Image synthesis method and device

[0040] Embodiment 1 of the present application provides an image synthesis method, such as figure 1 shown, including the following steps:

[0041] Step 110, respectively extracting regions to be detected from multiple images to be synthesized;

[0042] In the embodiment of the present application, when multiple photographed images from different angles in the same scene are synthesized (for example, a building under a certain scenery is photographed, the building and its surrounding environment are included in each image, multiple image for scene synthesis), first extract the area to be detected from each image to be synthesized, calculate the size of the area to be detected, and then scale each image to be synthesized to a fixed size to facilitate image synthesis;

[0043] Specifically, for the extraction of the area to be detected, the area of ​​common feature points in each image to be synthesized can be extracted from all the images to be synthesized, and this area can be us

[0095] Embodiment 2 of the present application provides an image synthesis device, such as Figure 6 As shown, it includes an image segmentation module 61, an image preprocessing module 62, an image synthesis sequence confirmation module 63, an image registration stitching module 64 and an image synthesis module 65;

[0096] The image segmentation module 61 extracts the area to be detected from multiple images to be synthesized respectively; the image preprocessing module 62 performs rotation, scaling and translation of the image to be synthesized according to the size and position of the area to be detected; the image synthesis sequence confirmation module 63 acquires each An edge feature point of the area to be detected in an image to be synthesized, calculating the distance between the edge feature point of the area to be detected in each image to be synthesized and the edge of the image to be synthesized, and determining the image synthesis of the image to be synthesized accor