FOE-based regularization for optical flow estimation from an in-vehicle event camera

Jun Nagata, Yusuke Sekikawa, Kosuke Hara, Yoshimitsu Aoki

研究成果: Conference contribution

抄録

Optical flow estimation in onboard cameras is an important task in automatic driving and advanced driver- assistance systems. However, there is a problem that calculation is mistakable with high contrast and high speed. Event cameras have great features such as high dynamic range and low latency that can overcome these problems. Event cameras report only the change in the logarithmic intensity per pixel rather than the absolute brightness. There is a method of estimating the optical ow simultaneously with the luminance restoration from the event data. The regularization using the L1 norm of differentiation is insufficient for spatially sparse event data. Therefore, we propose to use the focus of expansion (FOE) for regularization of optical ow estimation in event camera. The FOE is defined as the intersection of the translation vector of the camera and the image plane. The optical ow becomes radial from the FOE excluding the rotational component. Using the property, the optical ow can be regularized in the correct direction in the optimization process. We demonstrated that the optical ow was improved by introducing our regularization using the public dataset.

元の言語English
ホスト出版物のタイトルInternational Workshop on Advanced Image Technology, IWAIT 2019
編集者Qian Kemao, Yung-Lyul Lee, Kazuya Hayase, Phooi Yee Lau, Wen-Nung Lie, Lu Yu, Sanun Srisuk
出版者SPIE
ISBN(電子版)9781510627734
DOI
出版物ステータスPublished - 2019 1 1
イベントInternational Workshop on Advanced Image Technology 2019, IWAIT 2019 - Singapore, Singapore
継続期間: 2019 1 62019 1 9

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
11049
ISSN(印刷物)0277-786X
ISSN(電子版)1996-756X

Conference

ConferenceInternational Workshop on Advanced Image Technology 2019, IWAIT 2019
Singapore
Singapore
期間19/1/619/1/9

Fingerprint

Optical flows
Optical Flow
Regularization
vehicles
Camera
Cameras
cameras
expansion
Luminance
Advanced driver assistance systems
High Dynamic Range
Driver Assistance
L1-norm
Brightness
Process Optimization
luminance
Restoration
norms
restoration
intersections

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

これを引用

Nagata, J., Sekikawa, Y., Hara, K., & Aoki, Y. (2019). FOE-based regularization for optical flow estimation from an in-vehicle event camera. : Q. Kemao, Y-L. Lee, K. Hayase, P. Y. Lau, W-N. Lie, L. Yu, & S. Srisuk (版), International Workshop on Advanced Image Technology, IWAIT 2019 [110492V] (Proceedings of SPIE - The International Society for Optical Engineering; 巻数 11049). SPIE. https://doi.org/10.1117/12.2521520

FOE-based regularization for optical flow estimation from an in-vehicle event camera. / Nagata, Jun; Sekikawa, Yusuke; Hara, Kosuke; Aoki, Yoshimitsu.

International Workshop on Advanced Image Technology, IWAIT 2019. 版 / Qian Kemao; Yung-Lyul Lee; Kazuya Hayase; Phooi Yee Lau; Wen-Nung Lie; Lu Yu; Sanun Srisuk. SPIE, 2019. 110492V (Proceedings of SPIE - The International Society for Optical Engineering; 巻 11049).

