Monocular Visual-IMU Odometry: A Comparative Evaluation of Detector–Descriptor-Based Methods

Xingshuai Dong; Xinghui Dong; Junyu Dong; Huiyu Zhou

doi:10.1109/TITS.2019.2919003

Monocular Visual-IMU Odometry: A Comparative Evaluation of Detector–Descriptor-Based Methods

Xingshuai Dong^*, Xinghui Dong, Junyu Dong, Huiyu Zhou

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Monocular visual-inertial measurement unit (IMU) odometry has been widely used in various intelligent vehicles. As a popular technique, detector-descriptor-based visual-IMU odometry is effective and efficient due to the fact that local descriptors are robust against occlusions, background clutter, and abrupt content changes. However, to our knowledge, there is not a comprehensive and comparative evaluation study on the performance of different combinations of detectors and descriptors recently developed. In order to bridge this gap, we conduct such a comparative study in a unified framework. In particular, six typical routes with different lengths, shapes, and road scenes are selected from the well-known KITTI dataset. We first evaluate the performance of different combinations of salient point detectors and local descriptors using the six routes. Then, we tune the parameters of the best detector or descriptor obtained for each route, to further augment the results. This paper provides not only comprehensive benchmarks for assessing various algorithms but also instructive guidelines and insights for developing detectors and descriptors to handle different road scenes.

Original language	English
Pages (from-to)	2471-2484
Number of pages	14
Journal	IEEE Transactions on Intelligent Transportation Systems
Volume	21
Issue number	6
Early online date	06 Jun 2019
DOIs	https://doi.org/10.1109/TITS.2019.2919003
Publication status	Published - 29 May 2020
Externally published	Yes

Bibliographical note

Funding Information:
Manuscript received December 19, 2017; revised October 28, 2018 and February 9, 2019; accepted May 17, 2019. Date of publication June 6, 2019; date of current version May 29, 2020. The work of X. Dong was supported by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/L022125/1. The work of J. Dong was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 60702014, Grant 61271405, and Grant 61401413, and in part by the Ph.D. Program Foundation, Ministry of Education, China, under Grant 20120132110018. The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union’s Horizon 2020 Research and Innovation Program under the Marie-Sklodowska-Curie under Grant 720325. The Associate Editor for this paper was Q. Ji. (Corresponding author: Xinghui Dong.) X. Dong is with the School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia (e-mail: xingshuai.dong@student.adfa.edu.au).

Publisher Copyright:
© 2000-2011 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Evaluation
local descriptors
monocular visual-IMU odometry
navigation
odometry
salient point detectors

ASJC Scopus subject areas

Automotive Engineering
Mechanical Engineering
Computer Science Applications

Access to Document

10.1109/TITS.2019.2919003Licence: Unspecified

Fingerprint Dive into the research topics of 'Monocular Visual-IMU Odometry: A Comparative Evaluation of Detector–Descriptor-Based Methods'. Together they form a unique fingerprint.

Cite this

@article{76cb04b28e944e80ba109d6b431ee033,

title = "Monocular Visual-IMU Odometry: A Comparative Evaluation of Detector–Descriptor-Based Methods",

abstract = "Monocular visual-inertial measurement unit (IMU) odometry has been widely used in various intelligent vehicles. As a popular technique, detector-descriptor-based visual-IMU odometry is effective and efficient due to the fact that local descriptors are robust against occlusions, background clutter, and abrupt content changes. However, to our knowledge, there is not a comprehensive and comparative evaluation study on the performance of different combinations of detectors and descriptors recently developed. In order to bridge this gap, we conduct such a comparative study in a unified framework. In particular, six typical routes with different lengths, shapes, and road scenes are selected from the well-known KITTI dataset. We first evaluate the performance of different combinations of salient point detectors and local descriptors using the six routes. Then, we tune the parameters of the best detector or descriptor obtained for each route, to further augment the results. This paper provides not only comprehensive benchmarks for assessing various algorithms but also instructive guidelines and insights for developing detectors and descriptors to handle different road scenes.",

keywords = "Evaluation, local descriptors, monocular visual-IMU odometry, navigation, odometry, salient point detectors",

