The invention discloses a fuzzy image restoration method for a small unmanned aerial vehicle, and relates to the technical field of computer vision. The method is emphatically characterized in that the practicability and robustness of fuzzy image restoration of the small unmanned aerial vehicle are enhanced. The method comprises the following steps of (1) recognizing images of the small unmanned aerial vehicle by utilizing an unmanned aerial vehicle image fuzzy type recognition algorithm based on a convolutional neural network to obtain fuzzy types; (2) restoring the image with the fuzzy typebeing a motion fuzzy type by utilizing a motion fuzzy image blind restoration algorithm with a mixed characteristic regularization constraint to obtain a clear restored image; (3) restoring the imagewith the fuzzy type being an atmospheric fuzzy type by utilizing an image defogging algorithm based on mixed prior and guide filtering to obtain a clear restored image; and (4) restoring the image with the fuzzy type being an out-of-focus fuzzy type by utilizing an out-of-focus fuzzy blind restoration algorithm based on frequency spectrum preprocessing and improved Hough transform to obtain a clear restored image.