Next Article in Journal
Revolutionizing Distance Learning: The Impact of Ontology and the Semantic Web
Previous Article in Journal
Overview of Training LLMs on One Single GPU
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Computer Sciences & Mathematics Forum
Volume 10
Issue 1
10.3390/cmsf2025010015
csmf-logo
Submit to this Journal
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Proceeding Paper

Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024 †

by
Abdellah Dardour
1,
Essaid El Haji
2 and
Mohamed Achkari Begdouri
1
1
SIGL Laboratory, National School of Applied Sciences of Tetouan, Abdelmalek Essaadi University, Tetouan 93030, Morocco
2
Intelligent Automation and BioMed Genomics Laboratory, FST of Tangier, Abdelmalek Essaadi University, Tetouan 93030, Morocco
†
Presented at the International Conference on Sustainable Computing and Green Technologies (SCGT’2025), Larache, Morocco, 14–15 May 2025.
Comput. Sci. Math. Forum 2025, 10(1), 15; https://doi.org/10.3390/cmsf2025010015
Published: 16 June 2025
(This article belongs to the Proceedings of International Conference on Sustainable Computing and Green Technologies (SCGT’2025))
Browse Figures
Versions Notes

Abstract

The rapid growth of information and communication technologies, in particular big data, artificial intelligence (AI), and the Internet of Things (IoT), has made it possible to make smart cities a tangible reality. In this context, real-time video surveillance plays a crucial role in improving public safety. This article presents a systematic review of studies focused on the detection of acts of aggression and crime in these cities. By studying 100 indexed scientific articles, dating from 2018 to 2024, we examine the most recent methods and techniques, with an emphasis on the use of machine learning and deep learning for the processing of real-time video streams. The works examined cover several technological axes such as convolutional neural networks (CNNs), fog computing, and integrated IoT systems while also addressing issues such as the challenges related to the detection of anomalies, frequently affected by their contextual and uncertain nature. Finally, this article offers suggestions to guide future research, with the aim of improving the accuracy and efficiency of intelligent monitoring systems.

1. Introduction

The great development of information and communications technologies, in particular the rise in big data, the rise in AI, or the extensive use of IoT elements, has made it possible to make smart cities a reality. Real-time video surveillance is a key element of these innovations, playing a crucial role in public safety. Video surveillance systems allow for the continuous analysis of video streams, thus helping to detect potentially dangerous events and to intervene quickly to prevent incidents.
However, the widespread use of surveillance cameras in public and private spaces has generated an urgent need for advanced systems capable of effectively detecting and identifying human activities and other relevant elements in video recordings. The large amount of data produced by these video streams represent a major challenge concerning the analysis and extraction in real time of the relevant information, making it possible to effectively detect the events of aggression or offense. This highlights the need to design robust and fast models capable of processing large volumes of data in real time. The importance of these systems lies in their ability to prevent incidents, respond more effectively, and strengthen security in public places. In general, the main objective of these systems is to detect visual anomalies quickly and accurately, such as acts of violence, assaults, or even traffic violations and accidents. However, the detection of these anomalies remains a complex task, since they can include a wide range of behaviors, which makes their identification difficult and often ambiguous.
In the jargon of scientific research, the term “anomaly” is often linked to terms like “deviation” or “unusual behavior”. The definition of video anomalies is particularly difficult due to their ambiguous nature, which can vary depending on the context and practical conditions. For example, a behavior such as walking on an area may seem normal in some situations but be perceived as suspicious in others, thus making it difficult to create a universal model for the detection of anomalies [1].
The literature review, focusing on the detection of aggressive and violent behaviors in smart cities, covers an impressive number of works focusing on specific tasks, such as the detection of violence, fire, or smoke. However, the generic detection of anomalies remains difficult due to the absence of an exact or universal definition of an anomaly in various contexts [1,2,3].
The objective of this article is to offer a complete and in-depth analysis of the progress made and research carried out in the field of the detection of aggression and offense events within smart cities. It examines existing methods and technologies for analyzing and extracting relevant information from real-time video streams, highlighting recent progress, the most promising strategies, and the challenges ahead. The aim of this literature review is to establish a detailed and recent state of the art of scientific work concerning the detection of anomalies in real-time video streams.
This article is structured into six sections: Section 2, Related Work, presents some recent and similar works relevant to our research. Section 3 proposes a literature review, gathering and analyzing the relevant studies published between 2018 and 2024. Section 4 describes the methodology adopted, including research questions (Section 4.1), data collection (Section 4.2), and data exploration. Section 5 presents the results of the critical analyses of the articles studied, accompanied by an in-depth discussion aimed at answering the research questions raised. Finally, this article concludes with Section 6, which offers recommendations for future research.

