Solving monocular visual odometry scale factor with adaptive step length estimates for pedestrians using handheld devices

Nicolas Antigny, Hideaki Uchiyama, Myriam Servières, Valérie Renaudin, Diego Gabriel Francis Thomas, Rin-Ichiro Taniguchi

研究成果: ジャーナルへの寄稿記事

抄録

The urban environments represent challenging areas for handheld device pose estimation (i.e., 3D position and 3D orientation) in large displacements. It is even more challenging with low-cost sensors and computational resources that are available in pedestrian mobile devices (i.e., monocular camera and Inertial Measurement Unit). To address these challenges, we propose a continuous pose estimation based on monocular Visual Odometry. To solve the scale ambiguity and suppress the scale drift, an adaptive pedestrian step lengths estimation is used for the displacements on the horizontal plane. To complete the estimation, a handheld equipment height model, with respect to the Digital Terrain Model contained in Geographical Information Systems, is used for the displacement on the vertical axis. In addition, an accurate pose estimation based on the recognition of known objects is punctually used to correct the pose estimate and reset the monocular Visual Odometry. To validate the benefit of our framework, experimental data have been collected on a 0.7 km pedestrian path in an urban environment for various people. Thus, the proposed solution allows to achieve a positioning error of 1.6-7.5% of the walked distance, and confirms the benefit of the use of an adaptive step length compared to the use of a fixed-step length.

元の言語英語
記事番号953
ジャーナルSensors (Switzerland)
19
発行部数4
DOI
出版物ステータス出版済み - 2 2 2019

Fingerprint

Equipment and Supplies
estimates
Geographic Information Systems
information systems
ambiguity
positioning
resources
cameras
Units of measurement
Costs and Cost Analysis
Mobile devices
sensors
Information systems
Cameras
Pedestrians
Sensors
Costs

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

これを引用

Solving monocular visual odometry scale factor with adaptive step length estimates for pedestrians using handheld devices. / Antigny, Nicolas; Uchiyama, Hideaki; Servières, Myriam; Renaudin, Valérie; Thomas, Diego Gabriel Francis; Taniguchi, Rin-Ichiro.

:: Sensors (Switzerland), 巻 19, 番号 4, 953, 02.02.2019.

研究成果: ジャーナルへの寄稿記事

@article{b21ecae0c2ab4dc7870289b68277336c,
title = "Solving monocular visual odometry scale factor with adaptive step length estimates for pedestrians using handheld devices",
abstract = "The urban environments represent challenging areas for handheld device pose estimation (i.e., 3D position and 3D orientation) in large displacements. It is even more challenging with low-cost sensors and computational resources that are available in pedestrian mobile devices (i.e., monocular camera and Inertial Measurement Unit). To address these challenges, we propose a continuous pose estimation based on monocular Visual Odometry. To solve the scale ambiguity and suppress the scale drift, an adaptive pedestrian step lengths estimation is used for the displacements on the horizontal plane. To complete the estimation, a handheld equipment height model, with respect to the Digital Terrain Model contained in Geographical Information Systems, is used for the displacement on the vertical axis. In addition, an accurate pose estimation based on the recognition of known objects is punctually used to correct the pose estimate and reset the monocular Visual Odometry. To validate the benefit of our framework, experimental data have been collected on a 0.7 km pedestrian path in an urban environment for various people. Thus, the proposed solution allows to achieve a positioning error of 1.6-7.5{\%} of the walked distance, and confirms the benefit of the use of an adaptive step length compared to the use of a fixed-step length.",
author = "Nicolas Antigny and Hideaki Uchiyama and Myriam Servi{\`e}res and Val{\'e}rie Renaudin and Thomas, {Diego Gabriel Francis} and Rin-Ichiro Taniguchi",
year = "2019",
month = "2",
day = "2",
doi = "10.3390/s19040953",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

TY - JOUR

T1 - Solving monocular visual odometry scale factor with adaptive step length estimates for pedestrians using handheld devices

AU - Antigny, Nicolas

AU - Uchiyama, Hideaki

AU - Servières, Myriam

AU - Renaudin, Valérie

AU - Thomas, Diego Gabriel Francis

AU - Taniguchi, Rin-Ichiro

PY - 2019/2/2

Y1 - 2019/2/2

N2 - The urban environments represent challenging areas for handheld device pose estimation (i.e., 3D position and 3D orientation) in large displacements. It is even more challenging with low-cost sensors and computational resources that are available in pedestrian mobile devices (i.e., monocular camera and Inertial Measurement Unit). To address these challenges, we propose a continuous pose estimation based on monocular Visual Odometry. To solve the scale ambiguity and suppress the scale drift, an adaptive pedestrian step lengths estimation is used for the displacements on the horizontal plane. To complete the estimation, a handheld equipment height model, with respect to the Digital Terrain Model contained in Geographical Information Systems, is used for the displacement on the vertical axis. In addition, an accurate pose estimation based on the recognition of known objects is punctually used to correct the pose estimate and reset the monocular Visual Odometry. To validate the benefit of our framework, experimental data have been collected on a 0.7 km pedestrian path in an urban environment for various people. Thus, the proposed solution allows to achieve a positioning error of 1.6-7.5% of the walked distance, and confirms the benefit of the use of an adaptive step length compared to the use of a fixed-step length.

AB - The urban environments represent challenging areas for handheld device pose estimation (i.e., 3D position and 3D orientation) in large displacements. It is even more challenging with low-cost sensors and computational resources that are available in pedestrian mobile devices (i.e., monocular camera and Inertial Measurement Unit). To address these challenges, we propose a continuous pose estimation based on monocular Visual Odometry. To solve the scale ambiguity and suppress the scale drift, an adaptive pedestrian step lengths estimation is used for the displacements on the horizontal plane. To complete the estimation, a handheld equipment height model, with respect to the Digital Terrain Model contained in Geographical Information Systems, is used for the displacement on the vertical axis. In addition, an accurate pose estimation based on the recognition of known objects is punctually used to correct the pose estimate and reset the monocular Visual Odometry. To validate the benefit of our framework, experimental data have been collected on a 0.7 km pedestrian path in an urban environment for various people. Thus, the proposed solution allows to achieve a positioning error of 1.6-7.5% of the walked distance, and confirms the benefit of the use of an adaptive step length compared to the use of a fixed-step length.

UR - http://www.scopus.com/inward/record.url?scp=85064887631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064887631&partnerID=8YFLogxK

U2 - 10.3390/s19040953

DO - 10.3390/s19040953

M3 - Article

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

M1 - 953

ER -