Paper
18 November 2019 Fast bundle adjustment using adaptive moment estimation
Author Affiliations +
Abstract
Bundle adjustment (BA) is an important task for feature matching in multiple applications such as image stitching and position mapping. It aims to reconstruct the 8-parameter homography matrix, which is used for perspective transformation among different images. The existing algorithms such as the Levenberg-Marquardt (LM) algorithm and the Gauss{Newton (GN) algorithm require much computation and a large number of iterations. To accelerate reconstruction speed, here we propose a novel BA algorithm based on adaptive moment estimation (Adam). The Adam solver uses the mean and uncentered variance of the gradients in the previous iterations to dynamically adjust the gradient direction of the current iteration, which improves reconstruction quality and increases convergence speed. Besides, it requires only the first derivate calculation, and thus obtains low computational complexity. Both simulations and experiments validate that the proposed method converges faster than the conventional BA methods.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tiexin Liu, Liheng Bian, Xianbin Cao, and Jun Zhang "Fast bundle adjustment using adaptive moment estimation", Proc. SPIE 11187, Optoelectronic Imaging and Multimedia Technology VI, 111871R (18 November 2019); https://doi.org/10.1117/12.2538745
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Algorithm development

Reconstruction algorithms

3D image reconstruction

Electronics

3D image processing

Associative arrays

Astatine

Back to Top