Object Detection and Optimal Fuzzy-PID Controller Design for Tracking
No Thumbnail Available
Date
2021-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
In this thesis, static and dynamic camera-based object tracking systems have been developed. The static camera-based object tracking system was developed using LabVIEW and Math Script node. The dynamic camera-based object tracking system has been proposed using a Fuzzy-PID controller to locate and expeditiously follow the course/ trajectory of the moving object. The pan/tilt mechanism (a servomechanism) has been used to adjust the pan/azimuth and tilt/elevation positioning of the camera setup. PID, Fuzzy and Fuzzy-PID controllers have been designed for comparison purposes. A genetic algorithm was implemented in order to obtain the optimal values of the Fuzzy-PID controller parameters. The corresponding objective function used for optimization was Integral of Time-weighted Absolute Error (ITAE). The simulation results showed that the pan and tilt system time responses recorded for the Fuzzy-PID controller were 9.4 and 7.9 milliseconds rise time, and 16 and 15 milliseconds settling time respectively. In both cases the steady-state error and the maximum overshoot were negligible i.e., steady-state was reached. The overall performance shows that GA tuned Fuzzy-PID controller has given us the best results in contrast to the other control techniques.
Description
Keywords
Object Tracking, LabVIEW, Fuzzy-PID, Pan/Tilt System, Genetic Algorithm.