In this paper, a visual servoing method based on image moments and distance estimation was proposed for a two rotational degrees-of-freedom (DOF) video tracking system for tracking a flying target. The image Jacobian matrix is derived by selecting image moments instead of simple image points as image features. The proposed visual servoing control scheme can track the flying object with irregular image projection and unknown model. Meanwhile, in order to achieve a stable object tracking, the distance between the camera and the flying object is recursively estimated by using Kalman filter on-line. The simulation and experimental results show that the proposed algorithm is effective in flying target tracking.