Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909174299885568 |
|---|---|
| author | Retsinas, George Efthymiou, Niki Maragos, Petros |
| author_facet | Retsinas, George Efthymiou, Niki Maragos, Petros |
| contents | Modern agricultural applications rely more and more on deep learning solutions. However, training well-performing deep networks requires a large amount of annotated data that may not be available and in the case of 3D annotation may not even be feasible for human annotators. In this work, we develop a deep learning approach to segment mushrooms and estimate their pose on 3D data, in the form of point clouds acquired by depth sensors. To circumvent the annotation problem, we create a synthetic dataset of mushroom scenes, where we are fully aware of 3D information, such as the pose of each mushroom. The proposed network has a fully convolutional backbone, that parses sparse 3D data, and predicts pose information that implicitly defines both instance segmentation and pose estimation task. We have validated the effectiveness of the proposed implicit-based approach for a synthetic test set, as well as provided qualitative results for a small set of real acquired point clouds with depth sensors. Code is publicly available at https://github.com/georgeretsi/mushroom-pose. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12144 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding Retsinas, George Efthymiou, Niki Maragos, Petros Computer Vision and Pattern Recognition Modern agricultural applications rely more and more on deep learning solutions. However, training well-performing deep networks requires a large amount of annotated data that may not be available and in the case of 3D annotation may not even be feasible for human annotators. In this work, we develop a deep learning approach to segment mushrooms and estimate their pose on 3D data, in the form of point clouds acquired by depth sensors. To circumvent the annotation problem, we create a synthetic dataset of mushroom scenes, where we are fully aware of 3D information, such as the pose of each mushroom. The proposed network has a fully convolutional backbone, that parses sparse 3D data, and predicts pose information that implicitly defines both instance segmentation and pose estimation task. We have validated the effectiveness of the proposed implicit-based approach for a synthetic test set, as well as provided qualitative results for a small set of real acquired point clouds with depth sensors. Code is publicly available at https://github.com/georgeretsi/mushroom-pose. |
| title | Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.12144 |