研究成果: Conference contribution

Nagata, J, Sekikawa, Y, Hara, K & Aoki, Y 2019, FOE-based regularization for optical flow estimation from an in-vehicle event camera. : Q Kemao, Y-L Lee, K Hayase, PY Lau, W-N Lie, L Yu & S Srisuk (版), International Workshop on Advanced Image Technology, IWAIT 2019., 110492V, Proceedings of SPIE - The International Society for Optical Engineering, 巻. 11049, SPIE, International Workshop on Advanced Image Technology 2019, IWAIT 2019, Singapore, Singapore, 19/1/6. https://doi.org/10.1117/12.2521520
Nagata J, Sekikawa Y, Hara K, Aoki Y. FOE-based regularization for optical flow estimation from an in-vehicle event camera. : Kemao Q, Lee Y-L, Hayase K, Lau PY, Lie W-N, Yu L, Srisuk S, 編集者, International Workshop on Advanced Image Technology, IWAIT 2019. SPIE. 2019. 110492V. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2521520
Nagata, Jun ; Sekikawa, Yusuke ; Hara, Kosuke ; Aoki, Yoshimitsu. / FOE-based regularization for optical flow estimation from an in-vehicle event camera. International Workshop on Advanced Image Technology, IWAIT 2019. 編集者 / Qian Kemao ; Yung-Lyul Lee ; Kazuya Hayase ; Phooi Yee Lau ; Wen-Nung Lie ; Lu Yu ; Sanun Srisuk. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{78700c743e094fc586e14a92d2793843,
title = "FOE-based regularization for optical flow estimation from an in-vehicle event camera",
abstract = "Optical flow estimation in onboard cameras is an important task in automatic driving and advanced driver- assistance systems. However, there is a problem that calculation is mistakable with high contrast and high speed. Event cameras have great features such as high dynamic range and low latency that can overcome these problems. Event cameras report only the change in the logarithmic intensity per pixel rather than the absolute brightness. There is a method of estimating the optical ow simultaneously with the luminance restoration from the event data. The regularization using the L1 norm of differentiation is insufficient for spatially sparse event data. Therefore, we propose to use the focus of expansion (FOE) for regularization of optical ow estimation in event camera. The FOE is defined as the intersection of the translation vector of the camera and the image plane. The optical ow becomes radial from the FOE excluding the rotational component. Using the property, the optical ow can be regularized in the correct direction in the optimization process. We demonstrated that the optical ow was improved by introducing our regularization using the public dataset.",
keywords = "Event camera, Focus of expansion, Optical ow",
author = "Jun Nagata and Yusuke Sekikawa and Kosuke Hara and Yoshimitsu Aoki",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2521520",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Qian Kemao and Yung-Lyul Lee and Kazuya Hayase and Lau, {Phooi Yee} and Wen-Nung Lie and Lu Yu and Sanun Srisuk",
booktitle = "International Workshop on Advanced Image Technology, IWAIT 2019",

}

TY - GEN

T1 - FOE-based regularization for optical flow estimation from an in-vehicle event camera

AU - Nagata, Jun

AU - Sekikawa, Yusuke

AU - Hara, Kosuke

AU - Aoki, Yoshimitsu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Optical flow estimation in onboard cameras is an important task in automatic driving and advanced driver- assistance systems. However, there is a problem that calculation is mistakable with high contrast and high speed. Event cameras have great features such as high dynamic range and low latency that can overcome these problems. Event cameras report only the change in the logarithmic intensity per pixel rather than the absolute brightness. There is a method of estimating the optical ow simultaneously with the luminance restoration from the event data. The regularization using the L1 norm of differentiation is insufficient for spatially sparse event data. Therefore, we propose to use the focus of expansion (FOE) for regularization of optical ow estimation in event camera. The FOE is defined as the intersection of the translation vector of the camera and the image plane. The optical ow becomes radial from the FOE excluding the rotational component. Using the property, the optical ow can be regularized in the correct direction in the optimization process. We demonstrated that the optical ow was improved by introducing our regularization using the public dataset.

AB - Optical flow estimation in onboard cameras is an important task in automatic driving and advanced driver- assistance systems. However, there is a problem that calculation is mistakable with high contrast and high speed. Event cameras have great features such as high dynamic range and low latency that can overcome these problems. Event cameras report only the change in the logarithmic intensity per pixel rather than the absolute brightness. There is a method of estimating the optical ow simultaneously with the luminance restoration from the event data. The regularization using the L1 norm of differentiation is insufficient for spatially sparse event data. Therefore, we propose to use the focus of expansion (FOE) for regularization of optical ow estimation in event camera. The FOE is defined as the intersection of the translation vector of the camera and the image plane. The optical ow becomes radial from the FOE excluding the rotational component. Using the property, the optical ow can be regularized in the correct direction in the optimization process. We demonstrated that the optical ow was improved by introducing our regularization using the public dataset.

KW - Event camera

KW - Focus of expansion

KW - Optical ow

UR - http://www.scopus.com/inward/record.url?scp=85063898065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063898065&partnerID=8YFLogxK

U2 - 10.1117/12.2521520

DO - 10.1117/12.2521520

M3 - Conference contribution

AN - SCOPUS:85063898065

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Workshop on Advanced Image Technology, IWAIT 2019

A2 - Kemao, Qian

A2 - Lee, Yung-Lyul

A2 - Hayase, Kazuya

A2 - Lau, Phooi Yee

A2 - Lie, Wen-Nung

A2 - Yu, Lu

A2 - Srisuk, Sanun

PB - SPIE

ER -