Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry

Junyi Yuan; Kaoru Hirota; Zelong Zhang; Yaping Dai

doi:10.1109/CCDC58219.2023.10327350

Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry

Junyi Yuan, Kaoru Hirota, Zelong Zhang, Yaping Dai^*

^*Corresponding author for this work

School of Automation

School of Automation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

When no photometric calibration is available in Direct Sparse Odemetry (DSO), a direct sparse odometry with method of Monocular Non-linear Photometric Transformation Visual Odometry is proposed to improve tracking accuracy and robustness of DSO. Compared with DSO method, a new regularization item and a non-linear brightness transfer function are integrated in proposed method, so it can better simulate the photometric calibration process. The proposed method is evaluated on 50 different sequences of TUM MonoVO datasets containing several hours of video in total. The results show that the rms of aligned error of the proposed Monocular Non-linear Photometric Transformation Visual Odometry method is 11.4% lower than original Direct Sparse Odometry on average. Successful running times of the proposed method are 4.4% more than original Direct Sparse Odometry when the environment light source intensity changing.

Original language	English
Title of host publication	Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2682-2687
Number of pages	6
ISBN (Electronic)	9798350334722
DOIs	https://doi.org/10.1109/CCDC58219.2023.10327350
Publication status	Published - 2023
Event	35th Chinese Control and Decision Conference, CCDC 2023 - Yichang, China Duration: 20 May 2023 → 22 May 2023

Publication series

Name	Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023

Conference

Conference	35th Chinese Control and Decision Conference, CCDC 2023
Country/Territory	China
City	Yichang
Period	20/05/23 → 22/05/23

Keywords

direct sparse odometry
photometric transformation
visual odometry

Access to Document

10.1109/CCDC58219.2023.10327350

Cite this

Yuan, J., Hirota, K., Zhang, Z., & Dai, Y. (2023). Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. In Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023 (pp. 2682-2687). (Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCDC58219.2023.10327350

Yuan, Junyi ; Hirota, Kaoru ; Zhang, Zelong et al. / Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 2682-2687 (Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023).

@inproceedings{d227134a94e541cc8f4eab200a84cfbf,

title = "Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry",

abstract = "When no photometric calibration is available in Direct Sparse Odemetry (DSO), a direct sparse odometry with method of Monocular Non-linear Photometric Transformation Visual Odometry is proposed to improve tracking accuracy and robustness of DSO. Compared with DSO method, a new regularization item and a non-linear brightness transfer function are integrated in proposed method, so it can better simulate the photometric calibration process. The proposed method is evaluated on 50 different sequences of TUM MonoVO datasets containing several hours of video in total. The results show that the rms of aligned error of the proposed Monocular Non-linear Photometric Transformation Visual Odometry method is 11.4% lower than original Direct Sparse Odometry on average. Successful running times of the proposed method are 4.4% more than original Direct Sparse Odometry when the environment light source intensity changing.",

keywords = "direct sparse odometry, photometric transformation, visual odometry",

author = "Junyi Yuan and Kaoru Hirota and Zelong Zhang and Yaping Dai",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 35th Chinese Control and Decision Conference, CCDC 2023 ; Conference date: 20-05-2023 Through 22-05-2023",

year = "2023",

doi = "10.1109/CCDC58219.2023.10327350",

language = "English",

series = "Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023",

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

pages = "2682--2687",

booktitle = "Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023",

address = "United States",

}

Yuan, J, Hirota, K, Zhang, Z & Dai, Y 2023, Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. in Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023, Institute of Electrical and Electronics Engineers Inc., pp. 2682-2687, 35th Chinese Control and Decision Conference, CCDC 2023, Yichang, China, 20/05/23. https://doi.org/10.1109/CCDC58219.2023.10327350

Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. / Yuan, Junyi; Hirota, Kaoru; Zhang, Zelong et al.
Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2682-2687 (Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry

AU - Yuan, Junyi

AU - Hirota, Kaoru

AU - Zhang, Zelong

AU - Dai, Yaping

PY - 2023

Y1 - 2023

N2 - When no photometric calibration is available in Direct Sparse Odemetry (DSO), a direct sparse odometry with method of Monocular Non-linear Photometric Transformation Visual Odometry is proposed to improve tracking accuracy and robustness of DSO. Compared with DSO method, a new regularization item and a non-linear brightness transfer function are integrated in proposed method, so it can better simulate the photometric calibration process. The proposed method is evaluated on 50 different sequences of TUM MonoVO datasets containing several hours of video in total. The results show that the rms of aligned error of the proposed Monocular Non-linear Photometric Transformation Visual Odometry method is 11.4% lower than original Direct Sparse Odometry on average. Successful running times of the proposed method are 4.4% more than original Direct Sparse Odometry when the environment light source intensity changing.

AB - When no photometric calibration is available in Direct Sparse Odemetry (DSO), a direct sparse odometry with method of Monocular Non-linear Photometric Transformation Visual Odometry is proposed to improve tracking accuracy and robustness of DSO. Compared with DSO method, a new regularization item and a non-linear brightness transfer function are integrated in proposed method, so it can better simulate the photometric calibration process. The proposed method is evaluated on 50 different sequences of TUM MonoVO datasets containing several hours of video in total. The results show that the rms of aligned error of the proposed Monocular Non-linear Photometric Transformation Visual Odometry method is 11.4% lower than original Direct Sparse Odometry on average. Successful running times of the proposed method are 4.4% more than original Direct Sparse Odometry when the environment light source intensity changing.

KW - direct sparse odometry

KW - photometric transformation

KW - visual odometry

UR - http://www.scopus.com/inward/record.url?scp=85181830098&partnerID=8YFLogxK

U2 - 10.1109/CCDC58219.2023.10327350

DO - 10.1109/CCDC58219.2023.10327350

M3 - Conference contribution

AN - SCOPUS:85181830098

T3 - Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023

SP - 2682

EP - 2687

BT - Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 35th Chinese Control and Decision Conference, CCDC 2023

Y2 - 20 May 2023 through 22 May 2023

ER -

Yuan J, Hirota K, Zhang Z, Dai Y. Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. In Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2682-2687. (Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023). doi: 10.1109/CCDC58219.2023.10327350

Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this