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.

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.