Due to the advancement in human motion capturing technology and the availability of public human motion database, human motion understanding has become a core component of many research problems in multiple research domains. In computer graphics, a good representation of human motion facilitates characters with realistic movement, intuitive ways of crowd controls, and the real-time processing of captured motion data. In computer vision, modelling human motion is a key process for effective action classification and gait analysis. The core problem here is to model human motion in a meaningful way, such that we can generalize knowledge to recognize, analyze and synthesize movement.
The problem of human motion understanding is important as it connects different research fields. Taking an example of motion gaming with the Microsoft Kinect, the system first applies computer vision techniques to identify human body parts. Then, artificial intelligence is introduced to understand the meaning of the movement and perform human-computer interaction. Virtual reality techniques based on movement are sometimes used to enhance gaming immersiveness. Character animation and graphical rendering algorithms are implemented to render the controlled virtual character.
In this talk, I will discuss the importance of human motion analysis in computer science. With the results of my research projects, I will demonstrate how motion analysis can connect different research fields. I will show how my projects achieve impact in research and the society, and conclude my presentation with future opportunities and potential directions.
I am an Associate Professor (Reader) in Computer Science at Northumbria University, as well as the Director of Research and Innovation of the Computer and Information Sciences Department. I lead the Computational Intelligence and Visual Computing research team, which consists of 11 faculty members and 22 PhDs. Before this, I worked as a Senior Lecturer at Northumbria University, a Lecturer at the University of Worcester, a postdoctoral researcher at RIKEN Japan, and a research assistant at the City University of Hong Kong. I received my PhD degree from the School of Informatics at the University of Edinburgh, as well as my Master and Bachelor degrees from the City University of Hong Kong. I have published more than 90 referred journals and conferences in the fields of computer graphics, computer vision, motion analysis and machine learning.
I am the PI of a £124,000 EPSRC grant, a £125,000 Ministry of Defence grant, and multiple £12,000 Royal Society grants. I have also been the funding management officer of a €3.03 million Erasmus Mundus project. I have received more than £365,000 from Northumbria University to hire PhD students and purchase research equipment. I have organized conferences such as the British Machine Vision Conference, ACM SIGGRAPH Conference on Motion in Games and the ACM Symposium on Virtual Reality Software and Technology. I have served as a member of Programme Committee more than 40 times in 11 conferences, including the Pacific Conference on Computer Graphics and Applications, and the ACM/Eurographics Symposium on Computer Animation. I am an Associate Editor of Computer Graphics Forum and Computer Animation & Virtual Worlds, and have been a Guest Editor of International Journal of Computer Vision and Computers & Graphics. I have collaborated with industrial partners especially from the healthcare sector, such as Royal Victoria Infirmary, City Hospitals Sunderland, NHS Innovation North, Sunderland City Council and Your Homes Newcastle. I have established an international academic network with institutes such as Waseda University, the University of Edinburgh, INRIA and Hokkaido University.
For more information, please visit http://info.hubertshum.com