# OliveTreeCrownsDb: High-Resolution UAV Images of Olive Orchards with 66,950 Tree Crown Bounding Boxes (Sidi Mohamed Ben Abdellah University, AgML Mirror)

## Facts

- Provider: Youness Hnida, Mohamed Adnane Mahraz, Ali Achebour, Ali Yahyaouy, Jamal Riffi and Hamid Tairi (Sidi Mohamed Ben Abdellah University, Fez); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/xym8rd2srf?version=3)
- Size: 15 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/olive_tree_crown_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/xym8rd2srf.3
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/olive_tree_crown_detection
- Page: https://scigantic.com/archive/1912ca59-1543-5dfd-9f6f-771547af85ee
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

Drone (UAV) imagery of olive orchards with every olive tree crown annotated for detection and counting. High-resolution images were divided into 1x1 (original), 3x3, 6x6 and 9x9 grids so crowns appear at several scales; this mirror holds 5,842 images with 66,950 crown boxes. The original Mendeley release also holds a photogrammetric point cloud, a digital elevation model (DEM) and KML spatial data of the study area, which are not part of this mirror. Useful for tree counting, orchard inventory, crown detection at multiple ground resolutions, and precision agriculture in olive groves. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/olive_tree_crown_detection") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Youness Hnida, Mohamed Adnane Mahraz, Ali Achebour, Ali Yahyaouy, Jamal Riffi and Hamid Tairi et al. and the DOI 10.17632/xym8rd2srf.3.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/olive_tree_crown_detection")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00013.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/1912ca59-1543-5dfd-9f6f-771547af85ee
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/1912ca59-1543-5dfd-9f6f-771547af85ee
- Over MCP: `get_schema_card` with id `1912ca59-1543-5dfd-9f6f-771547af85ee` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
