Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning

Muhamad Risqi U. Saputra, Pedro Porto Buarque de Gusmão, Sen Wang, Andrew Markham, Niki Trigoni

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

8 Citations (Scopus)
39 Downloads (Pure)

Abstract

Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data. In this paper, we study whether CL can be applied to complex geometry problems like estimating monocular Visual Odometry (VO). Unlike existing CL approaches, we present a novel CL strategy for learning the geometry of monocular VO by gradually making the learning objective more difficult during training. To this end, we propose a novel geometry-aware objective function by jointly optimizing relative and composite transformations over small windows via bounded pose regression loss. A cascade optical flow network followed by recurrent network with a differentiable windowed composition layer, termed CL-VO, is devised to learn the proposed objective. Evaluation on three real-world datasets shows superior performance of CL-VO over state-of-the-art feature-based and learning-based VO.
Original languageEnglish
Title of host publication2019 International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages3549-3555
Number of pages7
ISBN (Electronic)9781538660270
DOIs
Publication statusPublished - 12 Aug 2019

Publication series

NameInternational Conference on Robotics and Automation (ICRA)
ISSN (Electronic)2577-087X

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning'. Together they form a unique fingerprint.

Cite this