A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework

dc.contributor.authorShiba, Shintaro
dc.contributor.authorAoki, Yoshimitsu
dc.contributor.authorGallego, Guillermo
dc.date.accessioned2023-05-16T14:08:58Z
dc.date.available2023-05-16T14:08:58Z
dc.date.issued2023-01-19
dc.date.updated2023-04-19T23:08:27Z
dc.description.abstractEvent cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state‐of‐the‐art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. A novel, computationally efficient regularizer based on geometric principles to mitigate event collapse is proposed. The experiments show that the proposed regularizer achieves state‐of‐the‐art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, this regularizer is the only effective solution for event collapse without trading off the runtime. It is hoped that this work opens the door for future applications that unlocks the advantages of event cameras. Project page: https://github.com/tub‐rip/event_collapseen
dc.description.sponsorshipDFG, 390523135, EXC 2002: Science of Intelligence (SCIoI)
dc.description.sponsorshipTU Berlin, Open-Access-Mittel – 2023
dc.identifier.eissn2640-4567
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/18883
dc.identifier.urihttps://doi.org/10.14279/depositonce-17688
dc.language.isoen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subject.ddc600 Technik, Medizin, angewandte Wissenschaften::620 Ingenieurwissenschaften::620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
dc.subject.otherautonomous driving
dc.subject.othercontrast maximization
dc.subject.otherevent cameras
dc.subject.otherevent collapse
dc.subject.otherintelligent sensors
dc.subject.otherneuromorphic processing
dc.subject.otherrobotics
dc.titleA Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Frameworken
dc.typeArticle
dc.type.versionpublishedVersion
dcterms.bibliographicCitation.articlenumber2200251
dcterms.bibliographicCitation.doi10.1002/aisy.202200251
dcterms.bibliographicCitation.issue3
dcterms.bibliographicCitation.journaltitleAdvanced Intelligent Systemsen
dcterms.bibliographicCitation.originalpublishernameWiley
dcterms.bibliographicCitation.originalpublisherplaceNew York, NY
dcterms.bibliographicCitation.volume5
dcterms.rightsHolder.referenceCreative-Commons-Lizenz
tub.accessrights.dnbfree
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Technische Informatik und Mikroelektronik::FG Robotic Interactive Perception
tub.publisher.universityorinstitutionTechnische Universität Berlin

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
AISY_AISY202200251.pdf
Size:
2.83 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.86 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections