Transformer-Based Spatio-Temporal Association of Apple Fruitlets
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914316526026752 |
|---|---|
| author | Freeman, Harry Kantor, George |
| author_facet | Freeman, Harry Kantor, George |
| contents | In this paper, we present a transformer-based method to spatio-temporally associate apple fruitlets in stereo-images collected on different days and from different camera poses. State-of-the-art association methods in agriculture are dedicated towards matching larger crops using either high-resolution point clouds or temporally stable features, which are both difficult to obtain for smaller fruit in the field. To address these challenges, we propose a transformer-based architecture that encodes the shape and position of each fruitlet, and propagates and refines these features through a series of transformer encoder layers with alternating self and cross-attention. We demonstrate that our method is able to achieve an F1-score of 92.4% on data collected in a commercial apple orchard and outperforms all baselines and ablations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03200 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transformer-Based Spatio-Temporal Association of Apple Fruitlets Freeman, Harry Kantor, George Computer Vision and Pattern Recognition Robotics In this paper, we present a transformer-based method to spatio-temporally associate apple fruitlets in stereo-images collected on different days and from different camera poses. State-of-the-art association methods in agriculture are dedicated towards matching larger crops using either high-resolution point clouds or temporally stable features, which are both difficult to obtain for smaller fruit in the field. To address these challenges, we propose a transformer-based architecture that encodes the shape and position of each fruitlet, and propagates and refines these features through a series of transformer encoder layers with alternating self and cross-attention. We demonstrate that our method is able to achieve an F1-score of 92.4% on data collected in a commercial apple orchard and outperforms all baselines and ablations. |
| title | Transformer-Based Spatio-Temporal Association of Apple Fruitlets |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2503.03200 |