Optimized CNNs for Rapid 3D Point Cloud Object Recognition
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_ | 1866910726513229824 |
|---|---|
| author | Lyu, Tianyi Gu, Dian Chen, Peiyuan Jiang, Yaoting Zhang, Zhenhong Pang, Huadong Zhou, Li Dong, Yiping |
| author_facet | Lyu, Tianyi Gu, Dian Chen, Peiyuan Jiang, Yaoting Zhang, Zhenhong Pang, Huadong Zhou, Li Dong, Yiping |
| contents | This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that capitalize on the typical sparsity observed in input data. We explore the trade-off between accuracy and speed across diverse network architectures and advocate for integrating an $\mathcal{L}_1$ penalty on filter activations to augment sparsity within intermediate layers. This research pioneers the proposal of sparse convolutional layers combined with $\mathcal{L}_1$ regularization to effectively handle large-scale 3D data processing. Our method's efficacy is demonstrated on the MVTec 3D-AD object detection benchmark. The Vote3Deep models, with just three layers, outperform the previous state-of-the-art in both laser-only approaches and combined laser-vision methods. Additionally, they maintain competitive processing speeds. This underscores our approach's capability to substantially enhance detection performance while ensuring computational efficiency suitable for real-time applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimized CNNs for Rapid 3D Point Cloud Object Recognition Lyu, Tianyi Gu, Dian Chen, Peiyuan Jiang, Yaoting Zhang, Zhenhong Pang, Huadong Zhou, Li Dong, Yiping Computer Vision and Pattern Recognition Machine Learning This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that capitalize on the typical sparsity observed in input data. We explore the trade-off between accuracy and speed across diverse network architectures and advocate for integrating an $\mathcal{L}_1$ penalty on filter activations to augment sparsity within intermediate layers. This research pioneers the proposal of sparse convolutional layers combined with $\mathcal{L}_1$ regularization to effectively handle large-scale 3D data processing. Our method's efficacy is demonstrated on the MVTec 3D-AD object detection benchmark. The Vote3Deep models, with just three layers, outperform the previous state-of-the-art in both laser-only approaches and combined laser-vision methods. Additionally, they maintain competitive processing speeds. This underscores our approach's capability to substantially enhance detection performance while ensuring computational efficiency suitable for real-time applications. |
| title | Optimized CNNs for Rapid 3D Point Cloud Object Recognition |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2412.02855 |