Abstract
Fast and automated recognizing of abnormal behaviors in crowded scenes is significantly effective in increasing public security. The traditional procedure of recognizing abnormalities in the Web of Thing (WoT) platform comprises monitoring the activities and describing the crowd properties such as density, trajectory, and motion pattern from the visual frames. Accordingly, incorporating real-time security monitoring based on the WoT platform and machine learning algorithms would significantly enhance the influential detection of abnormal behaviors in the crowds. This paper addresses various automatic and real-time surveillance methods for abnormal event detection to recognize the dynamic crowd behavior in security applications. The critical aspect of security and protection of public places is that we cannot manually monitor the unpredictable and complex crowded environments. The abnormal behavior algorithms have attempted to improve efficiency, robustness against pixel occlusion, generalizability, computational complexity, and execution time. Similar to the state-of-the-art abnormal behavior detection of crowded scenes, we broadly classified methods into different categories such as tracking, classification based on handcrafted extracted features, classification based on deep learning, and hybrid approaches. Hybrid and deep learning methods have been found to have more satisfactory results in the classification stage. A set of video frames called Motion Emotion Dataset (MED) is employed in this study to examine the various conditions governing these methods. Incorporating an appropriate real-time approach with considering WoT platform can facilitate the analysis of crowd and individuals’ behavior for security screening of abnormal events.
Similar content being viewed by others
References
Varghese EB, Thampi SM (2020) Towards the cognitive and psychological perspectives of crowd behaviour: a vision-based analysis. Connect Sci 3:1–26
Yuan Y, Fang J, Wang Q (2014) Online anomaly detection in crowd scenes via structure analysis. IEEE transactions on cybernetics 45(3):548–561
Singh K, Rajora S, Vishwakarma DK, Tripathi G, Kumar S, Walia GS (2020) Crowd anomaly detection using aggregation of ensembles of fine-tuned ConvNets. Neurocomputing. 371:188–198
Mousavi H, Mohammadi S, Perina A, Chellali R, Murino V (2015) Analyzing tracklets for the detection of abnormal crowd behavior. In 2015 IEEE Winter Conference on Applications of Computer Vision (pp. 148-155)
Hatirnaz E, Sah M, Direkoglu C (2020) A novel framework and concept-based semantic search interface for abnormal crowd behaviour analysis in surveillance videos. Multimed Tools Appl 20:1–39
Tripathi G, Singh K, Vishwakarma DK (2019) Convolutional neural networks for crowd behaviour analysis: a survey. Vis Comput 35(5):753–776
Tewell J, O’Sullivan D, Maiden N, Lockerbie J, Stumpf S (2019) Monitoring meaningful activities using small low-cost devices in a smart home. Pers Ubiquit Comput 23(2):339–357
Aguzzi C, Gigli L, Sciullo L, Trotta A, Di Felice M (2020) From cloud to edge: seamless software migration at the era of the web of things. IEEE Access 8:228118–228135
Wang J, Xu Z (2016) Spatio-temporal texture modelling for real-time crowd anomaly detection. Comput Vis Image Underst 144:177–187
Zhang X, Ma D, Yu H, Huang Y, Howell P, Stevens B (2020) Scene perception guided crowd anomaly detection. Neurocomputing. 414:291–302
Fan Z, Yin J, Song Y, Liu Z (2020) Real-time and accurate abnormal behavior detection in videos. Mach Vis Appl 31(7):1–3
Fagette A, Courty N, Racoceanu D, Dufour JY (2014) Unsupervised dense crowd detection by multiscale texture analysis. Pattern Recogn Lett 44:126–133
Lamba S, Nain N (2017) Crowd monitoring and classification: a survey. In Advances in computer and computational sciences (pp. 21-31). Springer, Singapore
Marana AN, Costa LD, Lotufo RA, Velastin SA (1999) Estimating crowd density with Minkowski fractal dimension. In1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No. 99CH36258) (Vol. 6, pp. 3521-3524). IEEE
Alabdulkarim L, Alrajhi W, Aloboud E (2016) Urban analytics in crowd management in the context of Hajj. In International Conference on Social Computing and Social Media (pp. 249-257). Springer, Cham
Ibrion M (2020) Iran: The impact of the beliefscape on the risk culture, resilience and disaster risk governance. Forensic Science and Humanitarian Action: Interacting with the Dead and the Living 10:117–134
Hodgetts HM, Vachon F, Chamberland C, Tremblay S (2017) See no evil: cognitive challenges of security surveillance and monitoring. Journal of applied research in memory and cognition 6(3):230–243
Hao H, Li X, Li M A Detection method of abnormal event in crowds based on image entropy. InProceedings of the 2019 4th International Conference on Intelligent Information Processing 2019 Nov 16 (pp. 362-367)
Steiger C, Walder H, Platzner M (2004) Operating systems for reconfigurable embedded platforms: online scheduling of real-time tasks. IEEE Trans Comput 53(11):1393–1407
Rezaee K, Alavi SR, Madanian M, Ghezelbash MR, Khavari H, Haddadnia J (2013) Real-time intelligent alarm system of driver fatigue based on video sequences. In2013 First RSI/ISM International Conference on Robotics and Mechatronics (ICRoM)Feb 13 (pp. 378-383).
