Fast Incremental Bundle Adjustment with Covariance Recovery

Fast Incremental Bundle Adjustment with Covariance Recovery

Stať ve sborníku v databázi WoS či Scopus

Effcient algorithms exist to obtain a sparse 3D representation of the environment. Bundle adjustment (BA) and structure from motion (SFM) are techniques used to estimate both the camera poses and the set of sparse points in the environment. Many applications require such reconstruction to be performed online, while acquiring the data and produce an updated result every step. Furthermore, using active feedback about the quality of the reconstruction can help selecting the best views to increase the accuracy as well as to maintain a reasonable size of the collected data. This paper provides novel and efcient solutions to solving the associated NLS incrementally, and to compute not only the optimal solution but also the associated uncertainty. The proposed technique highly increases the efciency of the incremental BA solver for long camera trajectory applications and provides extremely fast covariance recovery.

Effcient algorithms exist to obtain a sparse 3D representation of the environment. Bundle adjustment (BA) and structure from motion (SFM) are techniques used to estimate both the camera poses and the set of sparse points in the environment. Many applications require such reconstruction to be performed online, while acquiring the data and produce an updated result every step. Furthermore, using active feedback about the quality of the reconstruction can help selecting the best views to increase the accuracy as well as to maintain a reasonable size of the collected data. This paper provides novel and efcient solutions to solving the associated NLS incrementally, and to compute not only the optimal solution but also the associated uncertainty. The proposed technique highly increases the efciency of the incremental BA solver for long camera trajectory applications and provides extremely fast covariance recovery.

bundle adjustment, incremental, covariance, 3D reconstruction, structure from motion

bundle adjustment, incremental, covariance, 3D reconstruction, structure from motion

ILA, V.; POLOK, L.; ŠOLONY, M.; ISTENIČ, K.

2018

12.10.2017

Institute of Electrical and Electronics Engineers

Qingdao

978-989-8425-47-8

2017 Fifth International Conference on 3D Vision

1

9

8

https://www.fit.vut.cz/research/publication/11542/

egpaper_final