Modeling and Control of a Pan–Tilt Servo System for Face Tracking Using Deep Learning and PID

This paper presents a comprehensive modeling and control strategy for a pan–tilt (PT) servo system designed for real-time object tracking (specifically face detection) using deep learning and PID control. The system integrates a YOLO-based neural network to detect and localize the target within an image, mapping its coordinates from 3D space onto the 2D image plane through a mathematically defined geometric camera model. A complete mathematical representation of the pan–tilt mechanism is developed, accounting for all relevant forces and system components. Based on this model, a PID controller is designed, and its parameters are identified and implemented using the Ziegler–Nichols tuning method. Experimental results demonstrate that the system effectively tracks objects in real time, exhibiting minimal latency and precise motor responses. These findings suggest that the proposed approach is well-suited for practical applications, including security surveillance, assistive technologies, and interactive robotics.