Benefit from unobtrusive contexts: Towards the recognition of short and non-periodic activities

Jahn, Andreas

kassel university press, ISBN: 978-3-7376-0430-7, 2018, 168 Seiten

URN: urn:nbn:de:0002-404314

DOI: 10.19211/KUP9783737604314

Zugl.: Kassel, Univ., Diss. 2017

| Preis und lieferbare Formen -->

Inhalt: Context-aware systems can be used in a multitude of scenarios and applications. Examples include a pedestrian safety system which can help to detect a potential upcoming accident based on the knowledge of the pedestrian’s activity. In the field of human activity recognition, a majority of research focuses on long-lasting and continuous activities, such as walking or attending a dinner. Yet, the recognition of short and non-periodic activities, such as stepping onto the road, is still poorly understood. Due to the non-periodic nature, missing or incorrect recognitions of such activities imply that the entire activity is not recognized and remains unknown.

This thesis focuses on short and non-periodic activities, gives a definition and investigates three challenges in their recognition: inconsistent sensor data, overrepresentation of periodic activities and evaluation of the recognition. For each challenge a possible solution is proposed. It is shown that applying these solutions addresses the challenges and improves the recognition rates of short and non-periodic activities up to 20%.

Die Publikation ist in folgenden Formen erhältlich:

Volltext (pdf-Datei, ausdruckbar, kostenpflichtig - 3.60 MB) 29.00 Euro
(kostenfrei im Netz der Universität Kassel - Im Netz der Uni Kassel befinden Sie sich, wenn Sie z.B. an einem Rechner im ITS, Ihrem Arbeitsplatz an der Uni oder auch in der Multimediathek der Bibliothek befinden.)
PDF erwerben (download) - Achtung kostenpflichtig, da Sie sich zur Zeit nicht im Netz der Uni-Kassel befinden