AI-Driven Video Processing and IoT Frameworks for Intelligent Decision-Making in Smart City Surveillance: A Survey on Edge–Cloud Analytics, Predictive Urban Intelligence, and Trustworthy Governance

The demand for intelligent monitoring systems that aid real-time urban decision-making in smart cities has grown tremendously amid rapid urbanisation and the widespread deployment of surveillance infrastructure. Traditional solutions like standalone CCTV surveillance and centralised data analysis struggle with vast amounts of video data, a lack of context, latency, and an inability to support proactive decision-making. Finally, recent developments in Artificial Intelligence and IoT have paved the way for new possibilities in integrating video analytics into multimodal urban sensing, facilitating scalable, adaptive, and intelligent smart city surveillance. This survey provides a detailed survey of AI-based video processing and IoT-based intelligent decision-making systems for smart city surveillance. It reviews a wide variety of recent studies systematically in five key areas: AI-based video analytics for vehicle and pedestrian detection and tracking, re-identification, anomaly recognition, IoT sensor fusion and edge–cloud processing architectures, predictive analytics and reinforcement learning for urban intelligence, explainable AI, privacy preservation and governance, and comparative benchmarking of existing frameworks. A literature review methodology (based on PRISMA) was used to select and assess 52 relevant peer-reviewed articles from the IEEE Xplore, Scopus, Web of Science, ScienceDirect and SpringerLink databases. From the comparative analysis, it is evident that there is significant progress in real-time detection and multimodal sensing; however, hurdles remain in disjointed video and sensor intelligence, latency–bandwidth trade–offs, low-level predictive integration, limited explainability, and partial privacy-aware deployment. The survey also highlights potential developments in the near future, such as multimodal transformers, edge foundation models, urban simulation via generative AI, 6 G-enabled smart surveillance, digital twins, and autonomous policy agents. Conclusively, the overall scene of this survey presents a framework for a structured, contemporary approach to building Proactive, Scalable, Explainable, and Trustworthy Surveillance Intelligence Systems for Next Generation Smart Cities.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24304579
Primary Topic
IoT and Edge/Fog Computing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI-Driven Video Processing and IoT Frameworks for Intelligent Decision-Making in Smart City Surveillance: A Survey on Edge–Cloud Analytics, Predictive Urban Intelligence, and Trustworthy Governance

J Rajyalaxmi, B. Prabhakar
2 links
Zenodo (CERN European Organization for Nuclear Research)
IoT and Edge/Fog Computing
article

AI-Driven Video Processing and IoT Frameworks for Intelligent Decision-Making in Smart City Surveillance: A Survey on Edge–Cloud Analytics, Predictive Urban Intelligence, and Trustworthy Governance

J Rajyalaxmi, B. Prabhakar
article en

Abstract

The demand for intelligent monitoring systems that aid real-time urban decision-making in smart cities has grown tremendously amid rapid urbanisation and the widespread deployment of surveillance infrastructure. Traditional solutions like standalone CCTV surveillance and centralised data analysis struggle with vast amounts of video data, a lack of context, latency, and an inability to support proactive decision-making. Finally, recent developments in Artificial Intelligence and IoT have paved the way for new possibilities in integrating video analytics into multimodal urban sensing, facilitating scalable, adaptive, and intelligent smart city surveillance. This survey provides a detailed survey of AI-based video processing and IoT-based intelligent decision-making systems for smart city surveillance. It reviews a wide variety of recent studies systematically in five key areas: AI-based video analytics for vehicle and pedestrian detection and tracking, re-identification, anomaly recognition, IoT sensor fusion and edge–cloud processing architectures, predictive analytics and reinforcement learning for urban intelligence, explainable AI, privacy preservation and governance, and comparative benchmarking of existing frameworks. A literature review methodology (based on PRISMA) was used to select and assess 52 relevant peer-reviewed articles from the IEEE Xplore, Scopus, Web of Science, ScienceDirect and SpringerLink databases. From the comparative analysis, it is evident that there is significant progress in real-time detection and multimodal sensing; however, hurdles remain in disjointed video and sensor intelligence, latency–bandwidth trade–offs, low-level predictive integration, limited explainability, and partial privacy-aware deployment. The survey also highlights potential developments in the near future, such as multimodal transformers, edge foundation models, urban simulation via generative AI, 6 G-enabled smart surveillance, digital twins, and autonomous policy agents. Conclusively, the overall scene of this survey presents a framework for a structured, contemporary approach to building Proactive, Scalable, Explainable, and Trustworthy Surveillance Intelligence Systems for Next Generation Smart Cities.

Zenodo (CERN European Organization for Nuclear Research)
Jawaharlal Nehru Technological University, Hyderabad (IN)
Sustainable cities and communities, Industry, innovation and infrastructure, Peace, justice, and strong institutions
IoT and Edge/Fog Computing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon