# Litchi-UAV: Drone Images of Litchi Fruit in Dense Canopies with 39,415 Bounding Boxes, Guangzhou, China (AgML Mirror)

## Facts

- Provider: Weijia Li; Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://zenodo.org/records/19364014)
- Size: 5 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/litchi_fruit_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.19364014
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/litchi_fruit_detection
- Page: https://scigantic.com/archive/20de2381-6adc-5b5b-87f5-ca983e23b73c
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

UAV images of litchi (lychee) fruit in an orchard in Conghua District, Guangzhou, China, captured on 14 May 2024 (overcast) and 2 July 2024 (sunny) with a DJI Phantom 4 using vertical and oblique shots at 4096 x 2160 pixels. The 432 original photos were cut into 1024 x 1024 patches with a sliding window and augmented with Gaussian and salt-and-pepper noise and brightness changes, giving 1,756 training, 86 validation and 44 test images with YOLO bounding boxes for litchi fruit and fruit, branch and leaf occlusion. This mirror holds 1,880 images with 39,415 boxes. Released with the Edge-YOLOv11 paper on lightweight fruit detection for edge devices; useful for fruit counting and yield estimation from drones. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/litchi_fruit_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 Weijia Li et al. and the DOI 10.5281/zenodo.19364014.

## Load the data

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

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00003.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/20de2381-6adc-5b5b-87f5-ca983e23b73c
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/20de2381-6adc-5b5b-87f5-ca983e23b73c
- Over MCP: `get_schema_card` with id `20de2381-6adc-5b5b-87f5-ca983e23b73c` 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)
