I am currently a research scientist in the accessibility group at IBM Research Tokyo, working on the NavCog project jointly with Carnegie Mellon University. Within this project, I investigate intelligent systems to improve living and working conditions for senior citizens and people with disabilities. In particular, my research focuses on machine learning and computer vision for navigation in indoor/outdoor environments and higher level scene understanding.
Previously, I have been awarded the 2014 Toshiba fellowship as well as the JSPS international fellowship, which allowed me to work at the Toshiba R&D Center in Kawasaki on machine learning methods for bronchoscopy navigation and at Kagoshima University with Prof Hiroshi Kawasaki on active projection techniques for 3D reconstruction and BRDF estimation.
Before coming to Japan, I was a research associate in computer vision and signal processing at Imperial College London under Prof Pier Luigi Dragotti as part of the REWIND project consortium, an EU-funded FET Open project on image and video forensics. My Ph.D. work at the Hamlyn Center for Robotic Surgery, Imperial College London under Prof Guang-Zhong Yang focused on computer vision techniques in minimally invasive surgery. My final thesis, titled “3D Reconstruction from Stereo and Photometric Cues in Minimally Invasive Surgery” can be found here.
My research focuses on computer vision and machine learning, and specifically in 3D reconstruction for navigation, scene understanding, and augmented reality.