Adapted LBP Based Fast Image Mosaicing Algorithm for UAV Images

UAV images are widely used in many applications, however, there are some problems with these images, e.g. the Field Of View (FOV) of these images is smaller than those of traditional aerial images, and also; the resolution of them is less than those of aerial ones. As a solution for these problems, these images with small views can be mosaiced together in order to increase the visual field and the image resolution. The most important part of image mosaicing algorithm is to find out correspondence points between the split images. Different approaches were proposed for features matching task, but most of them takes a long calculation time and give a lot of false associations. Since the Local Binary Patterns Descriptors (LBPDs) provide good and robust description for the detected key-points in two overlapped images, fast and good features matching can be obtained using the measured Hamming distance between two LBPDs. But LBP approach depends on interpolation technique; which leads to false matching results, therefore, in our proposed algorithm, we will develop Adapted LBPDs in order to overcome drawback of LBP technique.