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

Standard

Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors. / Davidson, P.; Raunio, J. P.; Piché, R.

23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings. State Research Center of the Russian Federation, 2016. p. 249-257.

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

Harvard

Davidson, P, Raunio, JP & Piché, R 2016, Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors. in 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings. State Research Center of the Russian Federation, pp. 249-257, SAINT PETERSBURG INTERNATIONAL CONFERENCE ON INTEGRATED NAVIGATION SYSTEMS, 1/01/00.

APA

Davidson, P., Raunio, J. P., & Piché, R. (2016). Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors. In 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings (pp. 249-257). State Research Center of the Russian Federation.

Vancouver

Davidson P, Raunio JP, Piché R. Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors. In 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings. State Research Center of the Russian Federation. 2016. p. 249-257

Author

Davidson, P. ; Raunio, J. P. ; Piché, R. / Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors. 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings. State Research Center of the Russian Federation, 2016. pp. 249-257

Bibtex - Download

@inproceedings{1f43c745827a4858a555c037339dd382,
title = "Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors",
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",
author = "P. Davidson and Raunio, {J. P.} and R. Pich{\'e}",
year = "2016",
language = "English",
pages = "249--257",
booktitle = "23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings",
publisher = "State Research Center of the Russian Federation",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Accurate depth estimation from a sequence of monocular images supported by proprioceptive sensors

AU - Davidson, P.

AU - Raunio, J. P.

AU - Piché, R.

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

KW - Computer vision

KW - Gyroscope

KW - IMU

KW - Odometer

KW - Structure from motion

UR - http://www.scopus.com/inward/record.url?scp=84979573597&partnerID=8YFLogxK

M3 - Conference contribution

SP - 249

EP - 257

BT - 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016 - Proceedings

PB - State Research Center of the Russian Federation

ER -