A Survey of Video Surveillance Systems in Smart City
Open accessThe DOI matches its Crossref record; 170 of the 171 references it cites were found in a registry or an index; 53 of the 213 sources its claims cite were checked for support.
Abstract
Smart cities are being developed worldwide with the use of technology to improve the quality of life of citizens and enhance their safety. Video surveillance is a key component of smart city infrastructure, as it involves the installation of cameras at strategic locations throughout the city for monitoring public spaces and providing real-time surveillance footage to law enforcement and other city representatives. Video surveillance systems have evolved rapidly in recent years, and are now integrated with advanced technologies like deep learning, blockchain, edge computing, and cloud computing. This study provides a comprehensive overview of video surveillance systems in smart cities, as well as the functions and challenges of those systems. The aim of this paper is to highlight the importance of video surveillance systems in smart cities and to provide insights into how they could be used to enhance safety, security, and the overall quality of life for citizens.
Overview
CoChat Summary
TL;DR
This survey reviews video surveillance systems (VSS) in smart cities, covering architecture, monitoring devices, edge/cloud computing, blockchain, and video analytics functions. It synthesizes applications and challenges, emphasizing safety, security, and quality-of-life goals.
Key findings
- VSS architecture combines end camera devices, edge computing for fast local processing, cloud computing for intensive deep-learning analysis and storage, and blockchain for secure storage and consensus; monitoring devices can be fixed (CCTV, IP, PTZ) or moving (drones, cars, smartphones).
- Core functions include object detection/classification, object tracking, human action recognition (HAR), anomaly detection, and secure video data management; applications span healthcare, traffic management, public safety, and environmental monitoring.
- Reviewed studies report varied accuracies, e.g., DeepDC improved from 89.12% with CNN alone to 93.82% with a GAN discriminator; kNN plant disease detection reached 96.76% vs. SVM maximum 92.1%; YOLOv4 vehicle detection reached 97%; AnomalyNet achieved 95.6% on the avenue dataset; BESDDFFS reported up to 66% lesser delay, 36% greater throughput, and 12% greater ratio of successfully delivered packets.
- Challenges include accuracy, scalability, real-time processing, variability, privacy, data storage/retrieval, false alarms, drone resource/privacy limits, and unsupervised/multimodal system issues.
Methods
- Survey/overview of VSS for smart cities, presenting a general architecture and key components, based on studies published in 2018 or more recently.
- Discusses state-of-the-art techniques for object detection/classification, tracking, HAR, anomaly detection, and video data management, with tables comparing methods and references.
- No primary data collection or experimental evaluation is reported; performance figures are drawn from cited literature.
Limitations
- The paper states VSS still faces challenges including system accuracy, scalability, real-time processing, variability, privacy, data storage, and retrieval; a high false alarm rate incurs significant administrative workload.
- The paper states drone-based monitoring has limited flight duration/battery, limited CPU/memory, and security/privacy concerns; unsupervised learning needs human intervention, scalability, interpretability, and domain adaptation; multimodal systems face storage management, real-time processing, and format-adjustment challenges.
- Evident from the text: as a survey, it does not report a systematic search protocol or independent validation; reported accuracies come from heterogeneous cited studies and datasets.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
41 Valid · 4 Not valid · 134 Not checked · 9 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“It also sends alarms for proactive monitoring, rapid response, and efficient resource allocation by city authorities [6].”
§ A Survey of Video Surveillance Systems in Smart City > 1. Introduction
What the sources say
- Partly supportedcites [6] Sreenu, 2019, Intelligent video surveillance: A review through deep learning techniques for crowd analysis, J. Big Data sourceExperimental — accuracy not yet measured
The review lists an alarm as a step in one real-time crowd-behavior detection method (Table 9, p. 16), and says response time and prediction matter in emergencies (Surveillance video analysis: relevance in present world, p. 9). It does not say that an intelligent VSS sends alarms to city authorities or that those alarms enable efficient resource allocation. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recently, some of the published VSS survey papers focused on one specific area such as attacks and preventive measures on VSS [1], anomaly detection [2][3][4][5], crowd behavior analysis [6], and drone surveillance system [7].”
