Abstract
Intelligent detection of abnormal behaviors meets the need of engineering applications for identifying anomalies and alerting operators. However, most existing methods tackle the high-dimensional sequential video data with key frame extraction, which ignore the redundancy effect of inter- and intra- video frames. In this paper, a novel Abnormal Detection method based on double sparseness LSSVMoc (AD_LSSVMoc) is proposed, which combine both sample (i.e. frame) selection and feature selection simultaneously in a uniform sparse model. For the feature extraction, both handcrafted features and learned features are aggregated into effective descriptors. To achieve feature selection and sample selection, a improved LSSVMoc is proposed with sparse primal and dual optimization strategy, and alternating direction method of multipliers is used to solve the constrained linear equations problem raised in AD_LSSVMoc. Experiments show that the proposed AD_LSSVMoc method achieves a competitive detection performance and high detecting speed compared to state-of-the-art methods.
Similar content being viewed by others
References
Adam A, Rivlin E, Shimshoni I, Reinitz D (2008) Robust real-time unusual event detection using multiple fixedlocation monitors. IEEE Trans Pattern Anal Mach Intell 30(3):555–560. https://doi.org/10.1109/TPAMI.2007.70825
Akcay S, Atapourabarghouei A, Breckon T (2018) Ganomaly: semi-supervised anomaly detection via adversarial training. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 622–637. https://doi.org/10.1007/978-3-030-20893-6_39
Amraee S, Vafaei A, Jamshidi K, Adibi P (2018) Abnormal event detection in crowded scenes using one-class svm. Signal Image and Video Process 12(6):1115–1123. https://doi.org/10.1007/s11760-018-1267-z
Asad M, Jiang H, Yang J, Tu E, Malik AA (2021) Multi-stream 3D latent feature clustering for abnormality detection in videos. Appl Intell 145:1–18. https://doi.org/10.1007/s10489-021-02356-9
Barz B, Rodner E, Garcia Y, Denzler J (2019) Detecting regions of maximal divergence for spatio-temporal anomaly detection. IEEE Trans Pattern Anal Mach Intell 41(5):1088–1101. https://doi.org/10.1109/TPAMI.2018.2823766
Batchuluun G, Kim JH, Hong HG, Kang JK, Park KR (2017) Fuzzy system based human behavior recognition by combining behavior prediction and recognition. Expert Syst Appl 81:108–133. https://doi.org/10.1016/j.eswa.2017.03.052
Cao J, Pang Y, Xie J, Khan F, Shao L (2021) From handcrafted to deep features for pedestrian detection: a survey. IEEE Trans Pattern Anal Mach Intell, 1-23. https://doi.org/10.1109/tpami.2021.3076733
Chang H, Wang T, Li A, Fang H (2019) Local hyperspectral anomaly detection method based on low-rank and sparse matrix decomposition. J Appl Remote Sens 13(2):345–352. https://doi.org/10.1117/1.JRS.13.026513
Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. Computer Science pp 1–11. https://doi.org/10.5244/C.28.6
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297.https://doi.org/10.1023/A:1022627411411
Feng Y, Yuan Y, Lu X (2017) Learning deep event models for crowd anomaly detection. Neurocomputing. 219(219):548–556. https://doi.org/10.1016/j.neucom.2016.09.063
Garcia J, Varona L, Leskovsky P, Nieto M (2016) On-line normality modeling and anomaly event detection using spatio-temporal motion patterns. In: Proceeding of International Conference on Imaging for Crime Detection and Prevention, pp. 1–6. https://doi.org/10.1049/ic.2016.0070
George M, Jose B, Mathew J, Kokare P (2019) Autoencoder-based abnormal activity detection using parallelepiped spatio-temporal region. IET Comput Vis 13(1):23–30. https://doi.org/10.1049/iet-cvi.2018.5240
Hou E, Yilmaz Y, Hero A (2019) Anomaly detection in partially observed traffic networks. IEEE Trans Signal Process 67(6):1461–1476. https://doi.org/10.1109/TSP.2019.2892026
Huang G, Yang Z, Chen X, Ji G (2017) An innovative one-class least squares support vector machine model based on continuous cognition. Knowledge Based System 123:217–228. https://doi.org/10.1016/j.knosys.2017.02.024
Ionescu R T, Khan F S, Georgescu M I, Shao L (2019) Object-centric auto-encoders and dummy anomalies for abnormal event detection in video. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7842–7851. https://doi.org/10.1109/CVPR.2019.00803
Jaberi M, Pensky M, Foroosh H (2015) Swift: sparse withdrawal of inliers in a first trial. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition. pp. 4849–4857. https://doi.org/10.1109/CVPR.2015.7299118
Joshi A, Namboodiri V (2019) Unsupervised synthesis of anomalies in videos: transforming the normal. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. https://doi.org/10.1109/IJCNN.2019.8852035
Jvs A, Mg A, Wt B et al (2021) VASP: an autoencoder-based approach for multivariate anomaly detection and robust time series prediction with application in motorsport. Eng Appl Artif Intell 104:1–17. https://doi.org/10.1016/j.engappai.2021.104354
Kim J, Grauman K (2009) Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2928. https://doi.org/10.1109/CVPR.2009.5206569
Kimura D, Narita M, Munawar A, Tachibana R (2019) Spatially-weighted anomaly detection with regression model. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition. pp.1–4
