A system includes a control station that enables efficient human collaboration with automated object tracking. The control station is communicatively coupled to an aerial vehicle to receive full motion video of a ground scene taken by an airborne sensor of the aerial vehicle. The control station spatially registers features of a movable object present in the ground scene and determines motion of the movable object relative to the ground scene. The control station predicts a trajectory of the movable objective relative to the ground scene. The control station tracks the movable object based on data fusion of: (i) the spatially registered features; (ii) the determined motion; and (iii) the predicted trajectory of the movable object. The control station presents a tracking annotation and a determined confidence indicator for the tracking annotation on a user interface device to facilitate human collaboration with object tracking.