Tampere University of Technology

TUTCRIS Research Portal

Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings
PublisherState Research Center of the Russian Federation
Pages249-257
Number of pages9
ISBN (Electronic)9785919950370
Publication statusPublished - 2016
Publication typeA4 Article in a conference publication
EventSAINT PETERSBURG INTERNATIONAL CONFERENCE ON INTEGRATED NAVIGATION SYSTEMS -
Duration: 1 Jan 1900 → …

Conference

ConferenceSAINT PETERSBURG INTERNATIONAL CONFERENCE ON INTEGRATED NAVIGATION SYSTEMS
Period1/01/00 → …

Abstract

This paper describes an extended Kalman filter based algorithm for fusion of monocular vision measurements, inertial rate sensor measurements, and camera motion. The motion of the camera between successive images generates a baseline for range computations by triangulation. The recursive estimation algorithm is based on extended Kalman filtering. The depth estimation accuracy is strongly affected by mutual observer and feature point geometry, measurement accuracy of observer motion parameters and line of sight to a feature point. The simulation study investigates how the estimation accuracy is affected by the following parameters: linear and angular velocity measurement errors, camera noise, and observer path. These results draw requirements to the instrumentation and observation scenarios. It was found that under favorable conditions the error in distance estimation does not exceed 2% of the distance to a feature point.

Keywords

  • Computer vision, Gyroscope, IMU, Odometer, Structure from motion

Publication forum classification