IntroductionPhilip is a member of the CTO office at the RealSense group at Intel, conducting research in the field of Computer Vision with the focus of improving HCI. More specifically, he is developing tooling and architectures for capturing, sanitizing and learning from visual data.
These pages will give you a information about himself and his research. Feel free to contact if you have any questions. Intel Realsense
Lead the team to develop a markerless motion capture system. Allowing rapid and scaleable capture of ground truth annotation.
Designed, installed, tested and optimized the labs high speed network/storage infrastructure, providing a 20-50x improvement in transfer times for the rest of the team. Designed and lead the capture of large scale datasets using the aforementioned system, couching the captured participants and wrangling of the data. Developed tools that allow the exploration of large, N-dimensional spaces, this was later extended to identify and remove biases from the captured data. Physics based Hand pose estimationPhilip Krejov received a BEng (Hons) degree in Electronic Engineering from the University of Surrey, United Kingdom in 2011, including an industrial placement at National Instruments.
On graduation he was awarded the prize for best final year dissertation. Then a Research Fellow in the Centre for Vision Speech and Signal Processing at the University of Surrey, having completed his PhD in January 2016. The focus of his work is in Human Computer Interaction (HCI) with specialisation towards hand pose estimation. He has presented on many occasions, including: NI press conference held at the Royal Soiety, London British Computer Society, London. IMPA - Instituto de Matematica Pura e Aplicada ,Brazil NHK - Japan Broadcasting Corporation, Japan Intel RealSense, Santa Clara University of Washington CMU & Robotics Institute - Pittsburgh Philip has published several international papers regarding hand pose estimation and novel methods for human computer interaction. His research has lead to the development of two different approaches for estimating hand pose and has been demonstrated as a real time user interaction system. Hand pose estimation3D Table toppast projectsPublicationsPhilip Krejov, Andrew Gilbert, Richard Bowden
Guided Optimisation through Classification and Regression for Hand Pose Estimation. In Computer Vision and Image Understanding, Elsevier, 2016. Download: [bib] [pdf] Philip Krejov, Andrew Gilbert, Richard Bowden
Combining Discriminative and Model Based Approaches for Hand Pose Estimation. In International Conference on Automatic Face and Gesture Recognition, IEEE, 2015. Download: (Corrected Labels)[bib] [pdf] Philip Krejov, Andrew Gilbert, Richard Bowden
Multi-Touchless Interfaces: Interacting beyond the screen. In IEEE Computer Graphics and Applications, CG&A, Vol 34(3), 2014, pp40-48.. Download: [bib] [pdf] Project page Philip Krejov, Richard Bowden
Multi-touchless: Real-Time Fingertip Detection and Tracking Using Geodesic Maxima In International Conference on Automatic Face and Gesture Recognition, IEEE, pp. 7, 2013. Download: (dataset) [bib] [pdf] Project page |
|