Target tracking based on SURF and image based visual servoing

Abstract

In this paper we present a combination between a speed up robust features (SURF) and the image based visual servoing control law; in order to achieve a robust tracking mission. The validation of the proposed approach insured by the control of turret Pan-Tilt system using the visual features acquired by a webcam, and these visual features are extracted by the SURF algorithm; in the constraints of the variation of the scale and the rotation of the image; so that the use of the visual features in the image based visual servoing control law to compute the kinematics screw of the camera in the image frame. For tracking an object we need to introduce the jacobian of the robot to transfer the values of velocities from the camera frame to the robot articulation joints.