Joint optimization based on direct sparse stereo visual-inertial odometry

Shuhuan Wen, Yanfang Zhao, Hong Zhang (Lead / Corresponding author), Hak Keung Lam, Luigi Manfredi

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)
178 Downloads (Pure)


This paper proposes a novel fusion of an inertial measurement unit (IMU) and stereo camera method based on direct sparse odometry (DSO) and stereo DSO. It jointly optimizes all model parameters within a sliding window, including the inverse depth of all selected pixels and the internal or external camera parameters of all keyframes. The vision part uses a photometric error function that optimizes 3D geometry and camera pose in a combined energy functional. The proposed algorithm uses image blocks to extract neighboring image features and directly forms measurement residuals in the image intensity space. A fixed-baseline stereo camera solves scale drift. IMU information is accumulated between several frames using manifold pre-integration and is inserted into the optimization as additional constraints between keyframes. The scale and gravity inserted are incorporated into the stereo visual inertial odometry model and are optimized together with other variables such as poses. The experimental results show that the tracking accuracy and robustness of the proposed method are superior to those of the state-of-the-art fused IMU method. In addition, compared with previous semi-dense direct methods, the proposed method displays a higher reconstruction density and scene recovery.
Original languageEnglish
Pages (from-to)791-809
Number of pages19
JournalAutonomous Robots
Issue number5
Early online date10 Jan 2020
Publication statusPublished - 1 May 2020


  • Direct sparse odometry
  • IMU pre-integration
  • Sliding window optimization
  • 3D reconstruction

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Joint optimization based on direct sparse stereo visual-inertial odometry'. Together they form a unique fingerprint.

Cite this