2. Related Work

The academic literature documents numerous studies examining smart cities and related technologies, particularly those focused on anomaly detection in surveillance video streams. These studies primarily aim to enhance quality of life through intelligent solutions applied to public safety, emergency management, traffic accident reduction, and crime prevention [4].
To analyze video footage captured in urban environments, researchers frequently employ artificial intelligence techniques, including machine learning and deep learning, to identify critical incidents. However, the very concept of a “smart city” remains debated, and no universally accepted architectural framework yet exists.
Publications such as those by [5,6] categorize different interpretations of smart cities and compare data processing infrastructures, including cloud, fog, and edge computing. Meanwhile, ref. [7] explores the challenges related to data privacy, urban infrastructure security, and citizen adoption of connected services while also highlighting potential operational vulnerabilities.
Regarding video analytics, the works of [8,9] evaluate the methods for detecting violent or suspicious behavior, demonstrating the superior performance of CNNs. A recent study by [10] provides an overview of deep learning algorithms (CNNs, RNNs, LSTMs, AEs, GANs) used to identify unusual events in urban settings, with a focus on applications such as fires, acts of violence, and traffic disruptions.

3. Literature Review

The literature on smart cities covers a wide range of topics, including security, infrastructure management, and crisis response. Several studies focus on intelligent technologies for crisis management, particularly during the COVID-19 pandemic [11], and the use of crowdsourcing for service provision [12]. Surveillance systems with smart cameras for road safety and abnormal behavior detection have also been explored [13], as well as the use of social networks to assess security risks [3]. Research has also investigated IoT-based solutions, such as Raspberry Pi and ESP-32 devices, for real-time abnormal movement detection [14]. Other studies examine the evolution of video data processing in surveillance systems [15], satellite data for detecting thermal anomalies [2], and the use of UAVs for traffic control and infrastructure inspection [16]. IoT and ICT technologies are fundamental for addressing challenges in terms of security, environmental management, and agriculture [17]. In terms of anomaly detection, deep learning methods like CNN and LSTM have proven to be effective for identifying violent behavior [18], while other studies [19] review various deep learning approaches. Recent studies also focus on cybercrime detection in IoT systems using machine learning [20,21]. The literature on video anomaly detection [22] and traffic event classification [23] further highlights various deep learning models, including those for urban fire detection [24]. The integration of IoT and image processing for real-time fire detection [25] and smart city security [26] is also examined. Additionally, research on energy efficiency in smart cities focuses on reducing IoT node consumption [27]. The combination of IoT, big data, cloud computing, and video streaming is key for improving urban management and public safety [28], while the integration of natural resources and smart technologies supports sustainable development [29]. Studies from various regions, including Saudi Arabia [30] and Africa [31], emphasize community involvement in smart city development. Real-time data analysis from social networks for crisis detection [32] and intelligent traffic management via visual sensor networks [33] are also explored. Finally, IoT security, crime detection, and real-time abnormal event detection using machine learning and big data are central to addressing the challenges in smart city security [34,35,36].

4. Methodology

This study aimed to answer frequently asked questions about smart cities and the analysis and extraction of anomalies in real time from the video stream. The specific questions are as follows: What is the current situation in this context? What are the most popular areas to spot video anomalies? What are the methods and approaches used to solve the problems of detecting assaults and offenses in urban areas?
The major challenge is to advance research aimed at detecting real-time incidents of aggression and crime in smart cities. To answer these questions, this study used a systematic review of the existing literature to analyze in depth the empirical work carried out in this area. A systematic approach was adopted to extract and select the articles reviewed in this study.

4.1. Data Collection

The main objective of this study was to access articles that gave a real overview of the methods for detecting specific anomalies, such as assaults, offenses, fires, and accidents in smart cities. The search for articles in the databases took place in two phases: First, we used the titles, abstracts, and keywords. Then, we resorted to an advanced search method, using Boolean logical operators to improve the results. The keywords used included terms such as “detection of aggression or offense in smart cities”, “detection of events from the video stream in real time”, and other similar logical combinations.
The most relevant articles have been selected according to their quality and their relevance to the objectives of this systematic review.
For this research, we have chosen articles from several university databases recognized for their completeness and reliability. These platforms include ScienceDirect, Scopus, SpringerLink, IEEE Xplore, ResearchGate, SAGE Journals, and Google Scholar as examples. These platforms have been chosen particularly for their ability to offer a wide range of scientific literature while ensuring access to excellent-quality resources, crucial to guarantee the accuracy and validity of the documentary analysis.

4.2. Data Exploration and Analysis

Several research questions have been identified to structure this analysis: What are the existing methods for the detection of aggression and offense events based on video in smart cities? What are the most popular and studied approaches? Which machine learning and deep learning approaches are most frequently used? What are the most widespread areas of application?
To answer these questions, a corpus of 100 scientific articles has been assembled. The selection of publications has been restricted to journal and conference articles published between 2018 and 2024, in order to guarantee an up-to-date synthesis of the research results. The work began with an in-depth study of smart cities, then by detecting unusual events in these urban environments using video streams, and finally by analyzing and extracting unusual events in other contexts.
The selected articles were then classified according to their year of publication, their impact factor, and the area covered, and this information was presented in the form of graphs and tables. In order to analyze the publications in detail, a manual review of the articles was carried out using Excel software to process and extract the relevant data necessary to answer the research questions.

