This paper presents a computer vision based head tracking system for augmented reality. A camera is attached to a head mounted display and used to track markers in the user's field of view. These markers are movable on a table and used as interface with virtual objects. Furthermore, they are used as landmarks to track the user's viewpoint and viewing direction by a homography based camera pose estimation algorithm. By integrating this computer vision tracker with a commercially available InterSense tracker, we take the advantages of the small jitter of the former one without losing the tracking speed of the later one. For static and slow head motion the system has less than 0.3mm RMS of position jitter and 0.165 degrees RMS of orientation jitter.

Human motion capture has lately been the object of much attention due to commercial interests. A "touch-free" computer vision solution to the problem is desirable to avoid the intrusiveness of standard capture devices. The object to be monitored is known a priori which suggests the inclusion of a human model in the capture process. We use a model-based approach known as the analysis-by-synthesis approach. This approach is powerful but has a problem with its potential huge search space. Using multiple cues we reduce the search space by introducing constraints through the 3D locations of salient points and a silhouette of the subject. Both data types are relatively easy to derive and only require limited computational effort so the approach remains suitable for real-time applications. The approach is tested on 3D movements of a human arm and the results show that we successfully can estimate the pose of the arm using the reduced search space.

Colour is an important and useful feature for object tracking and recognition in computer vision. However, it has the difficulty that the colour of the object changes if the illuminant colour changes. But under known illuminant colour it becomes a robust feature. There are more and more computer vision applications tracking humans, for example in interfaces for human computer interaction or automatic camera men, where skin colour is an often-used feature. Hence, it would be of significant importance to know the illuminant colour in such applications. This paper proposes a novel method to estimate the current illuminant colour from skin colour observations. The method is based on a physical model of reflections, the assumption that illuminant colours are located close to the Planckian locus, and the knowledge about the camera parameters. The method is empirically tested using real images. The average estimation error of the correlated colour temperature is as small as 180 K. Applications are for example in colour-based tracking to adapt to changes in lighting and in visualisation to re-render image colours to their appearance under canonical viewing conditions.

A method for segmentation of composite strings into their constituent substrings is presented as an extension to the Markov network inference technique. The basis for the segmentation is forced landmarks which are network representations of the positions where two substrings meet. The landmarks are forced into the Markov model in the inference thereof through supervised labeling. From subsequent string-to-network alignments, it is possible to estimate the positions in the strings that correspond to forced landmarks and thus segment the strings into their substrings. For discrimination between different classes of composite strings, classification probability measures are modified to include model-based information about estimated positions of the landmarks for individual classes. The potential of the method is illustrated with data representing banded human chromosomes.

Inference of Markov networks from finite sets of sample strings is formulated using dynamic programming. Strings are installed in a network sequentially via optimal string-to-network alignments computed with a dynamic programming matrix, the cost function of which uses relative frequency estimates of transition probabilities to emphasize landmark substrings common to the sample set. Properties of an inferred network are described and the method is illustrated with artificial data and with data representing banded human chromosomes.