§ A Survey of Video Surveillance Systems in Smart City > 1. Introduction
What the sources say
- Supportedcites [1] Vennam, P., T.C., P., B.M., T., Kim, Y.-G., and B.N., P.K. (2021). Attacks and Preventive Measures on Video Surveillance Systems: A Review. Appl. Sci., 11. source
The citation [1] identifies this paper as a survey focused on attacks and preventive measures for video surveillance systems. The Motivation and Our Contribution passage describes its literature survey, while Section 2 says it covers attacks and summarizes security measures in Section 3. The other survey topics in the citing sentence are attributed to different references. (LLM, conf=0.94)
- Not matchedcites [2][3][4][5]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [6] Sreenu, 2019, Intelligent video surveillance: A review through deep learning techniques for crowd analysis, J. Big Data source
The citation [6] is attached to “crowd behavior analysis,” not the other survey topics in the sentence. The Conclusion (p. 23) says the survey moves toward crowd analysis and discusses methods for analyzing crowd behavior, supporting its use as an example of a survey focused on that area. (LLM, conf=0.92)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“By employing a correlation tracking algorithm, the system can track the object based the characteristics of its appearance [93].”
§ A Survey of Video Surveillance Systems in Smart City > 4.2.1. Point-Based Object Tracking
What the sources say
- Supportedcites [93] Liu, 2020, Overview and methods of correlation filter algorithms in object tracking, Complex Intell. Syst. source
The “Object tracking” section says trackers extract features from candidate regions to identify the target, including shape and color features. The “Correlation filter tracking algorithm” section describes correlation-filter trackers that use such features to track objects. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using the lightweight DNN with edge computing can reduce the computational cost of object detection [49].”
§ A Survey of Video Surveillance Systems in Smart City > 4.1.1. Motion-Based Object Detection
What the sources say
- Supportedcites [49] Zhao, 2020, Lightweight Deep Learning Based Intelligent Edge Surveillance Techniques, IEEE Trans. Cogn. Commun. Netw. source
The Abstract says the paper builds a lightweight neural network to reduce computational cost and uses it for edge surveillance that recognizes objects. The section “Lightweight Neural Network at the Edge Node” describes the detection networks used in that system. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“To combine the strengths of both models, a CNN-LSTM hybrid architecture was developed in [114] to monitor and recognize human actions in indoor environments in 2022 with an accuracy of 90.89% on 30 frames.”
§ A Survey of Video Surveillance Systems in Smart City > 4.3.2. Action Classification
What the sources say
- Supportedcites [114] Khan, I.U., Afzal, S., and Lee, J.W. (2022). Human Activity Recognition via Hybrid Deep Learning Based Model. Sensors, 22. source
The Introduction describes the proposed system as indoor activity recognition using a hybrid CNN–LSTM approach. The Experimental Results (§4.4) report that this model achieved its highest accuracy, 90.89%, on a 30-frame sequence. (LLM, conf=0.94)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
54 more claims · 8 with their cited sources checked
Create a free account to see all 188 claims and to verify the 2 references still open.
- Probably not a substantial claim. 87
- It may state two separate claims as one. 64
- The quote only partly states this claim. 4
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Survey of Video Surveillance Systems in Smart City > 4.4.3. Fire and Environmental Monitoring
“Datta et al. [37] proposed blockchain and edge/drone-based secure data delivery for forest fire surveillance (BESDDFFS) in 2021.”
§ A Survey of Video Surveillance Systems in Smart City > References
“37. Sinha, S.D.D. BESDDFFS: Blockchain and EdgeDrone Based Secured Data Delivery for Forest Fire Surveillance. Peer-Peer Netw. Appl. 2021, 14, 3688-3717.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Survey of Video Surveillance Systems in Smart City > 5.1. Drone-Based Monitoring System
“For instance, leveraging algorithms like the Firefly algorithm can aid in rapidly estimating flood levels and spread rates [148].”
§ A Survey of Video Surveillance Systems in Smart City > References
“155. Kumar, V.S.; Sakthivel, M.; Karras, D.A.; Gupta, S.K.; Gangadharan, S.M.P.; Haralayya, B. Drone Surveillance in Flood Affected Ar- eas using Firefly Algorithm.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Survey of Video Surveillance Systems in Smart City > 5.2. Unsupervised-Learning-Based Surveillance System
“In the context of detecting anomalies in the marine domain [158], a challenge arises from the constrained availability of labeled data for supervised approaches, leading to potential oversight in detecting certain abnormalities.”
