OrcVIO: Object residual constrained Visual-Inertial Odometry

Mo Shan, Vikas Dhiman, Qiaojun Feng, Jinzhao Li, Nikolay Atanasov
7/29/2020
cs.ROcs.CV

Official code: shanmo/OrcVIO-Stereo-Mapping (17 stars, last commit 2021-10-20).

Abstract

Introducing object-level semantic information into simultaneous localization and mapping (SLAM) system is critical. It not only improves the performance but also enables tasks specified in terms of meaningful objects. This work presents OrcVIO, for visual-inertial odometry tightly coupled with tracking and optimization over structured object models. OrcVIO differentiates through semantic feature and bounding-box reprojection errors to perform batch optimization over the pose and shape of objects. The estimated object states aid in real-time incremental optimization over the IMU-camera states. The ability of OrcVIO for accurate trajectory estimation and large-scale object-level mapping is evaluated using real data.

View on arXivView PDF

Code Implementations(1)

shanmo/OrcVIO-Stereo-MappingOfficial100%

OrcVIO Stereo and object mapping

172C, C++Oct 6, 20215 years ago

Similar Papers

SemanticSLAM: Learning based Semantic Map Construction and Robust Camera Localization

86% match1 repo162024

VOOM: Robust Visual Object Odometry and Mapping using Hierarchical Landmarks

84% match1 repo1422024

Geometry-Constrained Monocular Scale Estimation Using Semantic Segmentation for Dynamic Scenes

82% match2025

SAGE-ICP: Semantic Information-Assisted ICP

82% match1 repo502023

FMCW-LIO: A Doppler LiDAR-Inertial Odometry

82% match1 repo932026

Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection

82% match2024

Cite this paper

@article{shan2020orcvio,
  title  = {OrcVIO: Object residual constrained Visual-Inertial Odometry},
  author = {Mo Shan and Vikas Dhiman and Qiaojun Feng and Jinzhao Li and Nikolay Atanasov},
  year   = {2020},
  eprint = {2007.15107},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2007.15107}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2007.15107.svg)](https://codeofpaper.com/paper/2007.15107)

Discussion