Selecting good measurements via ℓ1 relaxation: A convex approach for robust estimation over graphs

L Carlone, A Censi, F Dellaert - 2014 IEEE/RSJ International …, 2014 - ieeexplore.ieee.org
Pose graph optimization is an elegant and efficient formulation for robot localization and
map**. Experimental evidence suggests that, in real problems, the set of measurements …

Expectation-maximization for adaptive mixture models in graph optimization

T Pfeifer, P Protzel - 2019 international conference on robotics …, 2019 - ieeexplore.ieee.org
Non-Gaussian and multimodal distributions are an important part of many recent robust
sensor fusion algorithms. In difference to robust cost functions, they are probabilistically …

Constructing category-specific models for monocular object-slam

P Parkhiya, R Khawad, JK Murthy… - … on Robotics and …, 2018 - ieeexplore.ieee.org
We present a new paradigm for real-time object-oriented SLAM with a monocular camera.
Contrary to previous approaches, that rely on object-level models, we construct category …

Factor graph based 3d multi-object tracking in point clouds

J Pöschmann, T Pfeifer, P Protzel - 2020 IEEE/RSJ International …, 2020 - ieeexplore.ieee.org
Accurate and reliable tracking of multiple moving objects in 3D space is an essential
component of urban scene understanding. This is a challenging task because it requires the …

A high-precision LiDAR-inertial odometry via Kalman filter and factor graph optimization

J Tang, X Zhang, Y Zou, Y Li, G Du - IEEE Sensors Journal, 2023 - ieeexplore.ieee.org
For simultaneous localization and map** (SLAM) in large-scale scenarios, the influence of
long-distance and high-speed motion cannot be ignored because the risk of huge odometry …

A comparison of graph optimization approaches for pose estimation in SLAM

A Jurić, F Kendeš, I Marković… - 2021 44th International …, 2021 - ieeexplore.ieee.org
Simultaneous localization and map** (SLAM) is an important tool that enables
autonomous navigation of mobile robots through unknown environments. As the name …

Low-latency Visual-based High-Quality 3D Reconstruction using Point Cloud Optimization

P Chi, Z Wang, H Liao, T Li, J Zhan, X Wu… - IEEE Sensors …, 2023 - ieeexplore.ieee.org
In recent years, 3-D reconstruction has been widely used in robot pose estimation, mine
exploration, building of digital twins, and other fields. Visual-based reconstruction methods …

Opt: A domain specific language for non-linear least squares optimization in graphics and imaging

Z DeVito, M Mara, M Zollhöfer, G Bernstein… - ACM Transactions on …, 2017 - dl.acm.org
Many graphics and vision problems can be expressed as non-linear least squares
optimizations of objective functions over visual data, such as images and meshes. The …

Megba: A gpu-based distributed library for large-scale bundle adjustment

J Ren, W Liang, R Yan, L Mai, S Liu, X Liu - European Conference on …, 2022 - Springer
Abstract Large-scale Bundle Adjustment (BA) requires massive memory and computation
resources which are difficult to be fulfilled by existing BA libraries. In this paper, we propose …

What localizes beneath: A metric multisensor localization and map** system for autonomous underground mining vehicles

A Jacobson, F Zeng, D Smith, N Boswell… - Journal of Field …, 2021 - Wiley Online Library
Robustly and accurately localizing vehicles in underground mines is particularly challenging
due to the unavailability of GPS, variable and often poor lighting conditions, visual aliasing …