Visual navigation algorithm for unmanned aerial vehicle

The invention relates to the technical field of unmanned aerial vehicles, and discloses an unmanned aerial vehicle visual navigation algorithm, which comprises the following steps of: performing earth mapping transformation according to video images acquired by inertial navigation, satellite navigation and visual navigation, and converting the video images into images which are along the axis of a pod and in the due north direction and have approximate distance resolution with a binding image; calculating the longitude and latitude of the center of the collected image, and reading the corresponding position of the binding image and an area image which is 1.5 times of the size of the collected image; key points of the two images are searched, SIFT feature vectors of the images at the key points are calculated, the Euclidean distance of the feature vectors of the key points is adopted as similarity judgment measurement of the key points in the two images, the accurate positions of the video images in the pre-st