Abstract
Aiming at the problem of automatic detection of normal operation behavior in self-service business management, with improved motion history image as input, a recognition method of convolutional neural network is proposed to timely judge the occurrence of anomie behavior. Firstly, the key frame sequence was extracted from the self-service operation video based on the method of uniform energy down-sampling. Secondly, combined with the timing information of key frames to adaptively estimate the decay parameters of the motion history image, adding information contrast to generating a logic matrix can improve the calculation speed of the improved motion history image. Finally, the formed motion history image was input into the established convolutional neural network to obtain the class of self-service behavior and distinguish anomie behavior. In real scenarios of self-service baggage check-in for civil aviation passengers, the typical check-in behavior data set is established and tested in actual self-service baggage check-in system of the airport. The results show that the method proposed can effectively identify typical anomie behaviors and has high practical value.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dong, H., Wang, W., Gao, Q., Luo, Q.: Transmission control strategy for self-service baggage checking system based on petri net. Control Eng. China 21(01), 14–17 + 22 (2014)
Xu, G., Cao, Y.: Action recognition and activity understanding: a review. J. Image Graph. 14(02), 189–195 (2009)
Ding, C.-Y., Liu, K., Li, G., Yan, L., Chen, B.-Y., Zhong, Y.-M.: Spatio-temporal weighted posture motion features for human skeleton action recognition research. Chin. J. Comput. 43(1), 29–40 (2020)
Fan, Z., Zhao, X., Lin, T.: Attention-based multiview re-observation fusion network for skeletal action recognition. IEEE Trans. Multimedia 21(2), 363–374 (2019)
Yang, Y., Deng, C., Gao, S., Liu, W., Tao, D., Gao, X.: Discriminative multi-instance multitask learning for 3D action recognition. IEEE Trans. Multimedia (S1520-9210) 19(3), 519–529 (2017)
Kim, Y.-S., Yoon, J.-C., Lee, I.-K.: Real-time human segmentation from RGB-D video sequence based on adaptive geodesic distance computation. Multimedia Tools Appl. 78(20), 28409–28421 (2017). https://doi.org/10.1007/s11042-017-5375-5
Qian, L., Li, P., Huang, L.: An adaptive algorithm for activity recognition with evolving data streams. Chin. J. Sens. Actuators 30(6), 909–915 (2017)
Tran, D., Bourdev, L., Fergus, R.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489–4497 (2015)
Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533–5541 (2017)
Zhou, Y., Sun, X., Zha, Z.J.: Mict: Mixed 3D/2D convolutional tube for human action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 449–458 (2018)
Wei, X., Le, Y., Han, J., Lu, Y.: Vehicle behavior dynamic recognition network based on long short-term memory. J. Comput. Appl. 39(07), 1894–1898 (2019)
Shi, X., Liu, S., Zhang, D.: Human action recognition method based on key frames. J. Syst. Simul. 27(10), 2401–2408 (2015)
Zhao, Q., Sun, Y.: 3D tracking algorithm for quickly locating image scales and regions. J. Image Graph. 21(1), 114–121 (2016)
Xie, L., Yu, S., Zhou, G., Li, H.: Classification research of oil-tea pest images based on BOW model. J. Central South Univ. Forestry Technol. 35(05), 70–73 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Deng, L., Gao, Q., Xu, D. (2020). Self-service Behavior Recognition Algorithm Based on Improved Motion History Image Network. In: Zeng, J., Jing, W., Song, X., Lu, Z. (eds) Data Science. ICPCSEE 2020. Communications in Computer and Information Science, vol 1257. Springer, Singapore. https://doi.org/10.1007/978-981-15-7981-3_34
Download citation
DOI: https://doi.org/10.1007/978-981-15-7981-3_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7980-6
Online ISBN: 978-981-15-7981-3
eBook Packages: Computer ScienceComputer Science (R0)