The invention discloses an unmanned aerial vehicle detection image registration method, and relates to an unmanned aerial vehicle detection image registration method, comprising a Harris corner algorithm and an image registration process, and further comprising the following steps: S1, acquiring video information acquired by an unmanned aerial vehicle, and setting a source image set and a registration image set; S2, carrying out the same preprocessing of the source image and the registered image, carrying out the preliminary image rotation, translation and scale transformation through the basic statistical features, and removing the redundant noise; S3, performing Harris corner detection on the source image and the registration image by using a Harris corner algorithm, and recording cornercoordinates; S4, setting a registration area; S5, calculating a correlation coefficient of a registration area of the source image and the registration image; S6, judging the matching degree of the source image and the registration image by using the correlation coefficient; and S7, entering an image registration process. According to the unmanned aerial vehicle detection image registration method, the problem of unmanned aerial vehicle video frame image registration can be effectively solved, and an ideal registration image set is obtained; and the unmanned aerial vehicle detection image registration method has good feature invariance, uniqueness, stability and independence.