An Analysis of Sensor-Oriented vs. Model-Based Activity Recognition

Model-based activity recognition has been recently proposed as an alternative to signal-oriented recognition. Such model-based approaches seem attractive due to their ability to enable user-independent activity recognition and due to their improved robustness to signal-variation. The first goal of this paper is therefore to systematically analyze the benefit of body-model derived primitives in different sensor settings for multi activity recognition. Furthermore we propose a new body-model based approach using accelerometer sensors only thereby reducing the sensor requirements significantly. Results on a 20 activity dataset indicate that body-model based approaches consistently improve results over signal-oriented approaches.

[1]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[2]  Kenji Mase,et al.  Activity and Location Recognition Using Wearable Sensors , 2002, IEEE Pervasive Comput..

[3]  David W. Mizell,et al.  Using gravity to estimate accelerometer orientation , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[4]  Paul Lukowicz,et al.  Recognizing Workshop Activity Using Body Worn Microphones and Accelerometers , 2004, Pervasive.

[5]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[6]  Jani Mäntyjärvi,et al.  Accelerometer-based gesture control for a design environment , 2006, Personal and Ubiquitous Computing.

[7]  Blake Hannaford,et al.  A Hybrid Discriminative/Generative Approach for Modeling Human Activities , 2005, IJCAI.

[8]  Paul Lukowicz,et al.  Using Wearable Sensors for Real-Time Recognition Tasks in Games of Martial Arts - An Initial Experiment , 2006, 2006 IEEE Symposium on Computational Intelligence and Games.

[9]  Jörn Loviscach,et al.  A Mobile Low-Cost Motion Capture System Based on Accelerometers , 2006, ISVC.

[10]  Paul Lukowicz,et al.  Activity Recognition of Assembly Tasks Using Body-Worn Microphones and Accelerometers , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Gaetano Borriello,et al.  A Practical Approach to Recognizing Physical Activities , 2006, Pervasive.

[12]  Bernt Schiele,et al.  Scalable Recognition of Daily Activities with Wearable Sensors , 2007, LoCA.

[13]  Dieter Fox,et al.  Location-Based Activity Recognition , 2005, KI.

[14]  Luca Benini,et al.  MOCA: A Low-Power, Low-Cost Motion Capture System Based on Integrated Accelerometers , 2007, Adv. Multim..

[15]  Jennifer Healey,et al.  A Long-Term Evaluation of Sensing Modalities for Activity Recognition , 2007, UbiComp.

[16]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Paul Lukowicz,et al.  WearIT@work: Toward Real-World Industrial Wearable Computing , 2007, IEEE Pervasive Computing.

[18]  Bernt Schiele,et al.  A new approach to enable gesture recognition in continuous data streams , 2008, 2008 12th IEEE International Symposium on Wearable Computers.

[19]  James M. Rehg,et al.  Discriminative feature selection for hidden Markov models using Segmental Boosting , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Bernt Schiele,et al.  Sustained logging and discrimination of sleep postures with low-level, wrist-worn sensors , 2008, 2008 12th IEEE International Symposium on Wearable Computers.

[21]  Jessica K. Hodgins,et al.  Action capture with accelerometers , 2008, SCA '08.

[22]  Predrag V. Klasnja,et al.  Using wearable sensors and real time inference to understand human recall of routine activities , 2008, UbiComp.

[23]  Paul Lukowicz,et al.  Gesture spotting with body-worn inertial sensors to detect user activities , 2008, Pattern Recognit..

[24]  Paul Lukowicz,et al.  Using a complex multi-modal on-body sensor system for activity spotting , 2008, 2008 12th IEEE International Symposium on Wearable Computers.

[25]  Bernt Schiele,et al.  Multi Activity Recognition Based on Bodymodel-Derived Primitives , 2009, LoCA.