Abstract
Anomalous human activity detection is highly essential due to its numerous uses in both public and private safety. Autoencoders-based normality modeling approaches detect some anomalous events as normal activities. We propose an effective strategy Bag-of-Adapted-Model (BoAM)-based approaches that utilize multiple Adapted Gaussian Mixture Models (AGMMs). In the first approach, two base class GMMs are constructed for normal and anomalous event classes. Then, adapted GMMs are constructed using training snippets of normal and anomalous events by adapting the corresponding base class GMMs to derive class-specific characteristics in AGMM. For a given video segment, likelihood-based embeddings provide improved discrimination between normal and anomalous event classes. BoAM can also be created using only normal occurrences of training data, and then, the representations fed to OC-SVM in order to detect outliers. Another variant of BoAM that used Universal Background Model (UBM) as a base model (BoAM_UBM) for adaptation gives comparable performance. Results over three standard datasets proved the consistent improvement. The proposed embeddings are suitable for detecting abnormalities even with smaller amount of anomalous training data.
Similar content being viewed by others
Code availability
The code supporting this work is available from the corresponding author upon valid request.
References
Baby SA, Vinod B, Chinni C, Mitra K (2017) Dynamic vision sensors for human activity recognition. In: 2017 4th IAPR Asian conference on pattern recognition (ACPR), IEEE, p 316–321
Bendersky M, Garcia-Pueyo L, Harmsen J, Josifovski V, Lepikhin D (2014) Up next: retrieval methods for large scale related video suggestion. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, p 1769–1778
Chandrakala S, Deepak K, Vignesh L (2022) Bag-of-event-models based embeddings for detecting anomalies in surveillance videos. Expert Syst Appl 190:116168
Cheng M, Cai K, Li M (2021) Rwf-2000: an open large scale video database for violence detection. In: 2020 25th International conference on pattern recognition (ICPR), IEEE, p 4183–4190
Deepak K, Chandrakala S, Mohan CK (2021) Residual spatiotemporal autoencoder for unsupervised video anomaly detection. Signal Image Video Process 15(1):215–222
Dong F, Zhang Y (2020) Nie X Dual discriminator generative adversarial network for video anomaly detection. IEEE Access 8:88170–88176
Du T, Bourdev L, Fergus R, Torresani L, Paluri M (2014) C3d: generic features for video analysis. Eprint Arxiv
Fang Z, Liang J, Zhou JT, Xiao Y, Yang F (2020) Anomaly detection with bidirectional consistency in videos. IEEE Trans Neural Netw Learn Syst 33:1079–1092
Gauvain JL, Lee CH (1994) Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains. IEEE Trans Speech Audio Process 2(2):291–298
Gong D, Liu L, Le V, Saha B, Mansour MR, Venkatesh S, Hengel AVD (2019) Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE international conference on computer vision, p 1705–1714
Hanson A, Pnvr K, Krishnagopal S, Davis L (2018) Bidirectional convolutional lstm for the detection of violence in videos. In: Proceedings of the European conference on computer vision (ECCV)
Hasan M, Choi J, Neumann J, Roy-Chowdhury AK, Davis LS (2016) Learning temporal regularity in video sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 733–742
Hassner T, Itcher Y, Kliper-Gross O (2012) Violent flows: real-time detection of violent crowd behavior. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops, p 1–6. https://doi.org/10.1109/CVPRW.2012.6239348
Huang C, Wen J, Xu Y, Jiang Q, Yang J, Wang Y, Zhang D (2022) Self-supervised attentive generative adversarial networks for video anomaly detection. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2022.3159538
Huang C, Wu Z, Wen J, Xu Y, Jiang Q, Wang Y (2021) Abnormal event detection using deep contrastive learning for intelligent video surveillance system. IEEE Trans Ind Inform 18(8):5171–5179
