Image mosaicing for UAV application

In times of disaster acquiring aerial images is challenging. The unmanned aircraft vehicle (UAV) is a low cost vehicle which can be carried close to the disaster site and flown to capture aerial images without any delay. This paper presents some techniques for UAV image mosaicing from a series of overlapped snapshot images. The process can be divided into three steps. The first step is to detect the feature points. The second step is to find the corresponding feature points between two images. The last step is to obtain the transformations for image mosaic using the corresponding points. In the second step, it is difficult to check up corresponding feature points because the feature points may be spurious. We proposed a method to solve this problem. The experimental results demonstrate the effectiveness of the proposed method.