5. Results and Discussion

In this section, we present the results of the detailed study of the 100 scientific articles collected for this work. The aim of this study is to address the key issues related to the detection of aggression and crime events based on video, highlighting the trends, popular approaches, and most commonly used techniques in smart cities.
Figure 1 shows the distribution of articles according to their year of publication, testifying to a significant progression of research in this sector over the last three decades. In the years 2020, 2021, and, more specifically, in 2023, there is an increase in the number of publications, with 22 articles, which makes it the most important year in this journal. This progression illustrates the increasing importance of the detection of aggression and crime events in smart cities, as well as the rapid evolution of associated technologies. These results confirm the rise in smart cities and the essential role played by video surveillance supported by machine learning and deep learning methods to guarantee the safety and efficiency of urban services.
The articles selected for this study were sourced from several databases that enhance the credibility of the sources and the completeness of the literature review. Among the consulted databases, which encompass a variety of articles, are ScienceDirect, Scopus, SpringerLink, IEEE Xplore, ResearchGate, SAGE Journals, and Google Scholar. As shown in Figure 2, ScienceDirect stands out as the primary source with 54 articles extracted, accounting for more than half of the selected references. This predominance reflects the extensive coverage and high-quality articles available on ScienceDirect, making it a key database for studies related to technologies in smart cities.
Regarding the quality of the journals, most of the articles selected in this research come from journals with a significant impact factor, generally divided into categories Q1 and Q2. As shown in Figure 3, 67 articles come from journals classified as Q1 and 21 articles from Q2 journals. This distribution testifies to the determination to base this research on high-quality academic work, endowed with a more significant scientific rigor. The small percentage of articles from journals ranked Q3 and Q4 confirms the importance given to the most significant and outstanding articles in this sector. This selection contributes to ensuring a thorough and precise analysis of the methods for detecting aggression and crime events in smart cities.
The results of the analysis of the literature articles highlight a multitude of fields of application for technologies for detecting and extracting abnormal events, in particular those related to violence and aggression. Figure 4 presents a variety of areas of interest, including the detection of textual aggression [37], the monitoring of anomalies in road traffic and the detection of accidents [23,38,39,40,41,42,43,44], as well as solutions to strengthen security in urban environments [3,7,9,42,45,46,47,48,49,50]. These different areas demonstrate the extent of the adoption of these technologies in various contexts, ranging from the moderation of online platforms to the proactive management of risks in physical environments. They also confirm their growing relevance for decision-makers and security managers, helping not only to quickly identify deviant behaviors but also to introduce preventive measures to improve urban safety and reduce the dangers linked to violent or risky behaviors.
The analysis of the literature articles reveals several methods developed for the detection of abnormal events in video streams, divided into three main categories: classical methods, approaches based on machine learning, and those based on deep learning. As shown in Figure 5, the conventional methods focus essentially on the extraction of particular characteristics, such as optical character recognition (OCR) [51], motion paths [52], and frame segmentation [53]. These techniques are often based on predefined rules and manual feature extractions, offering a robust approach for simple cases but with limitations in more dynamic contexts.
However, machine learning- and deep learning-based methods use annotated training datasets to fit their models, which improves the accuracy of predictions and classifications. In the analyzed literature, the ML methods frequently employed include SVM [8,41,54], random forest [45], clustering [55], KNN [56], and logistic regression [57]. These algorithms facilitate the detection of patterns and anomalies via supervised or unsupervised algorithms, well suited for complex data analysis due to their ability to generalize specific information from training data.
In addition, DL approaches are commonly used in recent research, given their ability to analyze complex video data in depth. The most commonly used algorithms include autoencoders [58,59], two-stream neural networks [60], recurrent neural networks (RNNs) [61,62], convolutional neural networks (CNNs) [1,24,60,63,64,65,66,67,68,69,70,71], and LSTM [18,63,72,73]. These models have significantly improved the accuracy and speed of anomaly detection thanks to their ability to automatically extract important characteristics from video data. In addition, some articles parallel the performance of various DL and ML methods, with DRL [74] demonstrating that hybrid models can sometimes exceed individual models in terms of efficiency [37,40].
However, despite the notable advances, the detection of real-time anomalies in surveillance videos still faces considerable obstacles. Among the main obstacles are privacy concerns, since the collection and analysis of video data can threaten the confidentiality of the individuals being monitored. Moreover, the absence of available and diversified data in certain geographical areas restricts the effectiveness of the models, leading to uneven performance and, often, delays in the field. These challenges highlight the need for advances in ethical data collection and the development of robust models capable of operating effectively in limited data conditions while respecting privacy concerns.