Aldissi B, Ammar H (2020) Real-time frequency-based detection of a panic behavior in human crowds. Multimed Tools Appl 79(33):24851–24871
Kh R, Ghezelbash MR, Haddadnia J, Delbari A (2012) An intelligent surveillance system for falling elderly detection based on video sequences. In19th Iranian Conference of Biomedical Engineering (ICBME), Tehran, Iran Dec (pp. 20-21)
Qasim T, Bhatti N (2019) A low dimensional descriptor for detection of anomalies in crowd videos. Math Comput Simul 166:245–252
Indrusiak LS, Davis RI, Dziurzanski P (2019) Evolutionary optimisation of real-time systems and networks. arXiv preprint arXiv 1905:01888
Hu Y (2020) Design and implementation of abnormal behavior detection based on deep intelligent analysis algorithms in massive video surveillance. Journal of Grid Computing 1:1–1
Leyva R, Sanchez V Li CT. The LV dataset: a realistic surveillance video dataset for abnormal event detection. In2017 5th International Workshop on Biometrics and Forensics (IWBF) 2017 Apr 4 (pp. 1-6). IEEE
Popoola OP, Wang K (2012) Video-based abnormal human behavior recognition—a review. IEEE Transactions on Systems, Man, and Cybernetics. Part C (Applications and Reviews) 42(6):865–878
Mabrouk AB, Zagrouba E (2018 Jan 1) Abnormal behavior recognition for intelligent video surveillance systems: a review. Expert Syst Appl 91:480–491
Wang L, Dong M (2012) Real-time detection of abnormal crowd behavior using a matrix approximation-based approach. In2012 19th IEEE International Conference on Image Processing Sep (pp. 2701-2704). IEEE.
Ryan D, Denman S, Fookes C, Sridharan S (2011) Textures of optical flow for real-time anomaly detection in crowds. In2011 8th IEEE international conference on advanced video and signal based surveillance (AVSS) Aug 30 (pp. 230-235). IEEE
Ihaddadene N, Djeraba C (2008) Real-time crowd motion analysis. In2008 19th International Conference on Pattern Recognition Dec 8 (pp. 1-4). IEEE
Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model. In2009 IEEE Conference on Computer Vision and Pattern Recognition Jun 20 (pp. 935-942). IEEE
Bay H, Tuytelaars T, Van Gool L (2006) SURF: speeded up robust features. InEuropean conference on computer vision (pp. 404-417). Springer, Berlin, Heidelberg
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Boghossian BA, Velastin SA (1999) Motion-based machine vision techniques for the management of large crowds. InICECS'99. Proceedings of ICECS'99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No. 99EX357) (Vol. 2, pp. 961-964). IEEE
Wang B, Ye M, Li X, Zhao F, Ding J (2012) Abnormal crowd behavior detection using high-frequency and spatio-temporal features. Mach Vis Appl 23(3):501–511
Horn BK, Schunck BG (1981) Determining optical flow. InTechniques and Applications of Image Understanding (Vol. 281, pp. 319-331). International Society for Optics and Photonics
Beauchemin SS, Barron JL (1995) The computation of optical flow. ACM computing surveys (CSUR) 27(3):433–466
Rezaee K, Haddadnia J, Delbari A (2015) Modeling abnormal walking of the elderly to predict risk of the falls using Kalman filter and motion estimation approach. Comput Electr Eng 46:471–486
Ravanbakhsh M, Nabi M, Mousavi H, Sangineto E, Sebe N (2018) Plug-and-play CNN for crowd motion analysis: an application in abnormal event detection. In2018 IEEE Winter Conference on Applications of Computer Vision (WACV) pp. 1689-1698). IEEE
Sabokrou M, Fathy M, Hoseini M, Klette R (2015) Real-time anomaly detection and localization in crowded scenes. InProceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 56-62).
