# VCD Vegetable Crops Dataset for Proximal Sensing: 2,801 Early-Stage Bean, Maize and Leek Images with 17,387 Boxes and Plant Structure Graphs (AgML Mirror)

## Facts

- Provider: Louis Lac; Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/d7kbzjr83k?version=1)
- Size: 9 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/vegetable_crop_early_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/d7kbzjr83k.1
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/vegetable_crop_early_detection
- Page: https://scigantic.com/archive/2f5e71b3-456c-55d3-be76-65b018252b68
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

The Vegetable Crops Dataset for Proximal Sensing (VCD) holds RGB images of bean, maize and leek crops at an early stage of development (2 to 5 weeks after sowing), captured close to the ground for in-row crop detection. Annotations give plant bounding boxes and crop structure annotations as star graphs. This mirror holds 2,801 images with 17,387 boxes across six categories. Useful for early crop plant detection, stem localization for mechanical weeding, and plant structure estimation. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/vegetable_crop_early_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 Louis Lac et al. and the DOI 10.17632/d7kbzjr83k.1.

## Load the data

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

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00007.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/2f5e71b3-456c-55d3-be76-65b018252b68
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/2f5e71b3-456c-55d3-be76-65b018252b68
- Over MCP: `get_schema_card` with id `2f5e71b3-456c-55d3-be76-65b018252b68` 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)
