Multiple-Stage Classification of Human Poses while Watching Television

We compared the accuracy measure between a single-stage classifier model and a multiple-stage classifier model in postural classifications using Kinect. Postural training sets were collected from Kinect's skeletal data streams, based on some of the common human postures during television watching. Three types of training sets were used, including Kinect's raw skeletal training set, skeletons with attribute selection training set, and skeletal position transformation training set. We selected four learning models, namely, neural network, naïve Bayes, logistic regression, and decision tree, for learning our data sets and classifying a testing set to find the appropriate learning model. The best accuracy value of our experiment was 87.68 % by using skeletal position transformation training set with neural network. In the future, we will apply our technique and methodology to track elderly behaviors while they are watching television.

[1]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[2]  Chen Wu,et al.  Model-based human posture estimation for gesture analysis in an opportunistic fusion smart camera network , 2007, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance.

[3]  Hubert P. H. Shum,et al.  Real-Time Posture Reconstruction for Microsoft Kinect , 2013, IEEE Transactions on Cybernetics.

[4]  Pornchai Mongkolnam,et al.  Postural classification using Kinect , 2014, 2014 International Computer Science and Engineering Conference (ICSEC).

[5]  Jun Zhang,et al.  Image-Based Fall Detection with Human Posture Sequence Modeling , 2013, 2013 IEEE International Conference on Healthcare Informatics.

[6]  Yi Sun,et al.  2D recovery of human posture , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[7]  Yung-Yaw Chen,et al.  Human Posture Recognition by Simple Rules , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[8]  Ao Li,et al.  View independent human posture identification using Kinect , 2012, 2012 5th International Conference on BioMedical Engineering and Informatics.

[9]  Othman O. Khalifa,et al.  Comparison of supervised and unsupervised learning classifiers for human posture recognition , 2010, International Conference on Computer and Communication Engineering (ICCCE'10).

[10]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[11]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[12]  Isaac Cohen,et al.  Inference of human postures by classification of 3D human body shape , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[13]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[14]  Eugenio Di Sciascio,et al.  Semantic Matchmaking for Kinect-Based Posture and Gesture Recognition , 2014, 2014 IEEE International Conference on Semantic Computing.

[15]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[16]  Kazuhiko Takahashi,et al.  Remarks on human posture classification using self-organizing map , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).