The invention relates to an unmanned aerial vehicle ground target positioning method based on different-source image matching, and the method comprises the following steps: S1, obtaining a high-resolution remote sensing satellite map of a flight region of an unmanned aerial vehicle from the Internet according to a flight task of the unmanned aerial vehicle; s2, the unmanned aerial vehicle carries a visible light camera, carpet type search is carried out in the flight area, the pitch angle of the camera is adjusted so that the camera can keep ortho-shooting on the target, and an ortho-image of the target is shot; s3, processing the aerial image; s4, performing sliding window search on the satellite base map to obtain a plurality of base map blocks, and searching a base map block closest to the aerial photo in all the base map blocks; and S5, according to a matching pair obtained by carrying out heterogeneous image matching on the aerial image and the closest base image block, calculating a homography matrix M of the two images by utilizing OpenCV, mapping the central point of the aerial image to the satellite base image by M, and obtaining the central point of the aerial image, namely the longitude and latitude of the center of the target. The method provided by the invention is stronger in anti-interference capability, can better adapt to a field environment, and can carry out unmanned aerial vehicle ground target positioning without depending on a GPS (Global Positioning System).