Abstract
As the accuracy of standard Harris algorithm is not high in the application of behavior recognition, this paper proposed a behavior recognition model based on scale adaptive local spatio-temporal characteristics Harris algorithm, which firstly uses local spatio-temporal characteristics function to achieve fast convolution in order to reduce complexity of the algorithm, and then uses scale adaptive local spatio-temporal characteristics function to replace Gaussian function as the filter of the algorithm, and finally calculates the adaptive matrix and the response value of the angle points in order to improve the accuracy of behavior recognition. Simulation results show that the accuracy of the Harris Algorithm based on scale adaptive local spatio-temporal characteristics, proposed in this paper, is higher than the standard Harris algorithm on behavior recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao G (2014) Application of improved EM algorithm in recognition of human actions. TV Eng 38(13):196–199
Zhou W (2014) Recognizing human actions by particle filter. J Chongqing Norm Univ Nat Sci Edition 31(5):105–109
Liu Y (2014) Abnormal behavior recognition based on corner motion history. Comput Eng Sci 36(6):1127–1131
Wang M (2014) Time-scale invariant modeling and classifying for object behaviors in 3D space based on monocular vision. Acta Automatica Sinica 40(8):1644–1653
Xiao D (2014) KFLD-SIFT with RVM fuzzy integral fusion recognition of human action based on tensor. Pattern Recognit Artif Intell 27(8):713–719
Wang H (2014) The research of human behavior recognition based on depth map sequence and space occupancy patterns. Sci Technol Eng 10(24):102–107
Li J (2014) Self-adaptive activity recognition method based on CHMMs. Appl Res Comput 31(10):3037–3040
Cai J (2014) Human action recognition based on local image contour and random forest. Acta Optica Sinica 10(10):204–213
Qin H (2014) Human action recognition based on composite spatio-temporal characteristics. J Comput Aided Des Comput Graphics 26(8):1320–1325
Liu H (2014) Human activity recognition based on 3D skeletons and MCRF model. J Univ Sci Technol China 44(4):285–291
Wang C (2014) Simulation of movement behavior recognition based on 3D virtual incomplete body image. Comput Simul 31(7):399–402
Acknowledgments
This work was supported by the Education of Zhejiang Province (Grant No. Y201225667), the Department of Science and Technology of Zhejiang Province (Grant No. 2014C31065), and the Department of Science and Technology of Zhejiang Province (Grant No. 2015C31091).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this paper
Cite this paper
Xu, Z., Li, X., Wu, F., Hu, F., Wu, L. (2017). Behavior Recognition of Scale Adaptive Local Spatio-Temporal Characteristics Harris Algorithm . In: Balas, V., Jain, L., Zhao, X. (eds) Information Technology and Intelligent Transportation Systems. Advances in Intelligent Systems and Computing, vol 454. Springer, Cham. https://doi.org/10.1007/978-3-319-38789-5_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-38789-5_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-38787-1
Online ISBN: 978-3-319-38789-5
eBook Packages: EngineeringEngineering (R0)