Fusion paradigms in cognitive technical systems for human-computer interaction

NEUROCOMPUTING

卷:161

Article

Glodek, Michael¹  Honold, Frank²  Geier, Thomas³  Krell, Gerald⁴  Nothdurfte, Florian⁵  Reuter, Stephan⁶  Schuessel, Felix²  Hoernle, Thilo³  Dietmayer, Klaus⁶  Minker, Wolfgang⁵  Biundo, Susanne³  Weber, Michael²  Palm, Guenther¹  Schwenker, Friedhelm¹ 

[1] Univ Ulm, Inst Neural Informat Proc, D-89069 Ulm, Germany

[2] Univ Ulm, Inst Media Informat, D-89069 Ulm, Germany

[3] Univ Ulm, Inst Artificial Intelligence, D-89069 Ulm, Germany

[4] Univ Magdeburg, Inst Informat Technol & Commun, D-39106 Magdeburg, Germany

[5] Univ Ulm, Inst Informat Technol, D-89069 Ulm, Germany

[6] Univ Ulm, Inst Measurement Control & Microtechnol, D-89069 Ulm, Germany

关键词: Cognitive technical systems;    Scene understanding;    Human-computer interaction;   

DOI  :  10.1016/j.neucom.2015.01.076

来源: Elsevier

【 摘 要 】

Recent trends in human-computer interaction (HCI) show a development towards cognitive technical systems (CTS) to provide natural and efficient operating principles. To do so, a CTS has to rely on data from multiple sensors which must be processed and combined by fusion algorithms. Furthermore, additional sources of knowledge have to be integrated, to put the observations made into the correct context. Research in this field often focuses on optimizing the performance of the individual algorithms, rather than reflecting the requirements of CTS. This paper presents the information fusion principles in CTS architectures we developed for Companion Technologies. Combination of information generally goes along with the level of abstractness, time granularity and robustness, such that large CTS architectures must perform fusion gradually on different levels - starting from sensor-based recognitions to highly abstract logical inferences. In our CTS application we sectioned information fusion approaches into three categories: perception-level fusion, knowledge-based fusion and application-level fusion. For each category, we introduce examples of characteristic algorithms. In addition, we provide a detailed protocol on the implementation performed in order to study the interplay of the developed algorithms. (C) 2015 The Authors. Published by Elsevier B.V.

【 授权许可】

Free