Pan-Tilt Modelling for Face Detection

Object detection is one of the important application in the surveillance system. In system design, a model is needed to be used for the compensator design process. The black-box modeling method is used so that we can get the mathematical model of the plant without using physics laws, while it is used an experimental approach so that it takes input and output data from the open-loop system response. In modeling the system, two datasets are required to estimate the model and validate the data. In the process, Arduino Mega controller commanded to transmit Pulse Width Modulation (PWM) signals on the pan and tilt servo motors. The command sets motion to pan and tilt systems which installed a camera in it, and the dataset retrieval process can be performed. In this case, the PWM signal as input and the center coordinates of the face (pixels) as outputs based on the viola jones method for the image processing of the open-loop system. The results of the mathematical model of the system show that the data obtained is quite accurate, it is proved from the estimation and data validation that has been done.