author = "Xingshuai Dong and Xinghui Dong and Junyu Dong and Huiyu Zhou",

note = "Funding Information: Manuscript received December 19, 2017; revised October 28, 2018 and February 9, 2019; accepted May 17, 2019. Date of publication June 6, 2019; date of current version May 29, 2020. The work of X. Dong was supported by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/L022125/1. The work of J. Dong was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 60702014, Grant 61271405, and Grant 61401413, and in part by the Ph.D. Program Foundation, Ministry of Education, China, under Grant 20120132110018. The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union{\textquoteright}s Horizon 2020 Research and Innovation Program under the Marie-Sklodowska-Curie under Grant 720325. The Associate Editor for this paper was Q. Ji. (Corresponding author: Xinghui Dong.) X. Dong is with the School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia (e-mail: xingshuai.dong@student.adfa.edu.au). Publisher Copyright: {\textcopyright} 2000-2011 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2020",

month = may,

day = "29",

doi = "10.1109/TITS.2019.2919003",

language = "English",

volume = "21",

pages = "2471--2484",

journal = "IEEE Transactions on Intelligent Transportation Systems ",

issn = "1524-9050",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Monocular Visual-IMU Odometry: A Comparative Evaluation of Detector–Descriptor-Based Methods

AU - Dong, Xingshuai

AU - Dong, Xinghui

AU - Dong, Junyu

AU - Zhou, Huiyu

N1 - Funding Information: Manuscript received December 19, 2017; revised October 28, 2018 and February 9, 2019; accepted May 17, 2019. Date of publication June 6, 2019; date of current version May 29, 2020. The work of X. Dong was supported by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/L022125/1. The work of J. Dong was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 60702014, Grant 61271405, and Grant 61401413, and in part by the Ph.D. Program Foundation, Ministry of Education, China, under Grant 20120132110018. The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union’s Horizon 2020 Research and Innovation Program under the Marie-Sklodowska-Curie under Grant 720325. The Associate Editor for this paper was Q. Ji. (Corresponding author: Xinghui Dong.) X. Dong is with the School of Engineering and Information Technology, University of New South Wales, Canberra, ACT 2612, Australia (e-mail: xingshuai.dong@student.adfa.edu.au). Publisher Copyright: © 2000-2011 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/5/29

Y1 - 2020/5/29

N2 - Monocular visual-inertial measurement unit (IMU) odometry has been widely used in various intelligent vehicles. As a popular technique, detector-descriptor-based visual-IMU odometry is effective and efficient due to the fact that local descriptors are robust against occlusions, background clutter, and abrupt content changes. However, to our knowledge, there is not a comprehensive and comparative evaluation study on the performance of different combinations of detectors and descriptors recently developed. In order to bridge this gap, we conduct such a comparative study in a unified framework. In particular, six typical routes with different lengths, shapes, and road scenes are selected from the well-known KITTI dataset. We first evaluate the performance of different combinations of salient point detectors and local descriptors using the six routes. Then, we tune the parameters of the best detector or descriptor obtained for each route, to further augment the results. This paper provides not only comprehensive benchmarks for assessing various algorithms but also instructive guidelines and insights for developing detectors and descriptors to handle different road scenes.

AB - Monocular visual-inertial measurement unit (IMU) odometry has been widely used in various intelligent vehicles. As a popular technique, detector-descriptor-based visual-IMU odometry is effective and efficient due to the fact that local descriptors are robust against occlusions, background clutter, and abrupt content changes. However, to our knowledge, there is not a comprehensive and comparative evaluation study on the performance of different combinations of detectors and descriptors recently developed. In order to bridge this gap, we conduct such a comparative study in a unified framework. In particular, six typical routes with different lengths, shapes, and road scenes are selected from the well-known KITTI dataset. We first evaluate the performance of different combinations of salient point detectors and local descriptors using the six routes. Then, we tune the parameters of the best detector or descriptor obtained for each route, to further augment the results. This paper provides not only comprehensive benchmarks for assessing various algorithms but also instructive guidelines and insights for developing detectors and descriptors to handle different road scenes.

KW - Evaluation

KW - local descriptors

KW - monocular visual-IMU odometry

KW - navigation

KW - odometry

KW - salient point detectors

U2 - 10.1109/TITS.2019.2919003

DO - 10.1109/TITS.2019.2919003

M3 - Article

AN - SCOPUS:85078707015

VL - 21

SP - 2471

EP - 2484

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 6

ER -