6. Conclusions

This article systematically examines recent scientific publications (2018–2024) on the automatic identification of aggression and crime events within ecosystems in smart cities. This study focuses more specifically on the instantaneous detection of criminal offenses and manifestations of violence in surveillance video sequences.
The study of more than 100 articles from recognized scientific databases has made it possible to identify several key trends: the increasing adoption of AI, in particular deep learning techniques (CNN, RNN, LSTM, GAN), the integration of IoT to enrich data flows, as well as the use of distributed architectures such as cloud and fog computing.
The strengths of the existing studies are found in the variety of technical methods, the increase in the accuracy of the models, and the progressive improvement in the training databases. However, several weaknesses persist: the absence of a clear definition of the anomaly, the limited performance in real conditions (complex urban scenes, noise, low lighting), the dependence on limited or undiversified datasets, and the challenges related to the adaptability of the systems in real conditions.
In order to overcome these shortcomings, future research should aim to develop hybrid models that incorporate computer vision, IoT sensors, and decision-making systems while constituting datasets more appropriate to concrete urban situations. It is also crucial to optimize algorithms for real-time processing on devices with limited resources while improving the explainability of artificial intelligence models in order to consolidate user confidence. This analysis, therefore, serves as a useful basis for directing subsequent research towards more efficient, solid, and sustainable solutions concerning the detection of anomalies in smart cities.

Author Contributions

Conceptualization, A.D. and E.E.H.; methodology, A.D.; software, A.D.; validation, A.D., E.E.H. and M.A.B.; formal analysis, E.E.H.; investigation, A.D.; resources, A.D.; data curation, A.D.; writing—original draft preparation, A.D.; writing—review and editing, E.E.H.; visualization, A.D.; supervision, E.E.H.; project administration, E.E.H. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data sharing is not applicable.

Conflicts of Interest

The authors declare no conflicts of interest.

Abbreviations

CNNConvolutional Neural Network
RNNRecurrent Neural Network
LSTMLong Short-Term Memory
GANGenerative Adversarial Network
ICTsInformation and Communication Technologies
IEEEInstitute of Electrical and Electronics Engineers

