Synthetic data enables faster annotation and robust segmentation for multi-object grasping in clutter
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910306807054336 |
|---|---|
| author | Lee, Dongmyoung Chen, Wei Rojas, Nicolas |
| author_facet | Lee, Dongmyoung Chen, Wei Rojas, Nicolas |
| contents | Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this work, we propose a synthetic data generation method that minimizes human intervention and makes downstream image segmentation algorithms more robust by combining a generated synthetic dataset with a smaller real-world dataset (hybrid dataset). Annotation experiments show that the proposed synthetic scene generation can diminish labelling time dramatically. RGB image segmentation is trained with hybrid dataset and combined with depth information to produce pixel-to-point correspondence of individual segmented objects. The object to grasp is then determined by the confidence score of the segmentation algorithm. Pick-and-place experiments demonstrate that segmentation trained on our hybrid dataset (98.9%, 70%) outperforms the real dataset and a publicly available dataset by (6.7%, 18.8%) and (2.8%, 10%) in terms of labelling and grasping success rate, respectively. Supplementary material is available at https://sites.google.com/view/synthetic-dataset-generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13405 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Synthetic data enables faster annotation and robust segmentation for multi-object grasping in clutter Lee, Dongmyoung Chen, Wei Rojas, Nicolas Computer Vision and Pattern Recognition Robotics Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this work, we propose a synthetic data generation method that minimizes human intervention and makes downstream image segmentation algorithms more robust by combining a generated synthetic dataset with a smaller real-world dataset (hybrid dataset). Annotation experiments show that the proposed synthetic scene generation can diminish labelling time dramatically. RGB image segmentation is trained with hybrid dataset and combined with depth information to produce pixel-to-point correspondence of individual segmented objects. The object to grasp is then determined by the confidence score of the segmentation algorithm. Pick-and-place experiments demonstrate that segmentation trained on our hybrid dataset (98.9%, 70%) outperforms the real dataset and a publicly available dataset by (6.7%, 18.8%) and (2.8%, 10%) in terms of labelling and grasping success rate, respectively. Supplementary material is available at https://sites.google.com/view/synthetic-dataset-generation. |
| title | Synthetic data enables faster annotation and robust segmentation for multi-object grasping in clutter |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2401.13405 |