Visual-Inertial Monocular SLAM With Map Reuse

By Raul Mur-Artal, Juan D. Tardós. IEEE Robotics and Automation Letters, 2016

732 citations recorded by the source corpus.

In recent years there have been excellent results in visual-inertial odometry techniques, which aim to compute the incremental motion of the sensor with high accuracy and robustness. However, these approaches lack the capability to close loops and trajectory estimation accumulates drift even if the sensor is continually revisiting the same place. In this letter, we present a novel tightly coupled visual-inertial simultaneous localization and mapping system that is able to close loops and reuse its map to achieve zero-drift localization in already mapped areas. While our approach can be applied to any camera configuration, we address here the most general problem of a monocular camera, with its well-known scale ambiguity. We also propose a novel IMU initialization method, which computes the scale, the gravity direction, the velocity, and gyroscope and accelerometer biases, in a few seconds with high accuracy. We test our system in the 11 sequences of a recent micro-aerial vehicle public dataset achieving a typical scale factor error of $1\%$ and centimeter precision. We compare to the state-of-the-art in visual-inertial odometry in sequences with revisiting, proving the better accuracy of our method due to map reuse and no drift accumulation.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/4205bef3748d427b71ce10de44d4755ffb908217

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 Geology

Citations in the corpus

A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots (2018, background): “A number of other approaches to visual-inertial odometry have been proposed [20], [21], [22], [23], [24], [25], [26], but these do not offer publicly-available implementations.”
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras (2016, methodology): “As shown in [22], this sequence can be processed using IMU information.”
Factor Graphs for Robot Perception (2017, methodology): “Finally, Mur-Artal and Tardos [149] added inertial sensing to their prior ORB-SLAM system, a visual SLAM approach based on ORB features detected in a video sequence.”
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM (2020, methodology): “ORB-SLAM-VI [4] was the ﬁrst true visual-inertial SLAM system capable of map reusing.”
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (2020, background): “…three estimations tightly into both the front-end tracking and the back-end non-linear optimization of a sparse direct odometry framework [16]. competitive performance compared to stereo [53, 74] or visual-inertial odometry (VIO) [44, 54, 56, 72], due to the scale drift [62,77] and low robustness.”
Tightly Coupled 3D Lidar Inertial Odometry and Mapping (2019, methodology): “Then the poses of the lidar and the IMU measurements are used to initialize the IMU states, which can be solved by the methods introduced in [10] and [17].”
A Comprehensive Survey of Visual SLAM Algorithms (2022, methodology): “The Visual-Inertial ORB-SLAM (VIORB) algorithm [71] is based on the already presented ORB-SLAM algorithm [44].”
Visual-Inertial Navigation: A Concise Review (2019, background): “indirect visual SLAM is the ORB-SLAM2 [83, 112], which”
A General Optimization-based Framework for Local Odometry Estimation with Multiple Sensors (2019, methodology): “Impressive optimization-based VIO approaches, such as [8, 10, 12], optimized variables over a bounded-size sliding window.”
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features (2018, methodology): “IMU pre-integration has been widely used in optimization-based VIO [18,23,24].”
RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, & New Methods (2019, background): “IMU sensor fusion produces real-time orientations of Virtual Reality headsets, augments SLAM [1]–[3] in Augmented Reality [4]–[6], and allows enhanced navigation and control in many domains.”
A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors (2019, methodology): “Among these work, [6, 7, 9] are ﬁlter-based methods while [8, 10, 11] are optimization-based methods.”