References

  1. Yang, Y.; Fu, Z.; Naqvi, S.M. Abnormal event detection for video surveillance using an enhanced two-stream fusion method. Neurocomputing 2023, 553, 126561. [Google Scholar] [CrossRef]
  2. Liu, L.; Li, C.; Sun, X.; Zhao, J. Event alert and detection in smart cities using anomaly information from remote sensing earthquake data. Comput. Commun. 2020, 153, 397–405. [Google Scholar] [CrossRef]
  3. Moustaka, V.; Theodosiou, Z.; Vakali, A.; Kounoudes, A.; Anthopoulos, L.G. Enhancing social networking in smart cities: Privacy and security borderlines. Technol. Forecast. Soc. Chang. 2019, 142, 285–300. [Google Scholar] [CrossRef]
  4. Costa, D.G.; Peixoto, J.P.J.; Jesus, T.C.; Portugal, P.; Vasques, F.; Rangel, E.; Peixoto, M. A Survey of Emergencies Management Systems in Smart Cities. IEEE Access 2022, 10, 61843–61872. [Google Scholar] [CrossRef]
  5. Kashef, M.; Visvizi, A.; Troisi, O. Smart city as a smart service system: Human-computer interaction and smart city surveillance systems. Comput. Hum. Behav. 2021, 124, 106923. [Google Scholar] [CrossRef]
  6. Sánchez-Corcuera, R.; Nuñez-Marcos, A.; Sesma-Solance, J.; Bilbao-Jayo, A.; Mulero, R.; Zulaika, U.; Azkune, G.; Almeida, A. Smart cities survey: Technologies, application domains and challenges for the cities of the future. Int. J. Distrib. Sens. Netw. 2019, 15, 1550147719853984. [Google Scholar] [CrossRef]
  7. Ismagilova, E.; Hughes, L.; Rana, N.P.; Dwivedi, Y.K. Security, Privacy and Risks Within Smart Cities: Literature Review and Development of a Smart City Interaction Framework. Inf. Syst. Front. 2022, 24, 393–414. [Google Scholar] [CrossRef] [PubMed]
  8. Ramzan, M.; Abid, A.; Khan, H.U.; Awan, S.M.; Ismail, A.; Ahmed, M.; Ilyas, M.; Mahmood, A. A Review on State-of-the-Art Violence Detection Techniques. IEEE Access 2019, 7, 107560–107575. [Google Scholar] [CrossRef]
  9. Laufs, J.; Borrion, H.; Bradford, B. Security and the smart city: A systematic review. Sustain. Cities Soc. 2020, 55, 102023. [Google Scholar] [CrossRef]
  10. Samaila, Y.A.; Sebastian, P.; Singh, N.S.S.; Shuaibu, A.N.; Ali, S.S.A.; Amosa, T.I.; Mustafa Abro, G.E.; Shuaibu, I. Video anomaly detection: A systematic review of issues and prospects. Neurocomputing 2024, 591, 127726. [Google Scholar] [CrossRef]
  11. Alshamaila, Y.; Papagiannidis, S.; Alsawalqah, H.; Aljarah, I. Effective use of smart cities in crisis cases: A systematic review of the literature. Int. J. Disaster Risk Reduct. 2023, 85, 103521. [Google Scholar] [CrossRef]
  12. Kumar, H.; Singh, M.K.; Gupta, M.P.; Madaan, J. Moving towards smart cities: Solutions that lead to the Smart City Transformation Framework. Technol. Forecast. Soc. Chang. 2020, 153, 119281. [Google Scholar] [CrossRef]
  13. Iqbal, Z.; Khan, M.I. Automatic incident detection in smart city using multiple traffic flow parameters via V2X communication. Int. J. Distrib. Sens. Netw. 2018, 14, 1550147718815845. [Google Scholar] [CrossRef]
  14. Bibri, S.E. The IoT for smart sustainable cities of the future: An analytical framework for sensor-based big data applications for environmental sustainability. Sustain. Cities Soc. 2018, 38, 230–253. [Google Scholar] [CrossRef]
  15. Khelvas, A.; Demyanova, D.; Gilya-Zetinov, A.; Konyagin, E.; Khafizov, R.; Pashkov, R. Adaptive distributed video surveillance system. In Proceedings of the 2020 International Conference on Technology and Entrepreneurship—Virtual (ICTE-V), San Jose, CA, USA, 20–21 April 2020. [Google Scholar]
  16. Alsamhi, S.H.; Ma, O.; Ansari, M.S.; Almalki, F.A. Survey on Collaborative Smart Drones and Internet of Things for Improving Smartness of Smart Cities. IEEE Access 2019, 7, 128125–128152. [Google Scholar] [CrossRef]
  17. Mohamed, N.; Al-Jaroodi, J.; Jawhar, I.; Idries, A.; Mohammed, F. Unmanned aerial vehicles applications in future smart cities. Technol. Forecast. Soc. Chang. 2020, 153, 119293. [Google Scholar] [CrossRef]
  18. Fenil, E.; Manogaran, G.; Vivekananda, G.N.; Thanjaivadivel, T.; Jeeva, S.; Ahilan, A.J.C.N. Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM. Comput. Netw. 2019, 151, 191–200. [Google Scholar] [CrossRef]
  19. Sreenu, G.; Saleem Durai, M.A. Intelligent video surveillance: A review through deep learning techniques for crowd analysis. J. Big Data 2019, 6, 48. [Google Scholar] [CrossRef]
  20. Huang, H.; Zhao, B.; Gao, F.; Chen, P.; Wang, J.; Hussain, A. A Novel Unsupervised Video Anomaly Detection Framework Based on Optical Flow Reconstruction and Erased Frame Prediction. Sensors 2023, 23, 4828. [Google Scholar] [CrossRef] [PubMed]
  21. Li, D.; Deng, L.; Lee, M.; Wang, H. IoT data feature extraction and intrusion detection system for smart cities based on deep migration learning. Int. J. Inf. Manag. 2019, 49, 533–545. [Google Scholar] [CrossRef]
