Abstract
With the development of public security awareness, anomaly detection has become a crucial demand in surveillance videos. To improve the accuracy of abnormal events detection, this paper proposes a novel spatio-temporal architecture called spatio-temporal CNN hashing model. In this paper, we propose a novel deep CNN learning framework that can exploit the differential binary motion image data to learn informative hash codes, to accurately classify abnormal events. However, we exploit the feature learning capabilities of CNN architectures to learn representative hash codes to obtain compact binary codes to solve the domain adaptation problem. In order to attain adequate computation for feature distance, we include hashing learning into a deep network. Exactly, a hashing layer is inserted after the last fully connected layer to move to the high-dimension and real-value features into low-dimension and binary features. Extensive experiments on a public available dataset have demonstrated the effectiveness of our framework, which achieves the state-of-the-art performance.
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
References
Ramachandra, B., Jones, M., Vatsavai, R.R.: A survey of single-scene video anomaly detection. IEEE TPAMI 44, 2293–2312 (2020)
Rodrigues, R., Bhargava, N., Velmurugan, R., Chaudhuri, S.: Multi-timescale trajectory prediction for abnormal human activity detection. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2615–2623 (2020)
Luo, W., Liu, W., Gao, S.: A revisit of sparse coding based anomaly detection in stacked rnn framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 341–349 (2017)
Pandey, H., Karnavat, T.L., Sandilya, M., Katiyar, S., Rathore, H.: Intrusion detection system based on machine and deep learning models: a comparative and exhaustive study. In: Abraham, A., et al. (eds.) HIS 2021. LNNS, vol. 420, pp. 407–418. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-96305-7_38
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of BMVC (2014)
Anoopa, S., Salim, A.: Survey on anomaly detection in surveillance videos. Mater. Today Proc. 58, 162–167 (2022)
Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 281–297. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_20
Jalal, A., Kamal, S., Azurdia-Meza, C.A.: Depth maps-based human segmentation and action recognition using full-body plus body color cues via recognizer engine. J. Electr. Eng. Technol. 14(1), 455–461 (2019)
Zin, T.T., Kurohane, J.: Visual analysis framework for two-person interaction. In: IEEE 4th Global Conference on Consumer Electronics (GCCE), pp. 519–520 (2015)
Gnouma, M., Ejbali, R., Zaied, M.: Human fall detection based on block matching and silhouette area. In Ninth International Conference on Machine Vision (ICMV), vol. 10341, pp. 18–22. SPIE (2017)
Ilyas, Z., Aziz, Z., Qasim, T., Bhatti, N., Hayat, M.F.: A hybrid deep network based approach for crowd anomaly detection. Multimedia Tools Appl. 80(16), 24053–24067 (2021). https://doi.org/10.1007/s11042-021-10785-4
Mohtavipour, S.M., Saeidi, M., Arabsorkhi, A.: A multi-stream CNN for deep violence detection in video sequences using handcrafted features. The Visual Computer 38(6), 2057–2072 (2022)
Chu, W., Xue, H., Yao, C., Cai, D.: Sparse coding guided spatiotemporal feature learning for abnormal event detection in large videos. IEEE Trans. Multimedia 21(1), 246–255 (2018)
Gnouma, M., Ejbali, R., Zaied, M.: Video anomaly detection and localization in crowded scenes. In: Martínez Álvarez, F., Troncoso Lora, A., Sáez Muñoz, J.A., Quintián, H., Corchado, E. (eds.) CISIS/ICEUTE -2019. AISC, vol. 951, pp. 87–96. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-20005-3_9
Gnouma, M., Ladjailia, A., Ejbali, R., Zaied, M.: Stacked sparse autoencoder and history of binary motion image for human activity recognition. Multimedia Tools Appl. 78(2), 2157–2179 (2018). https://doi.org/10.1007/s11042-018-6273-1
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS, pp. 1106–1114 (2012)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27, 1–9 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of CVPR, pp. 1–9 (2015)
Avenue Dataset. Detection of unusual crowd activity. http://www.cse.cuhk.edu.hk/leojia/projects/detectabnormal/dataset.html. Accessed 30 Sept 2022
Smeureanu, S., Ionescu, R.T., Popescu, M., Alexe, B.: Deep appearance features for abnormal behavior detection in video. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10485, pp. 779–789. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68548-9_70
Fang, L., Liu, Z., Song, W.: Deep hashing neural networks for hyperspectral image feature extraction. IEEE Geosci. Remote Sens. Lett. 16(9), 1412–1416 (2019)
Del Giorno, A., Bagnell, J.A., Hebert, M.: A discriminative framework for anomaly detection in large videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 334–349. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_21
Li, T., Chen, X., Zhu, F., Zhang, Z., Yan, H.: Two-stream deep spatial-temporal auto-encoder for surveillance video abnormal event detection. Neurocomputing 439, 256–270 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gnouma, M., Ejbali, R., Zaied, M. (2023). Abnormal Event Detection Method Based on Spatiotemporal CNN Hashing Model. In: Abraham, A., Pllana, S., Casalino, G., Ma, K., Bajaj, A. (eds) Intelligent Systems Design and Applications. ISDA 2022. Lecture Notes in Networks and Systems, vol 717. Springer, Cham. https://doi.org/10.1007/978-3-031-35510-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-35510-3_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35509-7
Online ISBN: 978-3-031-35510-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)