Vision-based state estimation of a ground target for an unmanned helicopter

For a ground target tracking system using an unmanned helicopter, an estimator is proposed in this paper to estimate the states of the target in the world coordinate. With the goal to reduce the estimation errors caused by the noises from on-board sensors, the static features in two successive images are first utilized to calculate the image variation induced by the camera movement, which is then fused with the on-board sensors to estimate the states of the dynamic target. Specifically, the KLT feature tracking algorithm is adopted to track the target and the static features respectively between successive images, then the image information, together with the velocities of the helicopter and the camera, is employed to calculate the target´s velocity in the image plane due to the motion of the camera. Based on this information, the velocity of the target is finally obtained by the utilization of the mapping between the world coordinate and the image plane. Simulation and experiment results are provided to validate the performance of the presented state estimation method.