  22. Nayak, R.; Pati, U.C.; Das, S.K. A comprehensive review on deep learning-based methods for video anomaly detection. Image Vis. Comput. 2021, 106, 104078. [Google Scholar] [CrossRef]
  23. Chen, Q.; Wang, W.; Huang, K.; De, S.; Coenen, F. Multi-modal generative adversarial networks for traffic event detection in smart cities. Expert Syst. Appl. 2021, 177, 114939. [Google Scholar] [CrossRef]
  24. Kustu, T.; Taskin, A. Deep learning and stereo vision based detection of post-earthquake fire geolocation for smart cities within the scope of disaster management: İstanbul case. Int. J. Disaster Risk Reduct. 2023, 96, 103906. [Google Scholar] [CrossRef]
  25. Sharma, A.; Singh, P.K.; Kumar, Y. An integrated fire detection system using IoT and image processing technique for smart cities. Sustain. Cities Soc. 2020, 61, 102332. [Google Scholar] [CrossRef]
  26. Sungheetha, A.; Rajendran, R.S. Real Time Monitoring and Fire Detection using Internet of Things and Cloud based Drones. J. Soft Comput. Paradig. 2020, 2, 168–174. [Google Scholar] [CrossRef]
  27. Santos, C.; Jiménez, J.A.; Espinosa, F. Effect of Event-Based Sensing on IoT Node Power Efficiency. Case Study: Air Quality Monitoring in Smart Cities. IEEE Access 2019, 7, 132577–132586. [Google Scholar] [CrossRef]
  28. Yong, X.; Xinxin, T.; Su, Z.; Yao, W.; Rui, C. Construction and application of digital creative platform for digital creative industry based on smart city concept. Comput. Electr. Eng. 2020, 87, 106748. [Google Scholar] [CrossRef]
  29. Hui, C.X.; Dan, G.; Alamri, S.; Toghraie, D. Greening smart cities: An investigation of the integration of urban natural resources and smart city technologies for promoting environmental sustainability. Sustain. Cities Soc. 2023, 99, 104985. [Google Scholar] [CrossRef]
  30. Muhammed, T.; Mehmood, R.; Albeshri, A.; Katib, I. UbeHealth: A Personalized Ubiquitous Cloud and Edge-Enabled Networked Healthcare System for Smart Cities. IEEE Access 2018, 6, 32258–32285. [Google Scholar] [CrossRef]
  31. Odendaal, N. Everyday urbanisms and the importance of place: Exploring the elements of the emancipatory smart city. Urban. Stud. 2021, 58, 639–654. [Google Scholar] [CrossRef]
  32. Yao, F.; Wang, Y. Towards resilient and smart cities: A real-time urban analytical and geo-visual system for social media streaming data. Sustain. Cities Soc. 2020, 63, 102448. [Google Scholar] [CrossRef]
  33. Al-Turjman, F.; Lemayian, J.P. Intelligence, security, and vehicular sensor networks in internet of things (IoT)-enabled smart-cities: An overview. Comput. Electr. Eng. 2020, 87, 106776. [Google Scholar] [CrossRef]
  34. Ahmed, S.; Hossain, M.; Kaiser, M.S.; Noor, M.; Mahmud, M.; Chakraborty, C. Artificial Intelligence and Machine Learning for Ensuring Security in Smart Cities. In Data-Driven Mining, Learning and Analytics for Secured Smart Cities. Advanced Sciences and Technologies for Security Applications; Springer: Cham, Switzerland, 2021; pp. 23–47. ISBN 978-3-030-72138-1. [Google Scholar]
  35. Hamza, A.; Gharakheili, H.H.; Benson, T.A.; Sivaraman, V. Detecting Volumetric Attacks on loT Devices via SDN-Based Monitoring of MUD Activity. In Proceedings of the 2019 ACM Symposium on SDN Research, San Jose, CA, USA, 3–4 April 2019; Association for Computing Machinery: New York, NY, USA, 2019; pp. 36–48. [Google Scholar]
  36. Tok, Y.C.; Chattopadhyay, S. Identifying Threats, Cybercrime and Digital Forensic Opportunities in Smart City Infrastructure via Threat Modeling. Forensic Sci. Int. Digit. Investig. 2023, 45, 301540. [Google Scholar] [CrossRef]
  37. Sadiq, S.; Mehmood, A.; Ullah, S.; Ahmad, M.; Choi, G.S.; On, B.-W. Aggression detection through deep neural model on Twitter. Future Gener. Comput. Syst. 2021, 114, 120–129. [Google Scholar] [CrossRef]
  38. Adewopo, V.A.; Elsayed, N.; ElSayed, Z.; Ozer, M.; Abdelgawad, A.; Bayoumi, M. A review on action recognition for accident detection in smart city transportation systems. J. Electr. Syst. Inf. Technol. 2023, 10, 57. [Google Scholar] [CrossRef]
  39. Felici-Castell, S.; García-Pineda, M.; Segura-Garcia, J.; Fayos-Jordan, R.; Lopez-Ballester, J. Adaptive live video streaming on low-cost wireless multihop networks for road traffic surveillance in smart cities. Future Gener. Comput. Syst. 2021, 115, 741–755. [Google Scholar] [CrossRef]
  40. Kumar, N.; Raubal, M. Applications of deep learning in congestion detection, prediction and alleviation: A survey. Transp. Res. Part. C Emerg. Technol. 2021, 133, 103432. [Google Scholar] [CrossRef]
  41. Liu, L.; Guevara, A.; Sanchez-Galan, J.E. Identification and classification of road traffic incidents in Panama City through the analysis of a social media stream and machine learning. Intell. Syst. Appl. 2022, 16, 200158. [Google Scholar] [CrossRef]
