Ballroom Dance Movement Recognition Using a Smart Watch
Preprint
Abstract
Inertial Measurement Unit (IMU) sensors are being increasingly used to detect human gestures and movements. Using a single IMU sensor, whole body movement recognition remains a hard problem because movements may not be adequately captured by the sensor. In this paper, we present a whole body movement detection study using a single smart watch in the context of ballroom dancing. Deep learning representations are used to classify well-defined sequences of movements, called \emph{figures}. Those representations are found to outperform ensembles of random forests and hidden Markov models. The classification accuracy of 85.95\% was improved to 92.31\% by modeling a dance as a first-order Markov chain of figures and correcting estimates of the immediately preceding figure.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Ensembles of Deep LSTM Learners for Activity Recognition using WearablesProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017
- Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations2016
- I am a Smartwatch and I can Track my User's Arm2016
- Detecting dance motion structure using body components and turning motions2010
- Tango or Waltz?: Putting Ballroom Dance Style into Tempo DetectionEURASIP Journal on Audio, Speech, and Music Processing, 2008
- Dance, Dance Evolution: Accelerometer Sensor Networks as Input to Video Games2007
- Phrase structure detection in dance2004
- Long Short-Term MemoryNeural Computation, 1997