In this paper the design and development of a vision based power line tracking system for power line inspection is presented to be used on quad-rotor aerial vehicles. The vehicle flies on top of a power line and a combination of the Gaussian steerable filters and the probabilistic Hough line transform were used for power line detection. An unscented Kalman filter was used as an observer to track the position of the line relative to the robot. The system's controller is designed based on backstepping method. The proposed approach has been simulated and actually implemented showing its capability in following lines.