A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework
Event 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. Prio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202200251 |
| _version_ | 1797860197381701632 |
|---|---|
| author | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego |
| author_facet | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego |
| author_sort | Shintaro Shiba |
| collection | DOAJ |
| description | Event 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_collapse |
| first_indexed | 2024-04-09T21:43:00Z |
| format | Article |
| id | doaj.art-0f0e3ff1d90f44c18f7b8eef57c40964 |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-04-09T21:43:00Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-0f0e3ff1d90f44c18f7b8eef57c409642023-03-25T19:40:27ZengWileyAdvanced Intelligent Systems2640-45672023-03-0153n/an/a10.1002/aisy.202200251A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization FrameworkShintaro Shiba0Yoshimitsu Aoki1Guillermo Gallego2Department of Electronics and Electrical Engineering Faculty of Science and Technology Keio University Kanagawa 223‐8522 JapanDepartment of Electronics and Electrical Engineering Faculty of Science and Technology Keio University Kanagawa 223‐8522 JapanDepartment of Electrical Engineering and Computer Science Technische Universität Berlin 10587 Berlin GermanyEvent 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_collapsehttps://doi.org/10.1002/aisy.202200251autonomous drivingcontrast maximizationevent camerasevent collapseintelligent sensorsneuromorphic processing |
| spellingShingle | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework Advanced Intelligent Systems autonomous driving contrast maximization event cameras event collapse intelligent sensors neuromorphic processing |
| title | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| title_full | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| title_fullStr | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| title_full_unstemmed | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| title_short | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| title_sort | fast geometric regularizer to mitigate event collapse in the contrast maximization framework |
| topic | autonomous driving contrast maximization event cameras event collapse intelligent sensors neuromorphic processing |
| url | https://doi.org/10.1002/aisy.202200251 |
| work_keys_str_mv | AT shintaroshiba afastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework AT yoshimitsuaoki afastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework AT guillermogallego afastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework AT shintaroshiba fastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework AT yoshimitsuaoki fastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework AT guillermogallego fastgeometricregularizertomitigateeventcollapseinthecontrastmaximizationframework |