SelvaBox: A high-resolution dataset for tropical tree crown detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915972692049920 |
|---|---|
| author | Baudchon, Hugo Ouaknine, Arthur Weiss, Martin Teng, Mélisande Walla, Thomas R. Caron-Guay, Antoine Pal, Christopher Laliberté, Etienne |
| author_facet | Baudchon, Hugo Ouaknine, Arthur Weiss, Martin Teng, Mélisande Walla, Thomas R. Caron-Guay, Antoine Pal, Christopher Laliberté, Etienne |
| contents | Detecting individual tree crowns in tropical forests is essential to study these complex and crucial ecosystems impacted by human interventions and climate change. However, tropical crowns vary widely in size, structure, and pattern and are largely overlapping and intertwined, requiring advanced remote sensing methods applied to high-resolution imagery. Despite growing interest in tropical tree crown detection, annotated datasets remain scarce, hindering robust model development. We introduce SelvaBox, the largest open-access dataset for tropical tree crown detection in high-resolution drone imagery. It spans three countries and contains more than 83,000 manually labeled crowns - an order of magnitude larger than all previous tropical forest datasets combined. Extensive benchmarks on SelvaBox reveal two key findings: (1) higher-resolution inputs consistently boost detection accuracy; and (2) models trained exclusively on SelvaBox achieve competitive zero-shot detection performance on unseen tropical tree crown datasets, matching or exceeding competing methods. Furthermore, jointly training on SelvaBox and three other datasets at resolutions from 3 to 10 cm per pixel within a unified multi-resolution pipeline yields a detector ranking first or second across all evaluated datasets. Our dataset, code, and pre-trained weights are made public. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SelvaBox: A high-resolution dataset for tropical tree crown detection Baudchon, Hugo Ouaknine, Arthur Weiss, Martin Teng, Mélisande Walla, Thomas R. Caron-Guay, Antoine Pal, Christopher Laliberté, Etienne Computer Vision and Pattern Recognition I.2.10; I.4.8; I.5.4 Detecting individual tree crowns in tropical forests is essential to study these complex and crucial ecosystems impacted by human interventions and climate change. However, tropical crowns vary widely in size, structure, and pattern and are largely overlapping and intertwined, requiring advanced remote sensing methods applied to high-resolution imagery. Despite growing interest in tropical tree crown detection, annotated datasets remain scarce, hindering robust model development. We introduce SelvaBox, the largest open-access dataset for tropical tree crown detection in high-resolution drone imagery. It spans three countries and contains more than 83,000 manually labeled crowns - an order of magnitude larger than all previous tropical forest datasets combined. Extensive benchmarks on SelvaBox reveal two key findings: (1) higher-resolution inputs consistently boost detection accuracy; and (2) models trained exclusively on SelvaBox achieve competitive zero-shot detection performance on unseen tropical tree crown datasets, matching or exceeding competing methods. Furthermore, jointly training on SelvaBox and three other datasets at resolutions from 3 to 10 cm per pixel within a unified multi-resolution pipeline yields a detector ranking first or second across all evaluated datasets. Our dataset, code, and pre-trained weights are made public. |
| title | SelvaBox: A high-resolution dataset for tropical tree crown detection |
| topic | Computer Vision and Pattern Recognition I.2.10; I.4.8; I.5.4 |
| url | https://arxiv.org/abs/2507.00170 |