Abstract
A group activities recognition algorithm is proposed by combining M-DTCWT (multi directional dual tree complex wavelet transform) with elliptic Mahalanobis metric. M-DTCWT is composed of directional filter bank in cascade with dual tree complex wavelet transform. By using the M-DTCWT to decompose the human images in videos for multi-scale and multi-direction, the high and low frequency coefficients can be obtained. The texture features of the high and low frequency coefficients are extracted by using improved local binary pattern and gray level co-occurrence matrix and classified by using elliptic Mahalanobis metric. According to the results of classification, group activities are recognized. Experimental results on Group activity video set and self built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms and Euclidean metric algorithm.
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
Similar content being viewed by others
References
Zhang, C., Yang, X., Lin, W., Zhu, J.: Recognizing human group behaviors with multi-group causalities. In: 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology (WI-IAT), Macau, pp. 44–48 (2012)
Yin, Y., Yang, G., Xu, J., Man, H.: Small group human activity recognition. In: 2012 19th IEEE International Conference on Image Processing, Orlando, FL, pp. 2709–2712 (2012)
Andrade, E.L., Blunsden, S.R.B.: Hidden Markon models for optical flow analysis in crowds. In: Proceedings of the 18th International Conference on Pattern Recognition, pp. 460–463 (2006)
Ryoo, M.S., Aggarwal, J.K.: Semantic representation and recognition of continued and recursive human activities. Int. J. Comput. Vision 82, 1–24 (2009)
Choi, W., Shahid, K., Savarese, S.: Learning context for collective recognition. In: Proceedings of the IEEE Internation Conference on Computer Vision and Pattern Recognition (2011)
Antic, B., Ommer, B.: Learning Latent constituents for recognition of group activities in video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 33–47. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_3
Nabi, M., Bue, A.D., Murino, V.: Temporal poselets for collective activity detection and recognition. In: International Conference on Computer Vision Workshops (ICCVW), Sydney, NSW, pp. 500–507 (2013)
Kingsbury, N.: Image processing with complex wavelets. Philos. Trans. Royal Soc. Lond. Ser. A Math. Phys. Eng. Sci. 357(1760), 2543–2560 (1999)
Selesnick, I.W., Baraniuk, R.G., Kingsbury, N.C.: The dual-tree complex wavelet transform. Sig. Process. Mag. 22(6), 123–151 (2005)
Ioannidou, S., Karathanassi, V.: Investigation of the dual-tree complex and shift-invariant discrete wavelet transforms on Quickbird image fusion. IEEE Geosci. Remote Sens. Lett. 4(1), 166–170 (2007)
Zhang, Y.X., Zhao, Y.Q., Liu, Y., Jiang, L.Q., Chen, Z.W.: Identification of wood defects based on LBP features. In: 2016 35th Chinese Control Conference (CCC), Chengdu, China, pp. 4202–4205 (2016)
Song, H., Xiao, B., Hu, Q., Ren, P.: Integrating local binary patterns into normalized moment of inertia for updating tracking templates. Chin. J. Electron. 25(4), 706–710 (2016)
Lu, F., Huang, J.: An improved local binary pattern operator for texture classification. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, pp. 1308–1311 (2016)
Flusser, J., Suk, T., Boldyš, J., Zitová, B.: Projection operators and moment invariants to image blurring. IEEE Trans. Pattern Anal. Mach. Intell. 37(4), 786–802 (2015)
Imamverdiyev, Y., Teoh, A.B.J., Kim, J.: Biometric crypto-system based on discretized fingerprint texture descriptors. Expert Syst. Appl. 40(5), 1888–1901 (2013)
Bi, Y., Fan, B., Wu, F.: Beyond Mahalanobis metric: Cayley-Klein metric learning. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp. 2339–2347 (2015)
Choi, W., Shahid, K., Savarese, S.: What are they doing? Collective activity classification using spatio-temporal relationship among people. In: Proceedings of 9th International Workshop on Visual Surveillance (VSWS 2009) in Conjuction with ICCV (2009)
Acknowledgements
This work has been partially supported by the National Natural Science Foundation of China (61672032, 61401001), the Natural Science Foundation of Anhui Province under Grant 1408085MF121, and the Opening Foundation of polarization imaging detection technology of Anhui Key Laboratory (2016-KFKT-003).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hu, G., Li, M., Liang, D., Bao, W. (2018). Recognition of Group Activities Based on M-DTCWT and Elliptic Mahalanobis Metrics. In: Wang, Y., et al. Advances in Image and Graphics Technologies. IGTA 2017. Communications in Computer and Information Science, vol 757. Springer, Singapore. https://doi.org/10.1007/978-981-10-7389-2_12
Download citation
DOI: https://doi.org/10.1007/978-981-10-7389-2_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7388-5
Online ISBN: 978-981-10-7389-2
eBook Packages: Computer ScienceComputer Science (R0)