%0 Journal Article %1 PnevmatikakisSoldatosEtAl09puc %A Pnevmatikakis, Aristodemos %A Soldatos, John %A Talantzis, Fotios %A Polymenakos, Lazaros %D 2009 %J Personal and Ubiquitous Computing %K v1205 springer paper embedded ai adaptive multimodal user interface location audio video processing %N 1 %P 3-14 %R 10.1007/s00779-007-0169-9 %T Robust Multimodal Audio-Visual Processing for Advanced Context Awareness in Smart Spaces %V 13 %X Identifying people and tracking their locations is a key prerequisite to achieving context awareness in smart spaces. Moreover, in realistic context-aware applications, these tasks have to be carried out in a non-obtrusive fashion. In this paper we present a set of robust person-identification and tracking algorithms, based on audio and visual processing. A main characteristic of these algorithms is that they operate on far-field and un-constrained audio-visual streams, which ensure that they are non-intrusive. We also illustrate that the combination of their outputs can lead to composite multimodal tracking components, which are suitable for supporting a broad range of context-aware services. In combining audio-visual processing results, we exploit a context-modeling approach based on a graph of situations. Accordingly, we discuss the implementation of realistic prototype applications that make use of the full range of audio, visual and multimodal algorithms.

@article{PnevmatikakisSoldatosEtAl09puc, abstract = {Identifying people and tracking their locations is a key prerequisite to achieving context awareness in smart spaces. Moreover, in realistic context-aware applications, these tasks have to be carried out in a non-obtrusive fashion. In this paper we present a set of robust person-identification and tracking algorithms, based on audio and visual processing. A main characteristic of these algorithms is that they operate on far-field and un-constrained audio-visual streams, which ensure that they are non-intrusive. We also illustrate that the combination of their outputs can lead to composite multimodal tracking components, which are suitable for supporting a broad range of context-aware services. In combining audio-visual processing results, we exploit a context-modeling approach based on a graph of situations. Accordingly, we discuss the implementation of realistic prototype applications that make use of the full range of audio, visual and multimodal algorithms.}, added-at = {2012-05-30T10:52:21.000+0200}, author = {Pnevmatikakis, Aristodemos and Soldatos, John and Talantzis, Fotios and Polymenakos, Lazaros}, biburl = {https://www.bibsonomy.org/bibtex/22b3b9d3ac9883746b8b63a9c85714735/flint63}, doi = {10.1007/s00779-007-0169-9}, file = {SpringerLink:2009/PnevmatikakisSoldatosEtAl09puc.pdf:PDF}, groups = {public}, interhash = {9b633b72f3fd9479b3c239e0f6001ee1}, intrahash = {2b3b9d3ac9883746b8b63a9c85714735}, issn = {1617-4909}, journal = {Personal and Ubiquitous Computing}, keywords = {v1205 springer paper embedded ai adaptive multimodal user interface location audio video processing}, number = 1, pages = {3-14}, timestamp = {2018-04-16T11:29:58.000+0200}, title = {Robust Multimodal Audio-Visual Processing for Advanced Context Awareness in Smart Spaces}, username = {flint63}, volume = 13, year = 2009 }