We present a Spatio-temporal 2D Models Framework (STMF) for 2D-Pose tracking. Space and time are discretized and a mixture of probabilistic “local models” is learnt associating 2D Shapes and 2D Stick Figures. Those spatio-temporal models generalize well for a particular viewpoint and state of the tracked action but some spatiotemporal discontinuities can appear along a sequence, as a direct con...

Origin of chaos in a simple slow-fast 2D map replicating the spiking and spiking-bursting activity of real biological neurons is studied. The map contains one fast and one slow variable. We study the bifurcation scenarios which reveal the dynamical mechanisms that lead to chaos through canards in alternation of silence and spiking phases.

In the interaction between man and machine, an efficient, natural and intuitive commanding system plays a key role. Vision based techniques are usually used to provide such a system. This paper presents a new solution using 2D/3D images for real time hand detection, tracking and classification which is used as an interface for sending the commands to an industrial robot. 2D/3D images, including...

We discuss Hough Transform, some of its key properties, a scheme of fast and complete calculation of the Hough Transform (similar to the Fast Fourier Transform), and an efficient implementation of this scheme on SIMD processors. We also demonstrate an application of the Fast Hough Transform in computer vision by the example of an automatic page orientation detection unit incorporated in an inte...

Protein dynamics and interactions in myoglobin (Mb) were characterized via two vibrational dynamics labels (VDLs): a genetically incorporated site-specific azide (Az) bearing unnatural amino acid (AzPhe43) and an active site CO ligand. The Az-labeled protein was studied using ultrafast two-dimensional infrared (2D IR) vibrational echo spectroscopy. CO bound at the active site of the heme serves...