Abstract
Traditional temporal template method can recognize actions which have different speed, because of loss of speed information. On the other hand, this method will mix up the action which has the similar shape and different force. To solve this problem, a temporal template representation method is proposed to perfect the description of the motion which combines the MOFI(maximal optical flow image) and MHI(motion history image). In this paper, MOFI represents the distribution of the maximal optical flow. The optical flow is calculated by Farnebäck algorithm. The direction of movement is represented by different colors. The value of the speed is indicated by shades of color. Then, the maximal optical flow image is obtained. After calculating the wavelet moments of the maximal optical flow image and motion history image, we get feature vectors which are rotation, translation and scale invariant. Experiments based on UT-interaction dataset verify the effectiveness of the proposed method. Our method can distinguish similar actions, for example “hitting” and “patting” or “handclapping” and “handwaving”.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bobick, A., Davis, J.: The recognition of human movement using temporal templates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(3), 257–267 (2001)
Lan, C., Coenen, F., Zhang, B.L.: Driving posture recognition by joint application of motion history image and pyramid histogram of oriented gradients. International Journal of Vehicular Technology (2014)
Chen, S.Z., Tian, Y.L., Liu, Q.S., et al.: Recognizing expressions from face and body gesture by temporal normalized motion and appearance features. Image and Vision Computing 31(2), 175–185 (2013)
Lee, J., Park, J.-S., Seo, Y.H.: Emergency detection based on motion history image and adaboost for an intelligent surveillance system. In: Park, J.J., Barolli, L., Xhafa, F., Jeong, H.-Y. (eds.) Information Technology Convergence. LNEE, vol. 253, pp. 881–888. Springer, Heidelberg (2013)
Liu, J.Y., Zhang, N.N.: Gait history image: a novel temporal template for gait recognition. In: Proceedings of IEEE International Conference on Multimedia and Expo, pp. 663–666 (2007)
Julia, R., Gangolf, H.: Novel methods for feature extraction based on motion history images and evaluation with regard to altering viewing angles. In: Proceeding of IEEE third Conference on Consumer Electronics, pp. 1–5 (2013)
Timotius, I., Setyawan, I.: Hand gesture recognition based on motion history images for a simple human-computer interaction system. In: Proceedings of International Conference on Graphic and Image Processing, Singapore, pp. 87684M-1-87684M-5 (2013)
Ahad, M., Tan, J., Kim, H.: Motion history image: its variants and applications. Machine Vision and Applications 23(2), 255–281 (2012)
Ahad, M., Tan, J., Kim, H., et al.: Action recognition by employing combined directional motion history and energy images. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, San Francisco, pp. 73–78 (2010)
Dan, M., Toshitaka, M., Koji, K., et al.: Human motion analysis under actual sports game situations: sequential multi-decay motion history image matching. In: Proceedings of International Conference on Computer Vision Theory and Applications, pp. 229–236 (2013)
Hiba, H., Sreela, S.: Detection of abnormal behavior in dynamic crowded gatherings. In: Proceedings of Applied Imagery Pattern Recognition Workshop: Sensing for Control and Augmentation, Washington, DC, pp. 1–6 (2013)
Tian, Y.L., Cao, L.L., Liu, Z.C., et al.: Hierarchical filtered motion for action recognition in crowded videos. IEEE Transactions on Systems, Man, and Cybernetics 42(3), 313–323 (2012)
Gupta, R., Jain, A., Rana, S.: A novel method to represent repetitive and overwriting activities in motion history images. In: Proceedings of International Conference on Communications and Signal Processing, Melmaruvathur, pp. 556–560 (2013)
Qin, S.X., Yang,Y.P., Jiang, Y.S.: Gesture recognition from depth images using motion and shape features. In: 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation, pp. 172–175 (2013)
Wang, D.L., Lu, Z.H., Li, S.B., et al.: Clustering analysis of complex energy formulation based on k-means. In: 2012 International Conference on Computer Science and Information Processing, pp. 1349– 1352 (2012)
Fred, W., Anna, K.: Interrelation of the natural color system and the munsell color order system. Color Research & Application 12(5), 243–255 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, M., Song, Y., Hu, X., Zhang, L. (2015). Human Behavior Recognition Based on Velocity Distribution and Temporal Information. In: Yang, J., Yang, J., Sun, Z., Shan, S., Zheng, W., Feng, J. (eds) Biometric Recognition. CCBR 2015. Lecture Notes in Computer Science(), vol 9428. Springer, Cham. https://doi.org/10.1007/978-3-319-25417-3_69
Download citation
DOI: https://doi.org/10.1007/978-3-319-25417-3_69
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25416-6
Online ISBN: 978-3-319-25417-3
eBook Packages: Computer ScienceComputer Science (R0)