Improved Ground-Based Monocular Visual Odometry Estimation using Inertially-Aided Convolutional Neural Networks

Abstract

While Convolutional Neural Networks (CNNs) can estimate frame-to-frame (F2F) motion even with monocular images, additional inputs can improve Visual Odometry (VO) predictions. In this thesis, a FlowNetS-based [1] CNN architecture estimates VO using sequential images from the KITTI Odometry dataset [2]. For each of three output types (full six degrees of freedom (6-DoF), Cartesian translation, and transitional scale), a baseline network with only image pair input is compared with a nearly identical architecture that is also given an additional rotation estimate such as from an Inertial Navigation System (INS). The inertially-aided networks show an order of magnitude improvement over the baseline when predicting rotation, but the aided rotation predictions are still worse than the input rotations. Translation predictions are not necessarily helped either. A full-trajectory analysis gives similar results. The INS-aided neural networks are also tested for sensitivity to angular random walk (ARW) and bias errors in the sensor measurements.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 26, 2020
Accession Number
AD1104210

Entities

People

  • Josiah D. Watson

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Ground and Sea Platforms
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence Software
  • Computer Vision
  • Convolutional Neural Networks
  • Detectors
  • Feature Extraction
  • Global Positioning Systems
  • Inertial Measurement Units
  • Inertial Navigation
  • Inertial Navigation Systems
  • Information Science
  • Navigation
  • Neural Networks
  • Recurrent Neural Networks
  • Three Dimensional
  • Two Dimensional
  • United States Government

Readers

  • Computer Vision.
  • Inertial Navigation Systems.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks