Bundle adjustment (BA) is an important task for feature matching in multiple applications such as imagestitching and position mapping. It aims to reconstruct the 8-parameter homography matrix, which is used forperspective transformation among di erent images. The existing algorithms such as the Levenberg-Marquardt(LM) algorithm and the Gauss{Newton (GN) algorithm require much computation and a large number ofiterations. To accelerate reconstruction speed, here we propose a novel BA algorithm based on adaptive momentestimation (Adam). The Adam solver uses the mean and uncentered variance of the gradients in the previousiterations to dynamically adjust the gradient direction of the current iteration, which improves reconstructionquality and increases convergence speed. Besides, it requires only the rst derivate calculation, and thus obtainslow computational complexity. Both simulations and experiments validate that the proposed method convergesfaster than the conventional BA methods.
展开▼
