Abstract
Taking the characteristic value as the core, a population abnormality detection algorithm is used to process the crowd surveillance video. Using density detection, the density of the population is first obtained. Object-based feature extraction is used in low-density scenes, and pixel-based feature extraction in high-density scenes. So as to obtain the crowd of exercise intensity, trajectory gradient, entropy and local density and other characteristic value. Finally identify the abnormal behavior of the population based on characteristic value. The experimental results show that the characteristic value is obvious when the abnormality occurs. The algorithm’s performance index is superior to the traditional crowd behavior recognition algorithm with high recognition rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wei, Y., Zhuang, X., Fu, Q.: Research progress on the crowd abnormal recognition technology. Comput. Syst. Appl. 25(9), 10–16 (2016)
Zhang, P.: Crowd status analysis and abnormal behavior detection. Civil Aviation University of China (2016)
Zhang, J.: Anomaly detection of crowd based on motion entropy. Modem Comput. (07), 40–43 (2013)
He, C.-Y., Wang, P., Zhang, X.-H., et al.: Abnormal behavior detection of small and medium crowd based on intelligent video surveillance. J. Comput. Appl. 36(6), 1724–1729 (2016)
Chenguang, G., Xianglong, L., Linfeng, Z., et al.: A fast and accurate corner detector based on Harris algorithm. In: International Symposium on Intelligent Information Technology Application, pp. 49–52. IEEE (2009)
Shen, M., Song, H.: Optic flow target tracking method base on croner detection. Electron. Devices 30(4), 1397–1399 (2007)
Deng, X., Tong, Q., Wen, Z., et al.: The comparison and analysis of moving target detection based on optical flow of Horn-Schunk and Kalman filtering technology. Int. J. Adv. Comput. Technol. (2013)
Xu, S.-F., Wu, S.-L., Li, H.: An analysis on human skin texture based on gray-level co-occurrence matrix. Acta Lebihreei Sinica 20(3), 324–328 (2011)
Hu, B.: Detection of abnormal crowd event in high density video. Anhui University (2013)
Duan, J.-J., Gao, L., Fan, Y., et al.: Abnormal crowd behavior recognition based on KOD energy model. Appl. Res. Comput. 30(12), 3836–3839 (2013)
Acknowledgments
We thank our advisor, Professor Li Kangshun, for generously offers help in both software and hardware facilities, and supports us laboratory for research on our project. This work is supported by Ministry of Education of the People’s Republic of China for the National Student’s Training Program for Innovation and Entrepreneurship, “The Detection of Crowd Behavior Based on Deep Learning”. This work was jointly supported by Natural Science Foundation of Guangdong Province of China (#2017A010101037), and Natural Science Foundation of China (#61573157 and #61703170).
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
Li, K., Huang, H., Zheng, Z., Lu, Y. (2018). Research of Crowed Abnormal Behavior Detection Technology Based on Trajectory Gradient. In: Li, K., Li, W., Chen, Z., Liu, Y. (eds) Computational Intelligence and Intelligent Systems. ISICA 2017. Communications in Computer and Information Science, vol 874. Springer, Singapore. https://doi.org/10.1007/978-981-13-1651-7_43
Download citation
DOI: https://doi.org/10.1007/978-981-13-1651-7_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1650-0
Online ISBN: 978-981-13-1651-7
eBook Packages: Computer ScienceComputer Science (R0)