Kaltsa V, Briassouli A, Kompatsiaris I, Hadjileontiadis LJ, Strintzis MG (2015) Swarm intelligence for detecting interesting events in crowded environments. IEEE Trans Image Process 24(7):2153–2166
Kamoona AM, Gosta AK, Bab-Hadiashar A, Hoseinnezhad R (2020) Multiple instance-based video anomaly detection using deep temporal encoding-decoding. arXiv preprint arXiv:2007.01548
Khan MUK, Park HS, Kyung CM (2018) Rejecting motion outliers for efficient crowd anomaly detection. IEEE Trans Inf Forensics Secur 14(2):541–556
Kim J, Grauman K (2009) Observe locally, infer globally: a space-time mrf for detecting abnormal activities with incremental updates. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, p 2921–2928
Leyva R, Sanchez V, Li C (2017) Video anomaly detection with compact feature sets for online performance. IEEE Trans Image Process 26(7):3463–3478. https://doi.org/10.1109/TIP.2017.2695105
Leyva R, Sanchez V, Li CT (2017) The lv dataset: a realistic surveillance video dataset for abnormal event detection. In: 2017 5th International workshop on biometrics and forensics (IWBF), IEEE, p 1–6
Li G, Chung W (2018) Combined eeg-gyroscope-tdcs brain machine interface system for early management of driver drowsiness. IEEE Trans Hum Mach Syst 48(1):50–62. https://doi.org/10.1109/THMS.2017.2759808
Li J, Jiang X, Sun T, Xu K (2019) Efficient violence detection using 3d convolutional neural networks. In: 2019 16th IEEE international conference on advanced video and signal based surveillance (AVSS), IEEE, p 1–8
Li N, Chang F (2019) Video anomaly detection and localization via multivariate gaussian fully convolution adversarial autoencoder. Neurocomputing 369:92–105
Li W, Mahadevan V, Vasconcelos N (2013) Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell 36(1):18–32
Lu C, Shi J, Jia J (2013) Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE international conference on computer vision, p 2720–2727
Luo W, Liu W, Gao S (2017) Remembering history with convolutional lstm for anomaly detection. In: 2017 IEEE international conference on multimedia and expo (ICME), IEEE, p 439–444
Luo W, Liu W, Lian D, Tang J, Duan L, Peng X, Gao S (2019) Video anomaly detection with sparse coding inspired deep neural networks. IEEE Trans Pattern Anal Mach Intell 43(3):1070–1084
Nguyen TN, Roy S, Meunier J (2021) Smithnet: strictness on motion-texture coherence for anomaly detection. IEEE Trans Neural Netw Learn Syst 33(6):2287–2300
Nievas E.B, Suarez O.D, García GB, Sukthankar R (2011) Violence detection in video using computer vision techniques. In: International conference on computer analysis of images and patterns, Springer, p 332–339
Ramachandra B, Jones M, Vatsavai R (2020) Learning a distance function with a siamese network to localize anomalies in videos. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, p 2598–2607
Reddy V, Sanderson C, Lovell BC (2011) Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture. In: CVPR 2011 workshops, IEEE, p 55–61
Rodriguez M, Orrite C, Medrano C, Makris D (2016) One-shot learning of human activity with an map adapted gmm and simplex-hmm. IEEE Trans Cybern 47(7):1769–1780
Roshtkhari MJ, Levine MD (2013) An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions. Comput Vis Image Underst 117(10):1436–1452
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Song W, Zhang D, Zhao X, Yu J, Zheng R, Wang A (2019) A novel violent video detection scheme based on modified 3d convolutional neural networks. IEEE Access 7:39172–39179
Sovan B, Babu RV (2013) Real time anomaly detection in h. 264 compressed videos. In: Computer vision, pattern recognition, image processing and graphics (NCVPRIPG), 2013 4th national conference, p 1–4
Sudhakaran S, Lanz O (2017) Learning to detect violent videos using convolutional long short-term memory. CoRR abs/1709.06531
Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 6479–6488
