Document Type : Original Research Paper
Authors
1 Department of Information Technology Management , Faculty of Management and Economics, Islamic Azad University- Science and Research branch, Tehran, Iran
2 Department of Computer Engineering,, Islamic Azad University- Kashan Branch, Kashan, Iran
3 Department of Industrial Management , Faculty of Management and Accounting, Islamic Azad University- Central Tehran branch,Tehran, Iran
Abstract
Background and Objectives: Optimizing the placement of surveillance cameras is a fundamental component of intelligent urban traffic management systems. Proper camera deployment significantly enhances traffic monitoring accuracy and reduces incident detection time. As a result, the problem of optimal camera placement has long been a research challenge for many scholars. Modern approaches employ multi-objective optimization methods to enable simultaneous analysis of various influential parameters. Despite significant advancements in optimization techniques, current methods rely on 2D and 3D grid-based modeling of the study area, which faces major limitations in complex urban environments. In these methods, the space is divided into a regular grid, and optimal camera locations are selected with appropriate angular rotation. However, in real urban topologies, road networks consist of nested and irregular paths, causing many computed points to fall outside accessible routes. This mismatch between theoretical models and practical conditions severely undermines the effectiveness of traditional methods. Given these limitations, developing a new framework that simultaneously considers real urban topologies, physical constraints, and urban planning requirements has become essential. New methods must integrate actual traffic routes, permissible camera installation points, and mandatory angle adjustments into their models. This requires using realistic virtual traffic data and applying artificial intelligence algorithms for optimization.
Methods: The current research analyzes urban maps and requires a comprehensive and precise city map to identify optimal locations based on real data. The map is represented as a matrix—a 2D grid of points—where accessible paths and obstacles are defined by different numerical values. Since a street's width includes multiple points, a central row is selected to represent the path, restricting vehicle movement to this route and providing an ideal location for surveillance cameras. The optimal placement process is systematically conducted in four stages after matrix formation. First, origin-destination pairs are randomly generated using population density-based probability distribution. Second, optimal routing for each pair is simulated based on traffic behavior—shortest path selection during normal hours and alternative routes during peak hours. Third, all generated routes are aggregated to create virtual traffic, and path density is calculated for traffic-based optimization. Finally, considering different camera types based on purchase cost and installation expenses, placement is optimized for cost efficiency.
Findings: One hundred thousand new data points were generated, and two experiments were conducted. The first experiment used a greedy algorithm to maximize camera coverage across all paths. The second experiment applied the proposed method, first identifying high-traffic points, then maximizing coverage in these areas while minimizing installation costs. Results showed that the proposed method improves monitoring efficiency by 40% on new routes and reduces project costs by 6.6%.
Conclusion: In urban surveillance camera placement, methods focusing solely on maximum path coverage are ineffective, and traffic assessment is crucial for optimization. Additionally, since geometric features of paths are eliminated in the proposed method, it is scalable and applicable to any city and routing system. Furthermore, urban planners often purchase cameras with varying fields of view and brands, which can be leveraged as an opportunity for cost optimization.
Keywords
- CCTV Camera Placement
- Multi-Objective Optimization
- Intelligent Routing
- Q Learning Algorithm
- Video Surveillance System
Main Subjects
COPYRIGHTS
© 2025 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
)