Tightly coupled semantic RGB-D inertial odometry for accurate long-term localization and mapping

Naman Patel, Farshad Khorrami, Prashanth Krishnamurthy, Anthony Tzes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we utilize semantically enhanced feature matching and visual inertial bundle adjustment to improve the robustness of odometry especially in feature-sparse environments. A novel semantically enhanced feature matching algorithm is developed for robust: 1) medium and long-term tracking, and 2) loop-closing. Additionally, a semantic visual inertial bundle adjustment algorithm is introduced to robustly estimate pose in presence of ambiguous correspondences or in feature sparse environment. Our tightly coupled semantic RGB-D odometry approach is demonstrated on a real world indoor dataset collected using our unmanned ground vehicle (UGV). Our approach improves traditional visual odometry relying on low-level geometric features like corners, points, and planes for localization and mapping. Additionally, prior approaches are limited due to their sensitivity to scene geometry and changes in light intensity. The semantic inertial odometry is especially important to significantly reduce drifts in longer intervals.

Original languageEnglish (US)
Title of host publication2019 19th International Conference on Advanced Robotics, ICAR 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages523-528
Number of pages6
ISBN (Electronic)9781728124674
DOIs
StatePublished - Dec 2019
Event19th International Conference on Advanced Robotics, ICAR 2019 - Belo Horizonte, Brazil
Duration: Dec 2 2019Dec 6 2019

Publication series

Name2019 19th International Conference on Advanced Robotics, ICAR 2019

Conference

Conference19th International Conference on Advanced Robotics, ICAR 2019
CountryBrazil
CityBelo Horizonte
Period12/2/1912/6/19

ASJC Scopus subject areas

  • Artificial Intelligence
  • Mechanical Engineering
  • Control and Optimization
  • Modeling and Simulation

Fingerprint Dive into the research topics of 'Tightly coupled semantic RGB-D inertial odometry for accurate long-term localization and mapping'. Together they form a unique fingerprint.

Cite this