Automatic Segmentation of Therapeutic Exercises Motion Data with a Predictive Event Approach
We propose a novel approach for detecting events in data sequences, based on a predictive method using Gaussian processes. We have applied this approach for detecting relevant events in the therapeutic exercise sequences, wherein obtained results in addition to a suitable classifier, can be used directly for gesture segmentation. During exercise performing, motion data in the sense of 3D position of characteristic skeleton joints for each frame are acquired using a RGBD camera . Trajectories of joints relevant for the upper-body therapeutic exercises of Parkinson’s patients are modelled as Gaussian processes. Our event detection procedure using an adaptive Gaussian process predictor has been shown to outperform a first derivative based approach.
KeywordsGesture segmentation Predictive event approach Gaussian processes Physical rehabilitation RGBD camera
This work was partially funded by bilateral project COLBAR, between Instituto Superior Técnico, Lisbon, Portugal and Mihailo Pupin Institute, Belgrade, Serbia, FCT [PEst-OE/EEI/LA0009/2013], III44008, TR35003 and SNSF IP SCOPES, IZ74Z0_137361/1.
- 4.Gama A, Chaves T, Figueiredo L et al (2012) Guidance and movement correction based on therapeutics movements for motor rehabilitation support systems. In: 14th symposium on virtual and augmented reality, pp 191–200Google Scholar
- 5.Lee S (2006) Automatic gesture recognition for intelligent human-robot interaction. In: Proceedings of 7th international conference on automatic face and gesture recognition, pp 645–650Google Scholar
- 6.Park H, Jung D, Kim H (2006) Vision-based game interface using Human Gesture. In: Advances in image and video technology, pp 662–671Google Scholar
- 7.Alon J, Athitsos V, Sclaroff S (2005) Accurate and efficient gesture spotting via pruning and subgesture reasoning. In: Proceedings of IEEE ICCV workshop on human computer interaction, pp 189–198Google Scholar
- 10.Kruskall J, Liberman M (1983) The symmetric time warping algorithm: From continuous to discrete. In: Time warps, string edits and macromolecules. pp 125–162Google Scholar
- 11.Morguet P, Lang M (1998) Spotting dynamic hand gestures in video image sequences using hidden Markov models. In: Proceedings of IEEE international conference on image processing. pp 193–197Google Scholar
- 15.Kwon DY (2008) A design framework for 3D spatial gesture interfaces. PhD, ETH, SwitzerlandGoogle Scholar
- 16.Kahol K, Tripathi P, Panchanathan S (2004) Automated gesture segmentation from dance sequences. In: Proceeings of IEEE 6th international conference on automatic face and gesture recognition, pp 883–888Google Scholar
- 18.Nery Bruno, Ventura Rodrigo (2011) A dynamical systems approach to online event segmentation in cognitive robotics. Paladyn. J Behav Robot 2(1):18–24Google Scholar