Real Time Hand Pose Estimation for HCI.

É com prazer que convido a tod@s para mais um seminário do grupo de eScience. Nosso convidado será Dr. Philip Krejov, um recém doutor da universidade de Surrey, Inglaterra, que estará visitando o departamento nesse dia.

Data: 24/5/2016

Horário: 14h

Local: sala 136 do bloco A

Título: Real Time Hand Pose Estimation for HCI.

The aim of this presentation is to address the challenge of real-time pose estimation of the hand. Specifically aiming to determine the joint positions of a non-augmented hand. This methods discussed focus on the use of depth, performing localisation of the parts of the hand through efficient fitting of a kinematic model and consists of four main contributions.

The first part presents an approach to Multi-touch(less) tracking, where the objective is to track the fingertips with a high degree of accuracy without sensor contact. Using a graph based approach, the surface of the hand is modelled and extrema of the hand are located. The tracking approach allows for collaborative interactions due to its highly efficient tracking, resolving 4 hands simultaneously in real-time.

The second contribution applies a Randomised Decision Forest (RDF) to the problem of pose estimation and presents a technique to identify regions of the hand, using features that sample depth. The RDF is an ensemble based classifier that is capable of generalising to unseen data and is capable of modelling expansive datasets, learning from over 70,000 pose examples. The approach is also demonstrated in the challenging application of American Sign Language (ASL) finger-spelling recognition.

The third contribution combines a machine learning approach with a model based method to overcome the limitations of either technique in isolation. A RDF provides initial segmentation allowing surface constraints to be derived for a 3D model, which is subsequently fitted to the segmentation. This stage of global optimisation incorporates temporal information and enforces kinematic constraints. Using Rigid Body Dynamics for optimisation, invalid poses due to self-intersection and segmentation noise are resolved.

Accuracy of the approach is limited by the natural variance between users and the use of a generic hand model. The final contribution therefore proposes an approach to refine pose via cascaded linear regression which samples the residual error between the depth and the model. This combination of techniques is demonstrated to provide state of the art accuracy in real time, without the use of a GPU and without the requirement for model initialisation.

Short BIO:
Philip 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. He is currently 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 a press conference held at the Royal Society, London. Philip has also 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.