Fast Event-based Double Integral for Real-time Robotics

Shijie Lin; Yingqiang Zhang; Dongyue Huang; Bin Zhou; Xiaowei Luo; Jia Pan

doi:10.1109/ICRA48891.2023.10160727

Fast Event-based Double Integral for Real-time Robotics

Shijie Lin
, Yingqiang Zhang
, Dongyue Huang
, Bin Zhou
, Xiaowei Luo
, Jia Pan^*

^*Corresponding author for this work

Department of Architecture and Civil Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

11 Citations (Scopus)

Abstract

Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring prob-lem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, vi-sual tag detection, and feature matching. © 2023 IEEE.

Original language	English
Title of host publication	2023 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	IEEE
Pages	796-803
ISBN (Electronic)	979-8-3503-2365-8
DOIs	https://doi.org/10.1109/ICRA48891.2023.10160727
Publication status	Published - 2023
Event	40th IEEE International Conference on Robotics and Automation (ICRA 2023) - ExCeL London, London, United Kingdom Duration: 29 May 2023 → 2 Jun 2023 https://www.icra2023.org/

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2023-May
ISSN (Print)	1050-4729

Conference

Conference	40th IEEE International Conference on Robotics and Automation (ICRA 2023)
Abbreviated title	ICRA2023
Place	United Kingdom
City	London
Period	29/05/23 → 2/06/23
Internet address	https://www.icra2023.org/

Access Output

10.1109/ICRA48891.2023.10160727

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{1b7d00325ac24dd9829302cd28231bf6,

title = "Fast Event-based Double Integral for Real-time Robotics",

abstract = "Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring prob-lem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, vi-sual tag detection, and feature matching. {\textcopyright} 2023 IEEE.",

author = "Shijie Lin and Yingqiang Zhang and Dongyue Huang and Bin Zhou and Xiaowei Luo and Jia Pan",

year = "2023",

doi = "10.1109/ICRA48891.2023.10160727",

language = "English",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "IEEE",

pages = "796--803",

booktitle = "2023 IEEE International Conference on Robotics and Automation (ICRA)",

address = "United States",

note = "40th IEEE International Conference on Robotics and Automation (ICRA 2023) , ICRA2023 ; Conference date: 29-05-2023 Through 02-06-2023",

url = "https://www.icra2023.org/",

}

Lin, S, Zhang, Y, Huang, D, Zhou, B, Luo, X & Pan, J 2023, Fast Event-based Double Integral for Real-time Robotics. in 2023 IEEE International Conference on Robotics and Automation (ICRA). Proceedings - IEEE International Conference on Robotics and Automation, vol. 2023-May, IEEE, pp. 796-803, 40th IEEE International Conference on Robotics and Automation (ICRA 2023) , London, United Kingdom, 29/05/23. https://doi.org/10.1109/ICRA48891.2023.10160727

Fast Event-based Double Integral for Real-time Robotics. / Lin, Shijie; Zhang, Yingqiang; Huang, Dongyue et al.
2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023. p. 796-803 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2023-May).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Fast Event-based Double Integral for Real-time Robotics

AU - Lin, Shijie

AU - Zhang, Yingqiang

AU - Huang, Dongyue

AU - Zhou, Bin

AU - Luo, Xiaowei

AU - Pan, Jia

PY - 2023

Y1 - 2023

N2 - Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring prob-lem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, vi-sual tag detection, and feature matching. © 2023 IEEE.

AB - Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring prob-lem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, vi-sual tag detection, and feature matching. © 2023 IEEE.

UR - https://www.scopus.com/pages/publications/85161129398

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85161129398&origin=recordpage

U2 - 10.1109/ICRA48891.2023.10160727

DO - 10.1109/ICRA48891.2023.10160727

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 796

EP - 803

BT - 2023 IEEE International Conference on Robotics and Automation (ICRA)

PB - IEEE

T2 - 40th IEEE International Conference on Robotics and Automation (ICRA 2023)

Y2 - 29 May 2023 through 2 June 2023

ER -

Fast Event-based Double Integral for Real-time Robotics

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this