Kittler J, Christmas W, De Campos T, Windridge D, Yan F, Illingworth J, Osman M (2014) Domain anomaly detection in machine perception: a system architecture and taxonomy. IEEE Trans Pattern Anal Mach Intell 36(5):845–859. https://doi.org/10.1109/TPAMI.2013.209
Ko KE, Sim KB (2018) Deep convolutional framework for abnormal behavior detection in a smart surveillance system. Eng Appl Artif Intell 67:226–234. https://doi.org/10.1016/j.engappai.2017.10.001
Lu C, Shi J, Jia J (2014) Abnormal event detection at 150 fps in matlab. In: Proceeding of IEEE International Conference on Computer Vision, pp. 2720–2727 https://doi.org/10.1109/ICCV.2013.338
Ma C, Miao Z, Li M, Song S, Yang M (2018) Detecting anomalous trajectories via recurrent neural networks. In: Proceeding of Asian Conference on Computer Vision, pp. 370–382 https://doi.org/10.1007/978-3-030-20870-7_23
Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, 1975-1981. https://doi.org/10.1109/CVPR.2010.5539872
Mu H, Sun R, Yuan G, Shi G (2021) Positive unlabeled learning-based anomaly detection in videos. Int J Intell Syst, 1-22. https://doi.org/10.1002/int.22437
Mu H, Sun R, Yuan G, Wang Y (2021) Abnormal human behavior detection in videos: a review. Inf Technol Control 50(3):522–545. https://doi.org/10.5755/j01.itc.50.3.27864
Ribeiro M, Lazzaretti A, Lopes H (2018) A study of deep convolutional auto-encoders for anomaly detection in videos. Pattern Recogn Lett 105:13–22. https://doi.org/10.1016/j.patrec.2017.07.016
Rodrigues R, N Bhargava, Velmurugan R, Chaudhuri S (2020) Multi-timescale trajectory prediction for abnormal human activity detection. In: Proceeding of IEEE Winter Conference on Applications of Computer Vision, 2615–2623 https://doi.org/10.1109/WACV45572.2020.9093633
Sodemann A, Ross M, Borghetti B (2012) A review of anomaly detection in automated surveillance. IEEE Trans Syst Man Cybern 42(6):1257–1272. https://doi.org/10.1109/TSMCC.2012.2215319
Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, 6479–6488. https://doi.org/10.1109/CVPR.2018.00678
Sun J, Shao J, He C (2019) Abnormal event detection for video surveillance using deep one-class learning. Multimed Tools Appl 78(3):3633–3647. https://doi.org/10.1007/s11042-017-5244-2
Sun C, Jia YD, Song H, and Wu YW (2021) Adversarial 3D convolutional auto-encoder for abnormal event detection in videos. IEEE Trans Multimedia, PP(99):1-14. https://doi.org/10.1109/TMM.2020.3023303
Wang K, Lan H (2020) Robust support vector data description for novelty detection with contaminated data. Eng Appl Artif Intell 91:103554. https://doi.org/10.1016/j.engappai.2020.103554
Wang T, Chen J, Zhou Y, Snoussi H (2013) Online least squares one-class support vector machines-based abnormal visual event detection. Sensors. 13(12):17130–17155. https://doi.org/10.3390/s131217130
Xu D, Ricci E, Yan Y, Song J, Sebe N (2015) Learning deep representations of appearance and motion for anomalous event detection. In: Proceeding of British Machine Vision Conference on Computer Vision and Image Understanding, 1–18. https://doi.org/10.1016/j.cviu.2016.10.010
Xu K, Jiang X, Sun T (2018) Anomaly detection based on stacked sparse coding with intra-frame classification strategy. IEEE Trans Multimedia 20(5):1062–1074. https://doi.org/10.1109/TMM.2018.2818942
Yu QY, Luo YL, Chen CM, Wang XH (2018) Trajectory outlier detection approach based on common slices sub-sequence. Appl Intell 48:2661–2680. https://doi.org/10.1007/s10489-017-1104-z
Zhang J, Wang K, Zhu W, Zhong P (2015) Least squares fuzzy one-class support vector machine for imbalanced data. International Journal of Signal Processing, Image Processing and Pattern Recognition, 8, 299-308. https://doi.org/10.14257/ijsip.2015.8.8.31
Zhao B, Li F, Xing E (2011) Online detection of unusual events in videos via dynamic sparse coding. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3313–3320. https://doi.org/10.1109/CVPR.2011.5995524
Zhao Y, Xi P, Li B, Li Z (2018) Sparse kernel minimum squared error using householder transformation and givens rotation. Appl Artif Intell 48(2):390–415. https://doi.org/10.1007/s10489-017-0978-0
Zhao YP, Xie YL, Ye ZF (2021) A new dynamic radius SVDD for fault detection of aircraft engine. Eng Appl Artif Intell 100:104177. https://doi.org/10.1016/j.engappai.2021.104177
Zhou J, Du J, Zhu H, Peng X, Liu Y, Goh R (2019) Anomalynet: an anomaly detection network for video surveillance. IEEE Trans Inf Forensics Secur 14(10):2537–2550. https://doi.org/10.1109/TIFS.2019.2900907
Acknowledgments
This work described in this paper was supported by the National Key Research and Development Program of China (grant no. 2016YFB0501805) and the Project of Research and Integrated Demonstration on the Technology of Unmanned Driving and Autonomous Operation of Agricultural Machinery (grant no. Z201100008020008).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mu, H., Sun, R., Chen, Z. et al. Intelligent abnormal behavior detection using double sparseness method. Appl Intell 53, 7728–7740 (2023). https://doi.org/10.1007/s10489-022-03903-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03903-8