We present a system for fast model-based segmentation and 3D pose
estimation of specular objects using appearance based specular
features. We use observed (a) specular reflection...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron ac...
In this paper, we propose Multiple-Surface Active Volume Models (MSAVM) to extract 3D objects from volumetric medical images. Being able to incorporate spatial constraints among mu...
—We present an application of machine learning to the semi-automatic synthesis of robust servo-trackers for underwater robotics. In particular, we investigate an approach based o...