As panoramic image stitching includes image registration and blending which combines the different view images, which has overlapping area and forms a high resolution image. In previous paper for image registration they used Speed Up Robust Features (SURF), k-d trees and Random Space Consensus (RANSAC) algorithms for detecting interest points, matching those interest points and eliminating mismatch points respectively for the given images.But in this paper instead of k-d trees Fast Library for Approximate Nearest Neighbor Search (FLANN) trees are used because it is easy to implement and its performance is higher when compared with other nearest neighbor search algorithms. FLANN trees are efficient to find nearest neighbor features and are mostly useful for large data scaling. The theoretical and performance analysis of the AERIAL image stitching is shown. © Research India Publications.