Visual Tracking Control for Inertial Stabilization System

Abstract

This paper presents an approach to the image tracking for an inertial stabilization system, comprised of a
camera system set up into the aircraft structure. The motion control of the camera system can be divided into
two portions; the first portion is a feedback control system, the second portion is the autonomous tracking
objects in video sequences. We propose an object tracking algorithm based on a combined HSV color
probability histogram model using a CAMshift algorithm that finds the most probable target position in the
current frame. The CAMshift algorithm applications can track objects presenting strong modifications of
shape. We can quote the management of the target appearance changes during the sequence. The feedback
control loop for the pan-tilt unit would send rate commands to move the camera position in order to keep the
target in the center of the camera image. The capability of the tracker to handle in real-time target scale
variation, partial occlusion, and significant clutter, is demonstrated. The experiment results are presented to
verify the effectiveness of the proposed method in image tracking object