

DeepRay will be publicly unveiled at CES 2019 in Las Vegas, from January 8th 2019. You can visit the company in the Sands Expo, Level 2, Halls A-D, booth 44337.