sOc-EUSAI'2005 conference

Regular session - Analyzing users activities
O4-1 Analyzing Features for Activity Recognition
Huynh, Tam - Schiele, Bernt
As formated for the printed proceedings - - 42.pdf - pages 159-164
As delivered by the authors - 42_pdf_file.pdf
Abstract :
Human activity is one of the most important ingredients of context information. In wearable computing scenarios, activities such as walking, standing and sitting can be inferred from data provided by body-worn acceleration sensors. In such settings, most approaches use a single set of features, regardless of which activity to be recognized. In this paper we show that recognition rates can be improved by careful selection of individual features for each activity. We present a systematic analysis of features computed from a real-world data set and show how the choice of feature and the window length over which the feature is computed affects the recognition rates for different activities. Finally, we give a recommendation of suitable features and window lengths for a set of common activities.

O4-2 Facial action tracking using particle filters and active appearance models
Hamlaoui, Soumya - Davoine, Franck
As formated for the printed proceedings - - 57.pdf - pages 165-170
As delivered by the authors - 57_pdf_file.pdf
Abstract :
Tracking a face and its facial features in a video sequence is a challenging problem in computer vision. In this view, we propose a stochastic tracking system based on a particle-filtering scheme. In this sitting, the unobserved state includes global face pose and appearance parameters coding both shape and texture information of the face. The adopted observations distribution is derived from an Active Appearance Model (AAM). The transition distribution and the particles number are adaptive in the sense that they are guided by an AAM deterministic search. This optimization stage adjusts the explored area of the state space to the quality of the prediction and enables a substantial gain in computing time. The observation model uses a robust distance measure in order to account for occlusions. Experiments on real video show encouraging results.

O4-3 Using Task Context Variables for Selecting the Best Timing for Interrupting Users
Gievska, Sonja - Sibert, John
As formated for the printed proceedings - - 75.pdf - pages 171-176
As delivered by the authors - 75_pdf_file.pdf
Abstract :
This paper presents a framework that helps in selecting the most appropriate timing for interruption as a way to mediate human interruptions by the computer. The conceptual framework is based on the new Interruption Taxonomy and uses Bayesian Belief Networks as a decision-support aid. A proof-of-concept model was constructed for the experimental setting used in the exploratory study that was also part of this research. The steps in constructing the model that was built into the first version of the interruption mediator will be presented to show, in detail, how one might use the proposed framework for mediating interruptions.