§ A Survey of Video Surveillance Systems in Smart City > References
“158. Ruichek, Y. Attractive-and-repulsive center-symmetric local binary patterns for texture classification. Eng. Appl. Artif. Intell. 2019, 78, 158-172.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Survey of Video Surveillance Systems in Smart City > 6. Conclusions
“| [161] | Deep learning | Post-incident alarm triggering occurs from training crowd safety analysis on only human movement |”
§ A Survey of Video Surveillance Systems in Smart City > References
“161. Olmos, R.; Tabik, S.; Perez-Hernandez, F.; Lamas, A.; Herrera, F. MULTICAST: MULTI Confirmation-level Alarm SysTem based on CNN and LSTM to mitigate false alarms for handgun detection in video-surveillance.”
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“Abnormal action detection focuses on identifying actions that are uncommon, unusual, or potentially dangerous, which include falling, stumbling, abnormal body movements, sudden changes in speed or direction, and actions that are out of context in a given environment [76].”
Cited work 10.1016/j.micpro.2020.103084 · retracted 2020-07-01 · notice 10.1016/j.micpro.2020.103084 · this paper published 2023-08-23
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“Jha et al. [98] proposed an N-YOLO approach with a correlation-based tracker to produce efficient bounding boxes that predict the movement of the object in 2021.”
Cited work 10.1007/s11042-020-09749-x · retracted 2026-04-15 · notice 10.1007/s11042-026-21610-1 · this paper published 2023-08-23
Citations
Cites
2 retracted
RETRACTED ARTICLE: Real time object detection and trackingsystem for video surveillance system
Jha, S., Seo, C., Yang, E., & Joshi, G. P. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09749-x · Cited by 165 · cited 1×
“Jha et al. [98] proposed an N-YOLO approach with a correlation-based tracker to produce efficient bounding boxes that predict the movement of the object in 2021.”
MethodRetractedThenmozhi, T., & Kalpana, A. M. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103084 · Cited by 28 · cited 2×
“Abnormal action detection focuses on identifying actions that are uncommon, unusual, or potentially dangerous, which include falling, stumbling, abnormal body movements, sudden changes in speed or direction, and actions that are out of context in a given environment [76].”
BackgroundMethodRetractedLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · cited 2×
“Content filtering [22], compression [29], caching [169], and dynamic content delivery [50] techniques may be used to ensure efficient bandwidth utilization.”
BackgroundMethodA Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607 · cited 1×
“However, edge computing involves processing and analyzing video data closer to where the data are generated, such as on local camera devices, which may include smartphones and network entities like base stations and wireless access points [20].”
BackgroundComaniciu, D., Ramesh, V., & Meer, P. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1195991 · Cited by 4,560 · cited 1×
“By comparing the similarity scores of different candidate regions, the tracker can determine the most likely location of the object in the current frame [94,95].”
BackgroundAbnormal Event Detection at 150 FPS in MATLAB
Lu, C., Shi, J., & Jia, J. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.338 · Cited by 1,436
Learning Temporal Regularity in Video Sequences
Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A. K., & Davis, L. S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.86 · Cited by 1,397
An Overview on Edge Computing Research
Cao, K., Liu, Y., Meng, G., & Sun, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2991734 · Cited by 1,254 · cited 1×
“This reduction in network burden enhances the efficiency of network bandwidth utilization [21].”
BackgroundFuture Edge Cloud and Edge Computing for Internet of Things Applications
Pan, J., & McElhannon, J. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2767608 · Cited by 868 · cited 1×
“In smart city surveillance systems, edge nodes are typically positioned between the monitoring devices and the cloud server [24].”
Background
Research works printed but not linked: 4
- Khan, M.A., Alvi, B.A., Safi, A., and Khan, I.U. (2018, January 28–29). Drones for good in smart cities: A review. Proceedings of the 2018 International Conference on Electrical, Electronics, Computers, Communication, Mechanical and Computing (EECCMC), Chennai, India.
