Attention-Enhanced Lightweight Hourglass Network for Human 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_ | 1866909556678852608 |
|---|---|
| author | Kappan, Marsha Mariya Sandoval, Eduardo Benitez Meijering, Erik Cruz, Francisco |
| author_facet | Kappan, Marsha Mariya Sandoval, Eduardo Benitez Meijering, Erik Cruz, Francisco |
| contents | Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have complex architecture. Here we propose a lightweight attention based pose estimation network that utilizes depthwise separable convolution and Convolutional Block Attention Module on an hourglass backbone. The network significantly reduces the computational complexity (floating point operations) and the model size (number of parameters) containing only about 10% of parameters of original eight stack Hourglass network. Experiments were conducted on COCO and MPII datasets using a two stack hourglass backbone. The results showed that our model performs well in comparison to six other lightweight pose estimation models with an average precision of 72.07. The model achieves this performance with only 2.3M parameters and 3.7G FLOPs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06227 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation Kappan, Marsha Mariya Sandoval, Eduardo Benitez Meijering, Erik Cruz, Francisco Computer Vision and Pattern Recognition Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have complex architecture. Here we propose a lightweight attention based pose estimation network that utilizes depthwise separable convolution and Convolutional Block Attention Module on an hourglass backbone. The network significantly reduces the computational complexity (floating point operations) and the model size (number of parameters) containing only about 10% of parameters of original eight stack Hourglass network. Experiments were conducted on COCO and MPII datasets using a two stack hourglass backbone. The results showed that our model performs well in comparison to six other lightweight pose estimation models with an average precision of 72.07. The model achieves this performance with only 2.3M parameters and 3.7G FLOPs. |
| title | Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.06227 |