NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar
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_ | 1866915147452252160 |
|---|---|
| author | Guan, Runwei Liu, Jianan Jia, Liye Zhao, Haocheng Yao, Shanliang Zhu, Xiaohui Man, Ka Lok Lim, Eng Gee Smith, Jeremy Yue, Yutao |
| author_facet | Guan, Runwei Liu, Jianan Jia, Liye Zhao, Haocheng Yao, Shanliang Zhu, Xiaohui Man, Ka Lok Lim, Eng Gee Smith, Jeremy Yue, Yutao |
| contents | Recently, visual grounding and multi-sensors setting have been incorporated into perception system for terrestrial autonomous driving systems and Unmanned Surface Vehicles (USVs), yet the high complexity of modern learning-based visual grounding model using multi-sensors prevents such model to be deployed on USVs in the real-life. To this end, we design a low-power multi-task model named NanoMVG for waterway embodied perception, guiding both camera and 4D millimeter-wave radar to locate specific object(s) through natural language. NanoMVG can perform both box-level and mask-level visual grounding tasks simultaneously. Compared to other visual grounding models, NanoMVG achieves highly competitive performance on the WaterVG dataset, particularly in harsh environments and boasts ultra-low power consumption for long endurance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17207 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar Guan, Runwei Liu, Jianan Jia, Liye Zhao, Haocheng Yao, Shanliang Zhu, Xiaohui Man, Ka Lok Lim, Eng Gee Smith, Jeremy Yue, Yutao Computer Vision and Pattern Recognition Robotics Recently, visual grounding and multi-sensors setting have been incorporated into perception system for terrestrial autonomous driving systems and Unmanned Surface Vehicles (USVs), yet the high complexity of modern learning-based visual grounding model using multi-sensors prevents such model to be deployed on USVs in the real-life. To this end, we design a low-power multi-task model named NanoMVG for waterway embodied perception, guiding both camera and 4D millimeter-wave radar to locate specific object(s) through natural language. NanoMVG can perform both box-level and mask-level visual grounding tasks simultaneously. Compared to other visual grounding models, NanoMVG achieves highly competitive performance on the WaterVG dataset, particularly in harsh environments and boasts ultra-low power consumption for long endurance. |
| title | NanoMVG: USV-Centric Low-Power Multi-Task Visual Grounding based on Prompt-Guided Camera and 4D mmWave Radar |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2408.17207 |