Frequency-aware Event Cloud Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912172476465152 |
|---|---|
| author | Ren, Hongwei Ma, Fei Lin, Xiaopeng Fang, Yuetong Huang, Hongxiang Huang, Yulong Zhou, Yue Fu, Haotian Yang, Ziyi Yu, Fei Richard Cheng, Bojun |
| author_facet | Ren, Hongwei Ma, Fei Lin, Xiaopeng Fang, Yuetong Huang, Hongxiang Huang, Yulong Zhou, Yue Fu, Haotian Yang, Ziyi Yu, Fei Richard Cheng, Bojun |
| contents | Event cameras are biologically inspired sensors that emit events asynchronously with remarkable temporal resolution, garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformation, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates promise in addressing the mentioned weaknesses, but it ignores the polarity information, and its models have limited proficiency in abstracting long-term events' features. In this paper, we propose a frequency-aware network named FECNet that leverages Event Cloud representations. FECNet fully utilizes 2S-1T-1P Event Cloud by innovating the event-based Group and Sampling module. To accommodate the long sequence events from Event Cloud, FECNet embraces feature extraction in the frequency domain via the Fourier transform. This approach substantially extinguishes the explosion of Multiply Accumulate Operations (MACs) while effectively abstracting spatial-temporal features. We conducted extensive experiments on event-based object classification, action recognition, and human pose estimation tasks, and the results substantiate the effectiveness and efficiency of FECNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20803 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Frequency-aware Event Cloud Network Ren, Hongwei Ma, Fei Lin, Xiaopeng Fang, Yuetong Huang, Hongxiang Huang, Yulong Zhou, Yue Fu, Haotian Yang, Ziyi Yu, Fei Richard Cheng, Bojun Computer Vision and Pattern Recognition Event cameras are biologically inspired sensors that emit events asynchronously with remarkable temporal resolution, garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformation, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates promise in addressing the mentioned weaknesses, but it ignores the polarity information, and its models have limited proficiency in abstracting long-term events' features. In this paper, we propose a frequency-aware network named FECNet that leverages Event Cloud representations. FECNet fully utilizes 2S-1T-1P Event Cloud by innovating the event-based Group and Sampling module. To accommodate the long sequence events from Event Cloud, FECNet embraces feature extraction in the frequency domain via the Fourier transform. This approach substantially extinguishes the explosion of Multiply Accumulate Operations (MACs) while effectively abstracting spatial-temporal features. We conducted extensive experiments on event-based object classification, action recognition, and human pose estimation tasks, and the results substantiate the effectiveness and efficiency of FECNet. |
| title | Frequency-aware Event Cloud Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.20803 |