Tian Y, Pang G, Chen Y, Singh R, Verjans JW, Carneiro G (2021) Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE/CVF international conference on computer vision, p 4975–4986
Tziakos I, Cavallaro A, Xu LQ (2010) Local abnormality detection in video using subspace learning. In: 2010 7th IEEE international conference on advanced video and signal based surveillance, IEEE, p 519–525
Uijlings J, Duta IC, Sangineto E, Sebe N (2015) Video classification with densely extracted hog/hof/mbh features: an evaluation of the accuracy/computational efficiency trade-off. Int J Multimed Inf Retr 4(1):33–44
Wang J, Zhang G, Zhang K, Zhao Y, Wang Q, Li X (2020) Detection of small aerial object using random projection feature with region clustering. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2020.3018120
Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision, Springer, p 20–36
Xing P, Li Z (2023) Visual anomaly detection via partition memory bank module and error estimation. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2023.3237562
Xu D, Yan Y, Ricci E, Sebe N (2017) Detecting anomalous events in videos by learning deep representations of appearance and motion. Comput Vis Image Underst 156:117–127
Yang MY, Liao W, Cao Y, Rosenhahn B (2018) Video event recognition and anomaly detection by combining gaussian process and hierarchical dirichlet process models. Photogramm Eng Remote Sens 84(4):203–214
Yuan Y, Xiong Z, Wang Q (2019)VSSA-NET: vertical spatial sequence attention network for traffic sign detection. CoRR abs/1905.01583. http://arxiv.org/abs/1905.01583
Shuai Yuan, Chengli Sun, Haoge Yang (2017) Recognition of aircraft engine sound based on gmm-ubm model. MATEC Web Conf. 128:05011. https://doi.org/10.1051/matecconf/201712805011
Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, p 4694–4702
Zhang S, Gong M, Xie Y, Qin A, Li H, Gao Y, Ong YS (2022) Influence-aware attention networks for anomaly detection in surveillance videos. IEEE Trans Circuits Syst Video Technol 32:5427–5437
Zhang T, Jia W, He X, Yang J (2017) Discriminative dictionary learning with motion weber local descriptor for violence detection. IEEE Trans Circuits Syst Video Technol 27(3):696–709
Zhang T, Jia W, Yang B, Yang J, He X, Zheng Z (2017) Mowld: a robust motion image descriptor for violence detection. Multimed Tools Appl 76(1):1419–1438
Zhang T, Yang Z, Jia W, Yang B, Yang J, He X (2016) A new method for violence detection in surveillance scenes. Multimed Tools Appl 75(12):7327–7349
Zhao Y, Deng B, Shen C, Liu Y, Lu H, Hua XS (2017) Spatio-temporal autoencoder for video anomaly detection. In: Proceedings of the 25th ACM international conference on Multimedia, p 1933–1941
Zhong JX, Li N, Kong W, Liu S, Li TH, Li G (2019) Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, p 1237–1246
Zhong Y, Chen X, Hu Y, Tang P, Ren F (2022) Bidirectional spatio-temporal feature learning with multi-scale evaluation for video anomaly detection. IEEE Trans Circuits Syst Video Technol 32:6058–6072
Zhu H, Liu B, Lu Y, Li W, Yu N (2018) Real-time anomaly detection with hmof feature. In: Proceedings of the 2018 the 2nd international conference on video and image processing, ACM, p 49–54
Zhu Y, Newsam S (2019) Motion-aware feature for improved video anomaly detection. arXiv preprint arXiv:1907.10211
Funding
This work is supported by Cognitive Science Research Initiative, Department of Science & Technology, Government of India, vide No.DST/CSRI/2017/131(G).
Author information
Authors and Affiliations
Contributions
Single author.
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that there is 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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chandrakala, S. Anomalous human activity detection in videos using Bag-of-Adapted-Models-based representation. Pattern Anal Applic 26, 1101–1112 (2023). https://doi.org/10.1007/s10044-023-01177-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-023-01177-5