Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization

Visual–inertial odometry (VIO) is the primary supporting technology for autonomous systems, but it faces three major challenges: initialization sensitivity, dynamic illumination, and multi-sensor fusion. In order to overcome these challenges, this paper proposes stereo direct sparse visual–inertial...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenhui Fu, Jiangang Lu
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4852
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406255921102848
author Chenhui Fu
Jiangang Lu
author_facet Chenhui Fu
Jiangang Lu
author_sort Chenhui Fu
collection DOAJ
description Visual–inertial odometry (VIO) is the primary supporting technology for autonomous systems, but it faces three major challenges: initialization sensitivity, dynamic illumination, and multi-sensor fusion. In order to overcome these challenges, this paper proposes stereo direct sparse visual–inertial odometry with efficient second-order minimization. It is entirely implemented using the direct method, which includes a depth initialization module based on visual–inertial alignment, a stereo image tracking module, and a marginalization module. Inertial measurement unit (IMU) data is first aligned with a stereo image to initialize the system effectively. Then, based on the efficient second-order minimization (ESM) algorithm, the photometric error and the inertial error are minimized to jointly optimize camera poses and sparse scene geometry. IMU information is accumulated between several frames using measurement preintegration and is inserted into the optimization as an additional constraint between keyframes. A marginalization module is added to reduce the computation complexity of the optimization and maintain the information about the previous states. The proposed system is evaluated on the KITTI visual odometry benchmark and the EuRoC dataset. The experimental results demonstrate that the proposed system achieves state-of-the-art performance in terms of accuracy and robustness.
format Article
id doaj-art-a24b7b129ef14afa97ffdb7a3bf435b7
institution Kabale University
issn 1424-8220
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a24b7b129ef14afa97ffdb7a3bf435b72025-08-20T03:36:26ZengMDPI AGSensors1424-82202025-08-012515485210.3390/s25154852Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order MinimizationChenhui Fu0Jiangang Lu1State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaState Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, ChinaVisual–inertial odometry (VIO) is the primary supporting technology for autonomous systems, but it faces three major challenges: initialization sensitivity, dynamic illumination, and multi-sensor fusion. In order to overcome these challenges, this paper proposes stereo direct sparse visual–inertial odometry with efficient second-order minimization. It is entirely implemented using the direct method, which includes a depth initialization module based on visual–inertial alignment, a stereo image tracking module, and a marginalization module. Inertial measurement unit (IMU) data is first aligned with a stereo image to initialize the system effectively. Then, based on the efficient second-order minimization (ESM) algorithm, the photometric error and the inertial error are minimized to jointly optimize camera poses and sparse scene geometry. IMU information is accumulated between several frames using measurement preintegration and is inserted into the optimization as an additional constraint between keyframes. A marginalization module is added to reduce the computation complexity of the optimization and maintain the information about the previous states. The proposed system is evaluated on the KITTI visual odometry benchmark and the EuRoC dataset. The experimental results demonstrate that the proposed system achieves state-of-the-art performance in terms of accuracy and robustness.https://www.mdpi.com/1424-8220/25/15/4852direct sparse odometryefficient second-order minimizationmarginalizationsliding window optimization
spellingShingle Chenhui Fu
Jiangang Lu
Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
Sensors
direct sparse odometry
efficient second-order minimization
marginalization
sliding window optimization
title Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
title_full Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
title_fullStr Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
title_full_unstemmed Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
title_short Stereo Direct Sparse Visual–Inertial Odometry with Efficient Second-Order Minimization
title_sort stereo direct sparse visual inertial odometry with efficient second order minimization
topic direct sparse odometry
efficient second-order minimization
marginalization
sliding window optimization
url https://www.mdpi.com/1424-8220/25/15/4852
work_keys_str_mv AT chenhuifu stereodirectsparsevisualinertialodometrywithefficientsecondorderminimization
AT jianganglu stereodirectsparsevisualinertialodometrywithefficientsecondorderminimization