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^*

^*此作品的通讯作者

自动化学院

School of Automation

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

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.

源语言	英语
主期刊名	Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023
出版商	Institute of Electrical and Electronics Engineers Inc.
页	2682-2687
页数	6
ISBN（电子版）	9798350334722
DOI	https://doi.org/10.1109/CCDC58219.2023.10327350
出版状态	已出版 - 2023
活动	35th Chinese Control and Decision Conference, CCDC 2023 - Yichang, 中国期限: 20 5月 2023 → 22 5月 2023

出版系列

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

会议

会议	35th Chinese Control and Decision Conference, CCDC 2023
国家/地区	中国
市	Yichang
时期	20/05/23 → 22/05/23

访问文件

10.1109/CCDC58219.2023.10327350

其它文件与链接

链接到 Scopus 的出版物

引用此

Yuan, J., Hirota, K., Zhang, Z., & Dai, Y. (2023). Monocular Non-linear Photometric Transformation Visual Odometry Based on Direct Sparse Odometry. 在 Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023 (页码 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 等. / 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. 页码 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. 在 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., 页码 2682-2687, 35th Chinese Control and Decision Conference, CCDC 2023, Yichang, 中国, 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 等.
Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. 页码 2682-2687 (Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

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. 在 Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. 页码 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

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此