Multi-Agent Hierarchical Reinforcement Learning for PTZ Camera Control and Visual Enhancement

Border surveillance, as a critical component of national security, places increasingly stringent demands on the target perception capabilities of video monitoring systems, especially in wide-area and complex environments. To address the limitations of existing systems in low-confidence target detection and multi-camera collaboration, this paper proposes a novel visual enhancement method for cooperative control of multiple PTZ (Pan–Tilt–Zoom) cameras based on hierarchical reinforcement learning. The proposed approach establishes a hierarchical framework composed of a Global Planner Agent (GPA) and multiple Local Executor Agents (LEAs). The GPA is responsible for global target assignment, while the LEAs perform fine-grained visual enhancement operations based on the assigned targets. To effectively model the spatial relationships among multiple targets and the perceptual topology of the cameras, a graph-based joint state space is constructed. Furthermore, a graph neural network is employed to extract high-level features, enabling efficient information sharing and collaborative decision-making among cameras. Experimental results in simulation environments demonstrate the superiority of the proposed method in terms of target coverage and visual enhancement performance. Hardware experiments further validate the feasibility and robustness of the approach in real-world scenarios. This study provides an effective solution for multi-camera cooperative surveillance in complex environments.