  42. Olariu, S.; Popescu, D.C. See-trend: Secure traffic-related event detection in smart communities. Sensors 2021, 21, 7652. [Google Scholar] [CrossRef] [PubMed]
  43. Pramanik, A.; Sarkar, S.; Maiti, J. A real-time video surveillance system for traffic pre-events detection. Accid. Anal. Prev. 2021, 154, 106019. [Google Scholar] [CrossRef] [PubMed]
  44. Rathore, M.M.; Paul, A.; Rho, S.; Khan, M.; Vimal, S.; Shah, S.A. Smart traffic control: Identifying driving-violations using fog devices with vehicular cameras in smart cities. Sustain. Cities Soc. 2021, 71, 102986. [Google Scholar] [CrossRef]
  45. Alani, M.M. HoneyTwin: Securing smart cities with machine learning-enabled SDN edge and cloud-based honeypots. J. Parallel Distrib. Comput. 2024, 188, 104866. [Google Scholar] [CrossRef]
  46. Gallo, P.; Pongnumkul, S.; Quoc Nguyen, U. BlockSee: Blockchain for IoT Video Surveillance in Smart Cities. In Proceedings of the 2018 IEEE International Conference on Environment and Electrical Engineering and 2018 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Palermo, Italy, 12–15 June 2018; pp. 1–6. [Google Scholar]
  47. Memos, V.A.; Psannis, K.E.; Ishibashi, Y.; Kim, B.-G.; Gupta, B.B. An Efficient Algorithm for Media-based Surveillance System (EAMSuS) in IoT Smart City Framework. Future Gener. Comput. Syst. 2018, 83, 619–628. [Google Scholar] [CrossRef]
  48. Ouni, R.; Saleem, K. Secure smart home architecture for ambient-assisted living using a multimedia Internet of Things based system in smart cities. MBE 2024, 21, 3473–3497. [Google Scholar] [CrossRef] [PubMed]
  49. Sajjad, M.; Nasir, M.; Muhammad, K.; Khan, S.; Jan, Z.; Sangaiah, A.K.; Elhoseny, M.; Baik, S.W. Raspberry Pi assisted face recognition framework for enhanced law-enforcement services in smart cities. Future Gener. Comput. Syst. 2020, 108, 995–1007. [Google Scholar] [CrossRef]
  50. Telo, J. Smart City Security Threats and Countermeasures in the Context of Emerging Technologies. Int. J. Intell. Autom. Comput. 2023, 6, 31–45. [Google Scholar]
  51. Nabijonovich, S.B.; Ahror, K.; Kizi, A.D.B. Unveiling the future of data extraction using python and ai for video-based information recognition. Am. J. Technol. Appl. Sci. 2023, 17, 26–32. [Google Scholar]
  52. Qadir, Z.; Ullah, F.; Munawar, H.S.; Al-Turjman, F. Addressing disasters in smart cities through UAVs path planning and 5G communications: A systematic review. Comput. Commun. 2021, 168, 114–135. [Google Scholar] [CrossRef]
  53. Wan, S.; Xu, X.; Wang, T.; Gu, Z. An Intelligent Video Analysis Method for Abnormal Event Detection in Intelligent Transportation Systems. IEEE Trans. Intell. Transp. Syst. 2021, 22, 4487–4495. [Google Scholar] [CrossRef]
  54. Alkhatib, M.; El Barachi, M.; Shaalan, K. An Arabic social media based framework for incidents and events monitoring in smart cities. J. Clean. Prod. 2019, 220, 771–785. [Google Scholar] [CrossRef]
  55. Cesario, E.; Lindia, P.; Vinci, A. A scalable multi-density clustering approach to detect city hotspots in a smart city. Future Gener. Comput. Syst. 2024, 157, 226–236. [Google Scholar] [CrossRef]
  56. Zhang, X.; Yang, S.; Zhang, J.; Zhang, W. Video anomaly detection and localization using motion-field shape description and homogeneity testing. Pattern Recognit. 2020, 105, 107394. [Google Scholar] [CrossRef]
  57. Zacepins, A.; Komasilovs, V.; Kviesis, A. Implementation of smart parking solution by image analysis. In Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems, Madeira, Portugal, 16–18 March 2018; pp. 666–669. [Google Scholar]
  58. Basak, S.; Gautam, A. Diffusion-based normality pre-training for weakly supervised video anomaly detection. Expert Syst. Appl. 2024, 251, 124013. [Google Scholar] [CrossRef]
  59. Tsiktsiris, D.; Dimitriou, N.; Lalas, A.; Dasygenis, M.; Votis, K.; Tzovaras, D. Real-time abnormal event detection for enhanced security in autonomous shuttles mobility infrastructures. Sensors 2020, 20, 4943. [Google Scholar] [CrossRef] [PubMed]
  60. Ullah, W.; Ullah, A.; Hussain, T.; Muhammad, K.; Heidari, A.A.; Del Ser, J.; Baik, S.W.; De Albuquerque, V.H.C. Artificial Intelligence of Things-assisted two-stream neural network for anomaly detection in surveillance Big Video Data. Future Gener. Comput. Syst. 2022, 129, 286–297. [Google Scholar] [CrossRef]
  61. Javed, M.H.; Li, T.; Yu, Z.; Hussain, A.; Rajeh, T.M.; Zhang, F. Pyramidal temporal frame prediction for efficient anomalous event detection in smart surveillance systems. Knowl.-Based Syst. 2023, 282, 111111. [Google Scholar] [CrossRef]
