90% of the information processed by the human brain is visual information. In less than a second we can recognise the face of someone we know, detect how far away an object is or find a constellation in the night's sky. Visual information, what we see, is key to our perception of the world around us.
Mark helps computers to understand the physical world around us through the analysis of visual information captured from cameras and other sensors. His research employs artificial intelligence and machine learning to enable a computer to analyse an image or video, understand it's content and then make a decision in a fraction of the time it would take a human. This automated approach to image analysis is becoming vitally important as the quantity of visual information produced by CCTV cameras and on social media far exceeds what can be analysed by a set of human observers. This technology can allow us to better understand and manage our cities, produce faster medical diagnoses and detect hateful or illegal images online.
Mark's research interests include the analysis of crowd behaviour, medical imaging and facial analysis. His work has resulted in several exciting collaborations with the likes of Intel, the GAA, the UCD School of Medicine and Fuji Xerox Palo Alto Laboratory.