This paper presents a novel algorithm for forming coherent harmonic fragments from a mixture of speech sources. A multiple pitch detection algorithm is used to produce pitch candidates which are tracked using a pair of parallel HMMs. One novel aspect of the technique is that it systematically models pitch doubling and halving errors, thereby facilitating the identification of smooth pitch segme...

Object pose estimation aims at determining the relation between the camera and the object of interest. For rigid objects, the pose is defined through three degrees of freedom for rotation and three for translation. Across different applications in robotic perception, augmented reality and human-computer interaction, achieving a real-time robust object pose estimation is an integral component to...

A practical and robust head-position tracking method using computer vision is presented. By combining two simple image processing techniques, this tracker can report the position of the user's head in real time. Whole image processing is performed by software running on normal mid-range workstations. This tracker can support desk top virtual reality (also referred to as \ sh tank VR"), thereby ...

This paper introduces a hand tracking system with a theoretical proof of convergence. The tracking system follows a model-based approach and uses image-based cues, namely silhouettes and colour constancy. We show that, with the exception of a small set of parameter configurations, the cost function of our tracker has a well-behaved unique minimum. The convergence proof for the tracker relies on...

In earlier work we introduced a generic, modular tracker architecture that combines the advantages of several simple and rapidly performing tracking algorithms. The adaptive choice of critical system parameters such as processing regions and resolution results in robustness to varying frame rates and computational constraints. In this paper, we describe the embedding of our tracker into a distr...

This paper proposes novel algorithms and system architecture for tracking targets in video streams. The proposed system comprises a variation of Stauffer’s adaptive background algorithm with spacio-temporal adaptation of the learning parameters and a Kalman tracker in a feedback configuration. In the feed-forward path, the adaptive background module provides target evidence to the Kalman tracke...

This report presents recent results on track reconstruction and alignment with the silicon tracker of the CMS experiment at the LHC, obtained with a full detector simulation. After an overview of the layout of the tracker and its material budget, the baseline algorithm for track reconstruction is discussed. The performance of the track reconstruction and its dependence on misalignment is shown....

The advent and adoption of Web 2.0 technologies offers a powerful approach to enhancing the capture of information in natural resource ecology, notably community knowledge of species distributions. Such information has previously been collected using, for example, postal surveys; these are typically inefficient, with low response rates, high costs, and requiring respondents to be spatially lite...

In jüngster Zeit wurden viele neue Werkzeuge für die minimal-invasive Chirurgie entwickelt, darunter auch neue Instrumente für das Schneiden von knöchernem Material für die Kraniotomie, die für die Abtragung von Knochen einen Hochleistungslaser verwenden. Für die Steuerung des Laserstrahls wurde in Vorarbeiten u.a. der Tracker nach Kanade-Lukas-Tomasi (KLT) verwendet, ein etabliertes Verfahren ...