- Fernandez-Carrobles, M.M., Deniz, O., and Maroto, F. (2019). Proceedings of the Pattern Recognition and Image Analysis: 9th Iberian Conference, IbPRIA 2019, Madrid, Spain, 1–4 July 2019, Springer. Proceedings, Part II.
- Williams, J., Kleinegesse, S., Comanescu, R., and Radu, O. (2018). Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML), Association for Computational Linguistics.
- Bevilacqua, A., Macdonald, K., Rangarej, A., Widjaya, V., Caulfield, B., and Kechadi, T. (2019). Machine Learning and Knowledge Discovery in Databases, Springer International Publishing.
Cited by
Items 101–127 of 127
AI and Smart Technologies in Tourism
(2026) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83608-602-420261016
CRD-YOLO: a high-accuracy real-time crowded pedestrian detection algorithm
Hu, Z. H., Niu, W., & Mo, S. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05220-w · Cited by 1
Skarga-Bandurova, I., Biloborodova, T., Kjelstrup-Johnson, K. R., Scheper, T. V. O., & Derkach, M. (2026) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-032-11013-8_3
Rizk, M., Taleb, H., Rhayem, A., Chaaya, J. A., Zaki, C., & Nasser, A. (2026) · Research Square · doi:10.21203/rs.3.rs-8815873/v1
Enhancing Video Anomaly Detection by Leveraging Advanced Deep Learning Techniques
Shao, W. (2023) · theses.fr (ABES) · doi:10.70675/f1ab299cz0829z4deczaf67zdd2b12bdb885 · Cited by 2
Krame, G., & Davies, A. J. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-18487-0_14
A Light-Weight PRNU-Based Camera-Device Authentication Based on Device-Specific Image Downsampling
Naruse, K., Nishimura, N., Sasaki, H., Midoh, Y., Shiomi, J., Tanaka, Y., Kuribayashi, M., & Miura, N. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462055
Millimeter-wave radar-assisted skeleton-guided video reconstruction for surveillance systems
Leng, W., Luo, B., Dai, M., & 徐立 (2026) · The Visual Computer · doi:10.1007/s00371-026-04478-y
“Video surveillance is widely used in public safety, smart cities, transportation, and industrial sites [1–3].”
An Intelligent Deep Learning Framework for Violence Detection in Surveillance Images
Ahilan, A., Bindu, L. R., Prathusha, P., et al. (2026) · doi:10.1109/wccst67302.2026.11495652
“The proliferation of surveillance cameras in public and workplace environments is expanding rapidly, providing a wealth of data that can deter potential offenders [7].”
Pechiappan, G. S., Alqawasmi, K., Perumalla, S., et al. (2026) · doi:10.1109/iconic67661.2026.11517758
“Prior studies aimed to find ways to compress videos, identify objects in the footage, and optimize network traffic [8,9].”
Zhukabayeva, T. K., Ahmad, Z., Сатыбалдина, Д., & Yedilkhan, D. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1836157 · Cited by 1
Chen, Y. (2026) · International Conference on Integrated Intelligence and Communication Systems (ICIICS) · doi:10.1109/iciics67880.2026.11483438
Bono, F., Vaglica, G., Renaldi, G., Cazzato, D., Ojea, E. V., & Sousa, J. R. P. M. D. (2026) · Internet of Things · doi:10.1016/j.iot.2026.102004
A Survey of GCN-Based Two-Person Interaction Recognition AlgorithmsPreprint
Teng, Y., Li, Z., Li, F., & Wang, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6995702
Medvei, M. M., Gurău, D. G., & Coca, M. (2026) · Future Internet · doi:10.3390/fi18070349
“The study by [4] highlights how modern video surveillance systems in smart cities have progressed from basic monitoring to intelligent, real-time analysis.”
A Novel Approach Based on Deep Learning for Violence Detection in Public Places
Khan, S. F., Shah, S. K., Khan, F. U., Khan, W., & Idrees, F. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1773
Transformer-Enhanced Deep Vision Architecture for Real-Time Automated Security Video Analysis
Rajeswari, J., Nirmalkumar, V., Abitha, R., et al. (2026) · International Conference on System, Computation, Automation and Networking (ICSCAN) · doi:10.1109/icscan66520.2026.11588529
“Conventional surveillance systems heavily depend on human surveillance which is not only more impractical due to the large and dynamic environment but also operator fatigue, less situational awareness, real time processing of large volumes of video data [2].”
