V
Viorela Ila
Researcher at Australian National University
Publications - 51
Citations - 2346
Viorela Ila is an academic researcher from Australian National University. The author has contributed to research in topics: Simultaneous localization and mapping & Motion estimation. The author has an hindex of 15, co-authored 51 publications receiving 1877 citations. Previous affiliations of Viorela Ila include University of Girona & Spanish National Research Council.
Papers
More filters
Journal ArticleDOI
iSAM2: Incremental smoothing and mapping using the Bayes tree
TL;DR: The Bayes tree is applied to obtain a completely novel algorithm for sparse nonlinear incremental optimization, named iSAM2, which achieves improvements in efficiency through incremental variable re-ordering and fluid relinearization, eliminating the need for periodic batch steps.
Proceedings ArticleDOI
iSAM2: Incremental smoothing and mapping with fluid relinearization and incremental variable reordering
TL;DR: iSAM2 is a fully incremental, graph-based version of incremental smoothing and mapping (iSAM), based on a novel graphical model-based interpretation of incremental sparse matrix factorization methods, afforded by the recently introduced Bayes tree data structure.
Journal ArticleDOI
Information-Based Compact Pose SLAM
TL;DR: This work introduces an approach that takes into account only highly informative loop-closure links and nonredundant poses of Pose SLAM, and introduces a method to search for neighboring poses whose complexity ranges from logarithmic in the usual case to linear in degenerate situations.
Book ChapterDOI
The Bayes Tree: An Algorithmic Foundation for Probabilistic Robot Mapping
TL;DR: The Bayes tree is applied to obtain a completely novel algorithm for sparse nonlinear incremental optimization, that combines incremental updates with fluid relinearization of a reduced set of variables for efficiency, combined with fast convergence to the exact solution.
Proceedings ArticleDOI
3D reconstruction of underwater structures
TL;DR: The technique is a highly accurate sparse 3D reconstruction of underwater structures such as corals, constructed from synchronized high definition videos collected using a wide baseline stereo rig.