Activity Recognition Using Biomechanical Model Based Pose Estimation
2010 (English)In: Smart Sensing and Context, 2010 / [ed] Paul Lukowicz, Kai Kunze, Gerd Kortuem, Springer Berlin/Heidelberg, 2010, 42-55 p.Conference paper (Refereed)
In this paper, a novel activity recognition method based on signal-oriented and model-based features is presented. The model-based features are calculated from shoulder and elbow joint angles and torso orientation, provided by upper-body pose estimation based on a biomechanical body model. The recognition performance of signal-oriented and model-based features is compared within this paper, and the potential of improving recognition accuracy by combining the two approaches is proved: the accuracy increased by 4–6% for certain activities when adding model-based features to the signal-oriented classifier. The presented activity recognition techniques are used for recognizing 9 everyday and fitness activities, and thus can be applied for e.g., fitness applications or ‘in vivo’ monitoring of patients.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2010. 42-55 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 6446
IdentifiersURN: urn:nbn:se:liu:diva-90521DOI: 10.1007/978-3-642-16982-3_4ISBN: 978-3-642-16981-6ISBN: e-978-3-642-16982-3OAI: oai:DiVA.org:liu-90521DiVA: diva2:613687
5th European Conference, EuroSSC 2010, Passau, Germany, November 14-16, 2010