Chen YC, Su CT (2016) Distance-based margin support vector machine for classification. Appl Math Comput 283:141–152
Li W, Mahadevan V, Vasconcelos N (2013) Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Mach Intell 36(1):18–32
Yu J, Gwak J, Jeon M (2016) Gaussian-Poisson mixture model for anomaly detection of crowd behaviour. In2016 International Conference on Control, Automation and Information Sciences (ICCAIS) (pp. 106-111). IEEE
Lim KL, Wang H, Mou X (2016) Learning Gaussian mixture model with a maximization-maximization algorithm for image classification. In2016 12th IEEE International Conference on Control and Automation (ICCA) pp. 887-891). IEEE
Leyva R, Sanchez V, Li CT (2017) Video anomaly detection with compact feature sets for online performance. IEEE Trans Image Process 26(7):3463–3478
Lu C, Shi J, Wang W, Jia J (2019) Fast abnormal event detection. Int J Comput Vis 127(8):993–1011
Marsden M, McGuinness K, Little S, O'Connor NE (2016) Holistic features for real-time crowd behaviour anomaly detection. IEEE International Conference on Image Processing (ICIP):918–922 IEEE
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
Pennisi A, Bloisi DD, Iocchi L (2016) Online real-time crowd behavior detection in video sequences. Comput Vis Image Underst 144:166–176
Wang Q, Ma Q, Luo CH, Liu HY, Zhang CL (2016) Hybrid histogram of oriented optical flow for abnormal behavior detection in crowd scenes. Int J Pattern Recognit Artif Intell 30(02):1655007
Cai Y, Wang H, Chen X, Jiang H (2015) Trajectory-based anomalous behaviour detection for intelligent traffic surveillance. IET Intell Transp Syst 9(8):810–816
Zhu G, Song K, Zhang P, Wang L (2016) A traffic flow state transition model for urban road network based on Hidden Markov Model. Neurocomputing. 214:567–574
Kwon Y, Kang K, Jin J, Moon J, Park J (2017) Hierarchically linked infinite hidden Markov model based trajectory analysis and semantic region retrieval in a trajectory dataset. Expert Syst Appl 78:386–395
Sun S, Zhao J, Gao Q (2015) Modeling and recognizing human trajectories with beta process hidden Markov models. Pattern Recogn 48(8):2407–2417
Ding W, Liu K, Fu X, Cheng F (2016) Profile HMMs for skeleton-based human action recognition. Signal Process Image Commun 42:109–119
Zhou L, Li W, Ogunbona P, Zhang Z (2017) Semantic action recognition by learning a pose lexicon. Pattern Recogn 72:548–562
Wang Y, Zhang X, Li M, Jiang P, Wang F (2015) A GM-HMM based abnormal pedestrian behavior detection method. IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC):1, IEEE–6
Zheng CH, Pei WJ, Yan Q, Chong YW (2017 Mar 8) Pedestrian detection based on gradient and texture feature integration. Neurocomputing. 228:71–78
Güngör E, Özmen A (2017 Mar 1) Distance and density based clustering algorithm using Gaussian kernel. Expert Syst Appl 69:10–20
Zang X, Li G, Li Z, Li N, Wang W (2016) An object-aware anomaly detection and localization in surveillance videos. IEEE Second International Conference on Multimedia Big Data (BigMM):113–116 IEEE
Wang X, Fan B, Chang S, Wang Z, Liu X, Tao D, Huang TS (2017) Greedy batch-based minimum-cost flows for tracking multiple objects. IEEE Trans Image Process 26(10):4765–4776
Zhou S, Shen W, Zeng D, Zhang Z (2015) Unusual event detection in crowded scenes by trajectory analysis. In2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1300-1304). IEEE
Afiq AA, Zakariya MA, Saad MN, Nurfarzana AA, Khir MH, Fadzil AF, Jale A, Gunawan W, Izuddin ZA, Faizari M (2019) A review on classifying abnormal behavior in crowd scene. J Vis Commun Image Represent 58:285–303
Fradi H, Luvison B, Pham QC (2016) Crowd behavior analysis using local mid-level visual descriptors. IEEE Transactions on Circuits and Systems for Video Technology 27(3):589–602
Biswas S, Babu RV (2017) Anomaly detection via short local trajectories. Neurocomputing. 242:63–72
Luo X, Tan H, Guan Q, Liu T, Zhuo HH, Shen B (2016) Abnormal activity detection using pyroelectric infrared sensors. Sensors. 16(6):822
Zweng A, Kampel M (2010) Unexpected human behavior recognition in image sequences using multiple features. In2010 20th International Conference on Pattern Recognition (pp. 368-371). IEEE.
