Keyframe-based visual–inertial odometry using nonlinear optimization

By Stefan Leutenegger, Simon Lynen, M. Bosse, Roland Yves Siegwart, Paul Timothy Furgale. 2015

1,886 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing (2018, methodology): “Traditional approaches to autonomous MAV navigation build on visual inertial odometry (VIO) [5], [1], [13], [24] or simultaneous localization and mapping (SLAM) [21], [23], which are used to provide a pose estimate of the drone relative to an internal metric map [14], [4].”
Visual-Inertial Monocular SLAM With Map Reuse (2016, background): “This is due to the marginalization of past states to maintain a constant computational cost [1]– [3], [5], [6], or the use of full smoothing [4], [7], with an almost constant complexity in exploration but that can be as expensive as a batch method in the presence of loop closures.”
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features (2018, methodology): “• We compare the performances of the proposed PL-VIO with three state-of-the-art monocular VIO methods including ROVIO [17], OKVIS [18], and VINS-Mono [32] on both the EuRoc dataset and the PennCOSYVIO dataset, for which detailed evaluation results are reported.”
Direct Sparse Odometry (2016, methodology): “This technique is called “First Estimate Jacobians” [14, 10], and .”
RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation (2018, positive): “Figure 11 shows the paths computed for three EuRoC sequences using a stereo odometry approach (F2M) and the visual – inertial odometry approach of OKVIS, compared against the ground truths.”
LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping (2021, methodology): “Though OKVIS shows superior performance using a stereo camera, it is not optimized for a monocular camera.”
Extending Monocular Visual Odometry to Stereo Camera Systems by Scale optimization (2019, background): “To solve the scale problem without intensive computational cost, authors [4]–[6] have fused monocular VO with an inertial measurement unit (IMU) to create visual-inertial navigation systems (VINS).”
Visual-Inertial Navigation: A Concise Review (2019, background): “[28] introduced a keyframe-based optimization approach (i.”
LDSO: Direct Sparse Odometry with Loop Closure (2018, background): “Okvis [17] is a feature-based visual-inertial keyframe odometry that maintains a local map of feature points in a constant-size marginalization window (similar to DSO) that does not reuse points once it is out of the local window.”
A survey on vision-based UAV navigation (2018, background): “Currently, as the inertial measurement unit is getting smaller and cheaper, fusing IMU and visual measurement together is gaining much more attention (Leutenegger et al. 2015).”
Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras (2017, methodology): “To keep the active window of bounded size, old keyframes are removed by marginalization using the Schur complement [19, 7].”
Using Inertial Sensors for Position and Orientation Estimation (2017, positive): “n, we will focus on pose estimation using a camera and an IMU that are rigidly attached to each other. Inertial sensors and camera images have successfully been combined for pose estimation, see e.g. [18, 88, 68, 138, 78, 38, 13, 41, 105]. Application areas are for instance robotics, virtual reality”
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator (2017, methodology): “To achieve constant processing time, graph-based VIO methods [15], [17], [18] usually optimize over a bounded-size sliding window of recent states by marginalizing out past states and measurements.”
Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization (2017, background): “We only briefly highlight the ones that, in our opinion, bring a particular value to the robotics community: VIWLS: visual-inertial weighted least-squares optimization with cost terms similar to [1].”
Factor Graphs for Robot Perception (2017, background): “[131, 132] also present VIO and SLAM algorithms that are visualized as factor graphs.”
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM (2020, methodology): “The ﬁrst tightly coupled visual odometry system based on keyframes and bundle adjustment was OKVIS [38], [39] that is also able to use monocular and stereo vision.”
Visual-Inertial Teach and Repeat for Aerial Inspection (2018, background): “{marius.fehr, thomas.schneider, marcin.dymczyk}@mavt.ethz.ch, rsiegwart@ethz.ch 2Google Inc.: jsturm@google.com This reasearch was funded by Google Tango. maplab [7], ORB-SLAM2 [8], OKVIS [9], ROVIO [10] and the visual-inertial navigation system presented in [11] autonomous robots are able to perfor”