  62. Villegas-Ch, W.; Govea, J.; Jaramillo-Alcazar, A. IoT Anomaly Detection to Strengthen Cybersecurity in the Critical Infrastructure of Smart Cities. Appl. Sci. 2023, 13, 10977. [Google Scholar] [CrossRef]
  63. Amrutha, C.V.; Jyotsna, C.; Amudha, J. Deep Learning Approach for Suspicious Activity Detection from Surveillance Video. In Proceedings of the 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Bangalore, India, 5–7 March 2020; IEEE: Bangalore, India, 2020; pp. 335–339. [Google Scholar]
  64. Ansarnia, M.S.; Tisserand, E.; Berviller, Y.; Schweitzer, P.; Zidane, M.A. Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms. Sensors 2022, 22, 1381. [Google Scholar] [CrossRef] [PubMed]
  65. Heidari, A.; Navimipour, N.J.; Unal, M. Applications of ML/DL in the management of smart cities and societies based on new trends in information technologies: A systematic literature review. Sustain. Cities Soc. 2022, 85, 104089. [Google Scholar] [CrossRef]
  66. Khan, S.; Muhammad, K.; Mumtaz, S.; Baik, S.W.; de Albuquerque, V.H.C. Energy-Efficient Deep CNN for Smoke Detection in Foggy IoT Environment. IEEE Internet Things J. 2019, 6, 9237–9245. [Google Scholar] [CrossRef]
  67. Muhammad, K.; Hussain, T.; Baik, S.W. Efficient CNN based summarization of surveillance videos for resource-constrained devices. Pattern Recognit. Lett. 2020, 130, 370–375. [Google Scholar] [CrossRef]
  68. Muhammad, K.; Khan, S.; Palade, V.; Mehmood, I.; de Albuquerque, V.H.C. Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments. IEEE Trans. Ind. Inform. 2020, 16, 1067–1075. [Google Scholar] [CrossRef]
  69. Barthélemy, J.; Verstaevel, N.; Forehead, H.; Perez, P. Edge-Computing Video Analytics for Real-Time Traffic Monitoring in a Smart City. Sensors 2019, 19, 2048. [Google Scholar] [CrossRef] [PubMed]
  70. Shorfuzzaman, M.; Hossain, M.S.; Alhamid, M.F. Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemic. Sustain. Cities Soc. 2021, 64, 102582. [Google Scholar] [CrossRef] [PubMed]
  71. Ullah, W.; Min Ullah, F.U.; Ahmad Khan, Z.; Wook Baik, S. Sequential attention mechanism for weakly supervised video anomaly detection. Expert Syst. Appl. 2023, 230, 120599. [Google Scholar] [CrossRef]
  72. Cheng, M.; Cai, K.; Li, M. RWF-2000: An Open Large Scale Video Database for Violence Detection. In Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR); IEEE: Milan, Italy, 2021; pp. 4183–4190. [Google Scholar]
  73. Ullah, W.; Ullah, A.; Haq, I.U.; Muhammad, K.; Sajjad, M.; Baik, S.W. CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimed. Tools Appl. 2021, 80, 16979–16995. [Google Scholar] [CrossRef]
  74. Alhamed, K.M.; Iwendi, C.; Dutta, A.K.; Almutairi, B.; Alsaghier, H.; Almotairi, S. Building construction based on video surveillance and deep reinforcement learning using smart grid power system. Comput. Electr. Eng. 2022, 103, 108273. [Google Scholar] [CrossRef]
Csmf 10 00015 g001
Figure 1. The distribution of articles according to the year of publication.
Figure 1. The distribution of articles according to the year of publication.
Csmf 10 00015 g001
Csmf 10 00015 g002
Figure 2. The distribution of articles according to the databases consulted.
Figure 2. The distribution of articles according to the databases consulted.
Csmf 10 00015 g002
Csmf 10 00015 g003
Figure 3. The distribution of articles based on the quality level of scientific journals.
Figure 3. The distribution of articles based on the quality level of scientific journals.
Csmf 10 00015 g003
Csmf 10 00015 g004
Figure 4. The distribution of articles according to the areas concerned.
Figure 4. The distribution of articles according to the areas concerned.
Csmf 10 00015 g004
Csmf 10 00015 g005
Figure 5. The classification of articles according to the development methods used.
Figure 5. The classification of articles according to the development methods used.
Csmf 10 00015 g005
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Dardour, A.; El Haji, E.; Begdouri, M.A. Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024. Comput. Sci. Math. Forum 2025, 10, 15. https://doi.org/10.3390/cmsf2025010015

AMA Style

Dardour A, El Haji E, Begdouri MA. Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024. Computer Sciences & Mathematics Forum. 2025; 10(1):15. https://doi.org/10.3390/cmsf2025010015

Chicago/Turabian Style

Dardour, Abdellah, Essaid El Haji, and Mohamed Achkari Begdouri. 2025. "Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024" Computer Sciences & Mathematics Forum 10, no. 1: 15. https://doi.org/10.3390/cmsf2025010015

APA Style

Dardour, A., El Haji, E., & Begdouri, M. A. (2025). Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024. Computer Sciences & Mathematics Forum, 10(1), 15. https://doi.org/10.3390/cmsf2025010015

Article Metrics

Back to TopTop