Olansile, S. O., Amodu, O. A., Adam, M. S., Elesemoyo, I. O., & Mahmood, R. A. R. (2026) · Frontiers in Imaging · doi:10.3389/fimag.2026.1854187
Hardware Description Language Enabling Secure and Low-Power Surveillance Systems for Smart Cities
Philip-Kpae, F. O., Imoize, A. L., Faruk, N., Ojuka, O. E., & Kingsley, F. C. (2025) · IEEE Connecting the Unconnected Europe, Middle East, and Africa Regional Summit (CTUS-EMEA) · doi:10.1109/ctus-emea68989.2025.11592180
“These systems optimize hardware components for high-speed processing and real-time analytics while minimizing power consumption, which is essential for advanced technologies such as deep learning, blockchain, edge computing, and cloud computing [9].”
Reducing Prompt Sensitivity in Video Anomaly Understanding via Conditional Prompt Learning
Ignatosyan, A., Cao, L., & Doughty, H. (2026) · doi:10.1145/3810987.3815535
“This capability is critical in applications such as public surveillance [19, 22, 25, 31, 36], autonomous driving [2, 38], smart city monitoring [26], and industrial fault detection [9, 18], Prior finetuned methods exhibit high sensitivity to prompt variations, producing inconsistent responses when…”
Towards Deep Learning-Based Multi-class Classification of Vehicle Anomalies in Surveillance Videos
Mathur, H., Sharma, S., & Joshi, C. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31119-1_23
Bhat, M. H., & Lin, D.-T. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00072 · Cited by 2
“With the widespread deployment of CCTV cameras in smart city infrastructures[19], automated detection of dumping events from surveillance footage has become essential for scalable monitoring.”
Pakala, K., & Lingala, U. K. R. (2026) · International Conference on Intelligent and Sustainable AI Systems (ICOSAAS) · doi:10.1109/icosaas68663.2026.11648729
“The author Myagmar-Ochir et al., (2023) [10] says that the paper outlines an overview of video surveillance systems in smart cities, particularly on how it can contribute to improving safety, security and quality of life with smart video surveillance.”
Eshmurodov, A., Rustamovna, A. B., Kosimov, O., Gulzar, J., & Tolibjon, B. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0965-9.ch001
Jiang, X., Li, D., Xu, Q., & Zheng, Z. (2026) · Security Journal · doi:10.1057/s41284-026-00571-y
“Together with other policing capacities, it constitutes an integral component of contemporary public-safety infrastructures, and in recent years has exhibited accelerated growth and diffusion (Myagmar-Ochir and Kim 2023 ; Gaub and Koen 2021).”
Optimized Federated Adversarial Learning Framework for Privacy-Preserving Facial Surveillance
Sumathi, M., Srikar, K. V. P., Akhila, N. G., & Koushal, Y. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-27845-6_24
Multi-Object Tracking and Spatio-Temporal Graph-Based Relational Pattern Mining
Seo, T., & Chung, K. (2026) · Electronics · doi:10.3390/electronics15184086
Metadata
- Authors
- Myagmar-Ochir, Y., & Kim, W.
- Affiliations
- Gachon University (KR)
- Corresponding author
- Kim, Wooseong
- ORCID
- Kim, Wooseong
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2023-08-23
- Volume
- 12
- Issue
- 17
- Pages
- 3567
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W4386141924
- Cited by
- 134
- References
- 169
- Citations by year
- 2026: 41 · 2025: 55 · 2024: 32 · 2023: 6
- FWCI
- 14.75
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- Funders
- Gachon University (GCU-202106320001, 2022R1F1A1074767)
- Ministry of Science and ICT (GCU-202106320001, 2022R1F1A1074767)
- Topics
- Social Sciences › Urban Studies › Smart Cities and Technologies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- video surveillance systems, smart cities, public safety, urban security, deep learning, blockchain, edge computing, cloud computing, surveillance cameras, real-time video surveillance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.