A Neural Network Approach for Human Gesture Recognition with a Kinect Sensor

T. D’Orazio, C. Attolico, G. Cicirelli, C. Guaragnella

Abstract

Service robots are expected to be used in many household in the near future, provided that proper interfaces are developed for the human robot interaction. Gesture recognition has been recognized as a natural way for the communication especially for elder or impaired people. With the developments of new technologies and the large availability of inexpensive depth sensors, real time gesture recognition has been faced by using depth information and avoiding the limitations due to complex background and lighting situations. In this paper the Kinect Depth Camera, and the OpenNI framework have been used to obtain real time tracking of human skeleton. Then, robust and significant features have been selected to get rid of unrelated features and decrease the computational costs. These features are fed to a set of Neural Network Classifiers that recognize ten different gestures. Several experiments demonstrate that the proposed method works effectively. Real time tests prove the robustness of the method for realization of human robot interfaces.

References

  1. Almetwally, I. and Mallem, M. (2013). Real-time teleoperation and tele-walking of humanoid robot nao using kinect depth camera. 10th IEEE International Conference on Networking, Sensing and Control (ICNSC), page 463466.
  2. Bhattacharya, S., Czejdo, B., and Perez, N. (2012). Gesture classification with machine learning using kinect sensor data. Third International Conference on Emerging Applications of Information Technology (EAIT), pages 348 - 351.
  3. Biswas, K. and Basu, S. (2011). Gesture recognition using microsoft kinect. 5th International Conference on Automation, Robotics and Applications (ICARA), pages 100-103.
  4. Castiello, C., D'Orazio, T., Fanelli, A., Spagnolo, P., and Torsello, M. (2005). A model free approach for posture classificatin. IEEE Conf. on Advances Video and Signal Based Surveillance, AVSS.
  5. Cheng, L., Sun, Q., Cong, Y., and Zhao, S. (2012). Design and implementation of human-robot interactive demonstration system based on kinect. 24th Chinese Control and Decision Conference (CCDC), page 971975.
  6. Cruz, L., Lucio, F., and Velho, L. (2012). Kinect and rgbd images: Challenges and applications. XXV SIBGRAPI IEEE Confernce and Graphics, Patterns and Image Tutorials, page 3649.
  7. den Bergh, M. V., Carton, D., de Nijs, R., Mitsou, N., Landsiedel, C., Kuehnlenz, K., Wollherr, D., Gool, L. V., and Buss, M. (2011). Real-time 3d hand gesture interaction with a robot for understanding directions from humans. 20th IEEE international symposium on robot and human interactive communication, pages 357 - 362.
  8. Gu, Y., andY. Ou, H. D., and Sheng, W. (2012). Human gesture recognition through a kinect sensor. IEEE International Conference on Robotics and Biomimetics (ROBIO), pages 1379 - 1384.
  9. Hachaj, T. and Ogiela, M. (2013). Rule-based approach to recognizing human body poses and gestures in real time. Multimedia Systems.
  10. J.Oh, Kim, T., and Hong, H. (2013). Using binary decision tree and multiclass svm for human gesture recognition. International Conference on Information Science and Applications (ICISA), pages 1 - 4.
  11. Lai, K., Konrad, J., and Ishwar, P. (2012). A gesturedriven computer interface using kinect. IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), pages 185 - 188.
  12. Leo, M., P.Spagnolo, D'Orazio, T., and Distante, A. (2005). Human activity recognition in archaeological sites by hidden markov models. Advances in Multimedia Information Procesing - PCM 2004.
  13. Miranda, L., Vieira, T., Martinez, D., Lewiner, T., Vieira, A., and Campos, M. (2012). Real-time gesture recognition from depth data through key poses learning and decision forests. 25th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 268 - 275.
  14. SpecialOPeration (2013). Arm-and-hand signals for ground forces. www.specialoperations.com/Focus/Tactics/ Hand Signals/default.htm.
Download


Paper Citation


in Harvard Style

D’Orazio T., Attolico C., Cicirelli G. and Guaragnella C. (2014). A Neural Network Approach for Human Gesture Recognition with a Kinect Sensor . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 741-746. DOI: 10.5220/0004919307410746


in Bibtex Style

@conference{icpram14,
author={T. D’Orazio and C. Attolico and G. Cicirelli and C. Guaragnella},
title={A Neural Network Approach for Human Gesture Recognition with a Kinect Sensor},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={741-746},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004919307410746},
isbn={978-989-758-018-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Neural Network Approach for Human Gesture Recognition with a Kinect Sensor
SN - 978-989-758-018-5
AU - D’Orazio T.
AU - Attolico C.
AU - Cicirelli G.
AU - Guaragnella C.
PY - 2014
SP - 741
EP - 746
DO - 10.5220/0004919307410746