Xiang T, Gong S (2008) Video behavior profiling for anomaly detection. IEEE Trans Pattern Anal Mach Intell 30(5):893–908
Saligrama V, Konrad J, Jodoin PM (2010) Video anomaly identification. IEEE Signal Process Mag 27(5):18–33
Wang X, Ma X, Grimson WE (2008) Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models. IEEE Trans Pattern Anal Mach Intell 31(3):539–555
Simon C, Meessen J, De Vleeschouwer C (2010) Visual event recognition using decision trees. Multimed Tools Appl 50(1):95–121
Johnson N, Hogg D (1996) Learning the distribution of object trajectories for event recognition. Image Vis Comput 14(8):609–615
Yilmaz A, Javed O, Shah M (2004) Object tracking: a survey. Acm computing surveys (CSUR). 2006 Dec 25;38(4):13-es
Junejo IN, Javed O, Shah M (2004) Multi feature path modeling for video surveillance. InProceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. (Vol. 2, pp. 716-719). IEEE
Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).;34(3):334-52
Fu Z, Hu W, Tan T (2005) Similarity based vehicle trajectory clustering and anomaly detection. InIEEE International Conference on Image Processing 2005 Sep 14 (Vol. 2, pp. II-602). Ieee
Piciarelli C, Micheloni C, Foresti GL (2008) Trajectory-based anomalous event detection. IEEE transactions on circuits and systems for video technology 18(11):1544–1554
Kumar P, Ranganath S, Weimin H, Sengupta K (2005) Framework for real-time behavior interpretation from traffic video. IEEE Trans Intell Transp Syst 6(1):43–53
Vaswani N, Roy-Chowdhury AK, Chellappa R (2005) “ Shape activity”: a continuous-state HMM for moving/deforming shapes with application to abnormal activity detection. IEEE Trans Image Process 14(10):1603–1616
Zou J, Ye Q, Cui Y, Wan F, Fu K, Jiao J (2016) Collective motion pattern inference via locally consistent latent Dirichlet allocation. Neurocomputing. 184:221–231
Chaker R, Al Aghbari Z, Junejo IN (2017) Social network model for crowd anomaly detection and localization. Pattern Recogn 61:266–281
Singh D, Mohan CK (2017) Graph formulation of video activities for abnormal activity recognition. Pattern Recogn 65:265–272
Riveiro M, Lebram M, Elmer M (2017) Anomaly detection for road traffic: a visual analytics framework. IEEE Trans Intell Transp Syst 18(8):2260–2270
Yan W, Zou Z, Xie J, Liu T, Li P (2018) The detecting of abnormal crowd activities based on motion vector. Optik. 166:248–256
Swathi HY, Shivakumar G, Mohana HS (2017) Crowd behavior analysis: a survey. In2017 international conference on recent advances in electronics and communication technology (ICRAECT) (pp. 169-178). IEEE.
