@inbook {bBernardin09, title = {Person Tracking}, booktitle = {Computers in the human interaction loop}, year = {2009}, pages = {11{\textendash}22}, publisher = {Springer}, organization = {Springer}, address = {London}, abstract = {

One of the most basic building blocks for the understanding of human actions and interactions is the accurate detection and tracking of persons in a scene. In constrained scenarios involving at most one subject, or in situations where persons can be confined to a controlled monitoring space or required to wear markers, sensors, or microphones, these tasks can be solved with relative ease. However, when accurate localization and tracking have to be performed in an unobtrusive or discreet fashion, using only distantly placed microphones and cameras, in a variety of natural and uncontrolled scenarios, the challenges posed are much greater. The problems faced by video analysis are those of poor or uneven illumination, low resolution, clutter or occlusion, unclean backgrounds, and multiple moving and uncooperative users that are not always easily distinguishable.

}, isbn = {978-1-84882-053-1}, doi = {10.1007/978-1-84882-054-8}, url = {http://www.springerlink.com/content/tj2x827107563616/}, author = {Bernardin, K. and Stiefelhagen, R. and Pnevmatikakis, A. and Lanz, O. and Brutti, A. and Casas, J. and Potamianos, G.} } @article {aMostefa07, title = {The CHIL Audiovisual Corpus for Lecture and Meeting Analysis inside Smart Rooms}, journal = {Language resources and evaluation}, volume = {41}, number = {3}, year = {2007}, month = {01/2008}, pages = {389{\textendash}407}, abstract = {

The analysis of lectures and meetings inside smart rooms has recently attracted much interest in the literature, being the focus of international projects and technology evaluations. A key enabler for progress in this area is the availability of appropriate multimodal and multi-sensory corpora, annotated with rich human activity information during lectures and meetings. This paper is devoted to exactly such a corpus, developed in the framework of the European project CHIL, {\textquotedblleft}Computers in the Human Interaction Loop{\textquotedblright}. The resulting data set has the potential to drastically advance the state-of-the-art, by providing numerous synchronized audio and video streams of real lectures and meetings, captured in multiple recording sites over the past 4 years. It particularly overcomes typical shortcomings of other existing databases that may contain limited sensory or monomodal data, exhibit constrained human behavior and interaction patterns, or lack data variability. The CHIL corpus is accompanied by rich manual annotations of both its audio and visual modalities. These provide a detailed multi-channel verbatim orthographic transcription that includes speaker turns and identities, acoustic condition information, and named entities, as well as video labels in multiple camera views that provide multi-person 3D head and 2D facial feature location information. Over the past 3 years, the corpus has been crucial to the evaluation of a multitude of audiovisual perception technologies for human activity analysis in lecture and meeting scenarios, demonstrating its utility during internal evaluations of the CHIL consortium, as well as at the recent international CLEAR and Rich Transcription evaluations. The CHIL corpus is publicly available to the research community

}, issn = {1574-020X}, doi = {10.1007/s10579-007-9054-4}, author = {Mostefa, D. and Moreau, N. and Choukri, K. and Potamianos, G. and Chu, S. and Tyagi, A. and Casas, J. and Turmo, J. and Cristoforetti, L. and Tobia, F. and Pnevmatikakis, A. and Mylonakis, V. and Talantzis, F. and Burger, S. and Stiefelhagen, R. and Bernardin, K. and Rochet, C.} }