Application of IoT-assisted cooperative localization algorithms for UAV swarms in smart city traffic surveillance

Rapid urbanization in smart cities has intensified traffic congestion and safety issues, requiring real-time, scalable surveillance. This study proposes an IoT-assisted cooperative localization framework for UAV swarm traffic monitoring. It integrates IoT sensors, UAV-to-UAV, and UAV-to-infrastructure communication to enhance localization and task allocation. A DNN-assisted Butterfly Optimization Algorithm optimizes UAV trajectory planning and constraint handling efficiently. The DNN-assisted Butterfly Optimization Algorithm enhances trajectory planning by efficiently approximating nonlinear constraints and guiding the optimization process toward optimal solutions. Compared to conventional optimization methods, this approach improves convergence speed and solution quality, outperforming conventional optimization strategies in swarm coordination. The use of the Butterfly Optimization Algorithm (BOA) will optimize the trajectory of the UAVs by taking into account multiobjective performance constraints (i.e., energy consumption). Additionally, a deep learning-based method for approximating the complexity of trajectory constraints is employed to provide an enhanced optimization performance. Simulation results from a test case of 25 intersections and 50 road segments show that the proposed framework can achieve up to 27% reduction in localization error, 32% improvement in coverage efficiency, and 18% reduction in the energy consumed by the UAV compared to the conventional GPS-based methods for UAV deployment. The proposed IoT-assisted UAV system is scalable, efficient, and capable of providing robust real-time traffic surveillance in Smart City environments. The proposed framework follows a structured workflow involving data acquisition from IoT sensors, real-time data processing, and cooperative localization through multisource information fusion. This enables accurate positioning and efficient monitoring, ensuring efficient real-time traffic monitoring and localization.