Contractor U, Dixit C, Mahajan D (2018) CNNs for surveillance footage scene classification. arXiv preprint arXiv 1809:02766
Kotapalle GR, Kotni S (2018) Security using image processing and deep convolutional neural networks. In2018 IEEE International Conference on Innovative Research and Development (ICIRD) pp. 1-6). IEEE
Xie S, Zhang X, Cai J (2019) Video crowd detection and abnormal behavior model detection based on machine learning method. Neural Comput & Applic 31(1):175–184
Zhou S, Shen W, Zeng D, Fang M, Wei Y, Zhang Z (2016) Spatial–temporal convolutional neural networks for anomaly detection and localization in crowded scenes. Signal Process Image Commun 47:358–368
Liu M, Li S, Shan S, Wang R, Chen X (2014) Deeply learning deformable facial action parts model for dynamic expression analysis. InAsian conference on computer vision (pp. 143-157). Springer, Cham
Hu Y, Chang H, Nian F, Wang Y, Li T (2016) Dense crowd counting from still images with convolutional neural networks. J Vis Commun Image Represent 38:530–539
Shao J, Loy CC, Kang K, Wang X (2016) Slicing convolutional neural network for crowd video understanding. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5620-5628)
Zitouni MS, Sluzek A, Bhaskar H (2019) Visual analysis of socio-cognitive crowd behaviors for surveillance: a survey and categorization of trends and methods. Eng Appl Artif Intell 82:294–312
Yi S, Li H, Wang X (2016) Pedestrian behavior understanding and prediction with deep neural networks. InEuropean Conference on Computer Vision Oct 8 (pp. 263-279). Springer, Cham
Rezaee K, Badiei A, Meshgini S (2020) A hybrid deep transfer learning based approach for COVID-19 classification in chest X-ray images. In2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME) (pp. 234-241)
Chaturvedi I, Ong YS, Arumugam RV (2015) Deep transfer learning for classification of time-delayed Gaussian networks. Signal Process 110:250–262
Bendali-Braham M, Weber J, Forestier G, Idoumghar L, Muller PA (2019) Transfer learning for the classification of video-recorded crowd movements. In2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) (pp. 271-276)
Da Silva FL, Costa AH (2019) A survey on transfer learning for multiagent reinforcement learning systems. J Artif Intell Res 64:645–703
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 25:1097–1105
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778)
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9)
Canziani A, Paszke A, Culurciello E (2016) An analysis of deep neural network models for practical applications. arXiv preprint arXiv 1605:07678
Ballester P, Araujo R(2016) On the performance of GoogLeNet and AlexNet applied to sketches. InProceedings of the AAAI Conference on Artificial Intelligence (Vol. 30, No. 1)
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 1409:1556
Sánchez FL, Hupont I, Tabik S, Herrera F (2020) Revisiting crowd behaviour analysis through deep learning: taxonomy, anomaly detection, crowd emotions, datasets, opportunities and prospects. Information Fusion 29
Keçeli AS, Kaya AY (2017 Jun 20) Violent activity detection with transfer learning method. Electron Lett 53(15):1047–1048
Rabiee H, Haddadnia J, Mousavi H, Kalantarzadeh M, Nabi M, Murino V (2016) Novel dataset for fine-grained abnormal behavior understanding in crowd. In2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) Aug 23 (pp. 95-101). IEEE
Khan G, Farooq MA, Hussain J, Tariq Z, Khan MU (2019) Categorization of crowd varieties using deep concurrent convolution neural network. In2019 2nd International Conference on Advancements in Computational Sciences (ICACS) Feb 18 (pp. 1-6). IEEE
Yogameena B, Komagal E, Archana M, Abhaikumar SR (2010) Support vector machine-based human behavior classification in crowd through projection and star skeletonization. J Comput Sci 6(9):1008–1013
Wang T, Snoussi H (2014) Detection of abnormal visual events via global optical flow orientation histogram. IEEE Transactions on Information Forensics and Security 9(6):988–998
Wang T, Snoussi H (2012) Histograms of optical flow orientation for visual abnormal events detection. In2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance Sep 18 (pp. 13-18). IEEE
Yogameena B, Nagananthini C (2017) Computer vision based crowd disaster avoidance system: a survey. International journal of disaster risk reduction 22:95–129
Dupont C, Tobias L, Luvison B (2017) Crowd-11: a dataset for fine grained crowd behaviour analysis. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 9-16)
Rabiee H, Haddadnia J, Mousavi H (2016) Crowd behavior representation: an attribute-based approach. SpringerPlus. 5(1):1–7
Lazaridis L, Dimou A, Daras P (2018) Abnormal behavior detection in crowded scenes using density heatmaps and optical flow. In2018 26th European Signal Processing Conference (EUSIPCO) Sep 3 (pp. 2060-2064). IEEE
Varghese EB, Thampi SM (2018) A deep learning approach to predict crowd behavior based on emotion. InInternational Conference on Smart Multimedia Aug 24 (pp. 296-307). Springer, Cham
Varghese E, Thampi SM, Berretti S (2020) A psychologically inspired fuzzy cognitive deep learning framework to predict crowd behavior. IEEE Trans Affect Comput 13
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
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
Rezaee, K., Rezakhani, S.M., Khosravi, M.R. et al. A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance. Pers Ubiquit Comput 28, 135–151 (2024). https://doi.org/10.1007/s00779-021-01586-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-021-01586-5