DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation
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_ | 1866913329224613888 |
|---|---|
| author | Di Bella, Leandro Lyu, Yangxintong Munteanu, Adrian |
| author_facet | Di Bella, Leandro Lyu, Yangxintong Munteanu, Adrian |
| contents | This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter. By integrating a Bi-directional Kalman filter strategy utilizing forward and backward time-series processing, combined with a learnable motion model to represent complex motion patterns, our method significantly improves pose accuracy and robustness across various conditions, particularly for occluded or distant vehicles. Experimental validation on the KITTI dataset confirms that DeepKalPose outperforms existing methods in both pose accuracy and temporal consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation Di Bella, Leandro Lyu, Yangxintong Munteanu, Adrian Computer Vision and Pattern Recognition Artificial Intelligence Robotics This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter. By integrating a Bi-directional Kalman filter strategy utilizing forward and backward time-series processing, combined with a learnable motion model to represent complex motion patterns, our method significantly improves pose accuracy and robustness across various conditions, particularly for occluded or distant vehicles. Experimental validation on the KITTI dataset confirms that DeepKalPose outperforms existing methods in both pose accuracy and temporal consistency. |
| title | DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2404.16558 |