CoMamba: Real-time Cooperative Perception Unlocked with State Space Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912039203504128 |
|---|---|
| author | Li, Jinlong Liu, Xinyu Li, Baolu Xu, Runsheng Li, Jiachen Yu, Hongkai Tu, Zhengzhong |
| author_facet | Li, Jinlong Liu, Xinyu Li, Baolu Xu, Runsheng Li, Jiachen Yu, Hongkai Tu, Zhengzhong |
| contents | Cooperative perception systems play a vital role in enhancing the safety and efficiency of vehicular autonomy. Although recent studies have highlighted the efficacy of vehicle-to-everything (V2X) communication techniques in autonomous driving, a significant challenge persists: how to efficiently integrate multiple high-bandwidth features across an expanding network of connected agents such as vehicles and infrastructure. In this paper, we introduce CoMamba, a novel cooperative 3D detection framework designed to leverage state-space models for real-time onboard vehicle perception. Compared to prior state-of-the-art transformer-based models, CoMamba enjoys being a more scalable 3D model using bidirectional state space models, bypassing the quadratic complexity pain-point of attention mechanisms. Through extensive experimentation on V2X/V2V datasets, CoMamba achieves superior performance compared to existing methods while maintaining real-time processing capabilities. The proposed framework not only enhances object detection accuracy but also significantly reduces processing time, making it a promising solution for next-generation cooperative perception systems in intelligent transportation networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10699 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoMamba: Real-time Cooperative Perception Unlocked with State Space Models Li, Jinlong Liu, Xinyu Li, Baolu Xu, Runsheng Li, Jiachen Yu, Hongkai Tu, Zhengzhong Computer Vision and Pattern Recognition Cooperative perception systems play a vital role in enhancing the safety and efficiency of vehicular autonomy. Although recent studies have highlighted the efficacy of vehicle-to-everything (V2X) communication techniques in autonomous driving, a significant challenge persists: how to efficiently integrate multiple high-bandwidth features across an expanding network of connected agents such as vehicles and infrastructure. In this paper, we introduce CoMamba, a novel cooperative 3D detection framework designed to leverage state-space models for real-time onboard vehicle perception. Compared to prior state-of-the-art transformer-based models, CoMamba enjoys being a more scalable 3D model using bidirectional state space models, bypassing the quadratic complexity pain-point of attention mechanisms. Through extensive experimentation on V2X/V2V datasets, CoMamba achieves superior performance compared to existing methods while maintaining real-time processing capabilities. The proposed framework not only enhances object detection accuracy but also significantly reduces processing time, making it a promising solution for next-generation cooperative perception systems in intelligent transportation networks. |
| title | CoMamba: Real-time Cooperative Perception Unlocked with State Space Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10699 |