Matthew Trumble

Learn More
The paper presents a tool-supported approach to graphically editing scheme plans and their safety verification. The graphical tool is based on a Domain Specific Language which is used as the basis for transformation to a CSP‖B formal model of a scheme plan. The models produced utilise a variety of abstraction techniques that make the analysis of large scale(More)
OnTrack automates workflows for railway verification, starting with graphical scheme plans and finishing with automatically generated formal models set up for verification. OnTrack is grounded on an established domain specification language (DSL) and is generic in the formal specification language used. Using a DSL allows the formulation of abstractions(More)
We propose a human performance capture system employing convolutional neural networks (CNN) to estimate human pose from a volumetric representation of a performer derived from multiple view-point video (MVV).We compare direct CNN pose regression to the performance of an affine invariant pose descriptor learned by a CNN through a classification task. A(More)
We present a novel human performance capture technique capable of robustly estimating the pose (articulated joint positions) of a performer observed passively via multiple view-point video (MVV). An affine invariant pose descriptor is learned using a convolutional neural network (CNN) trained over volumetric data extracted from a MVV dataset of diverse(More)
  • 1