Prof. Dr. Didier Stricker

Dr. Alain Pagani

Nicole Stephanie Buhlinger

Keonna Cunningham

Jason Raphael Rambach

Dr. Oliver Wasenmüller

Dr. Gabriele Bleser

Dr. Bertram Taetz

Rashed Al Koutayni

Jilliam Maria Diaz Barros

Mahdi Chamseddine

Steve Dias da Cruz

Christiano Couto Gava

Tewodros Amberbir Habtegebrial

Jigyasa Katrolia

Andreas Kölsch

Onorina Kovalenko

Muhammad Jameel Nawaz Malik

Nareg Minaskan Karabid

Manthan Pancholi

María Alejandra Sánchez Marín

Kripasindhu Sarkar

Alexander Schäfer

André Luiz Brandão

Ahmet Firintepe

Vladislav Golyanik

Activity Recognition Using Biomechanical Model Based Pose Estimation

Activity Recognition Using Biomechanical Model Based Pose Estimation
Attila Reiss, Gustaf Hendeby, Gabriele Bleser, Didier Stricker
The 5th European Conference on Smart Sensing and Context European Conference on Smart Sensing and Context (EuroSSC-2010), November 14-16, Passau, Germany

Abstract:: 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 biome- chanical 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 ac- tivity 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.

Back to the overview