An efficient approach towards image stitching in aerial images

Abstract

Aerial images taken by Unmanned Aerial Vehicles (UAV) contain rich geographic information. However, the higher the altitude the cost for image capturing increases and image quality or the visibility decreases. To overcome this issue, people use low altitude UAV’s to capture images in bulk quantities and stitching algorithms were heavily used for merging these images. This paper presents a novel technique to automate this stitching process. This new technique is implemented based on well-known algorithms such as Speededup Robust Features (SURF), Principle Component Analysis (PCA) and Random Sample Consensus (RANSAC). The result of the proposed method was compared with some existing algorithms and the results are presented in this paper.