Target unmanned aerial vehicle state estimation method and device based on monocular vision

The invention discloses a target unmanned aerial vehicle state estimation method and device based on monocular vision. The method comprises the steps that (1) a sensor on a tracking unmanned aerial vehicle is used for obtaining state information of the tracking unmanned aerial vehicle; (2) the wind speed is calculated by combining stress analysis of the unmanned aerial vehicle; (3) obtaining an image of the target unmanned aerial vehicle by tracking a pan-tilt camera on the unmanned aerial vehicle, obtaining a position and a posture of the target unmanned aerial vehicle in a camera coordinate system by using a posture detection algorithm, and converting the position and the posture into a global coordinate system; (4) constructing a target unmanned aerial vehicle state estimation model containing wind disturbance according to the wind speed obtained through calculation; predicting the state of the target unmanned aerial vehicle by using the state estimation model, and correcting and updating the state of the