# Sunflower Plant Density Estimation 2024: DJI P4 Multispectral Drone Orthophotos and Low-Altitude Images of a Sunflower Field, April to July (Sofia University and SAP Labs Bulgaria)

## Facts

- Provider: Sofia University Faculty of Mathematics and Informatics and SAP Labs Bulgaria
- License: CC-BY-4.0 (https://huggingface.co/datasets/su-fmi/sunflower-density-estimation-2024)
- Size: 9,629 files
- Format: JPEG, TIFF (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/su-fmi/sunflower-density-estimation-2024
- Access: public, readable without an account
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/su-fmi/sunflower-density-estimation-2024
- Page: https://scigantic.com/archive/503e2f4f-1850-595f-acef-dd628faec8b5
- Keywords: Agriculture & Environment, JPEG, TIFF, Hugging Face

## About

Drone surveys of one sunflower field in Bulgaria through the 2024 growing season, collected by Sofia University's Faculty of Mathematics and Informatics and SAP Labs Bulgaria to estimate plant density (stand count) for germination assessment and yield forecasting. Twelve surveys between 15 April and 24 July 2024 used a DJI Phantom 4 Multispectral UAV with blue, green, red, red edge and near-infrared (NIR) cameras. Each survey folder (named DD.MM.YYYY) holds the raw aerial frames, DJI Terra orthophotos (RGB plus one GeoTIFF per band, with and without light uniformity correction), vegetation index maps (NDVI, GNDVI, NDRE, LCI, OSAVI) as float32 GeoTIFFs and false-color renders, and low-altitude images at 2, 5, 10 and 40 m for 32 survey points (one RGB JPEG and five band TIFFs each). All imagery is georeferenced (EPSG:4326, .tfw and .prj files). About 9,600 files and 37 GB, with a validation script. Useful for plant counting, multispectral crop monitoring and early-season density mapping. Metadata states CC BY 4.0 for access and use; credit Sofia University FMI and SAP Labs Bulgaria.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="su-fmi/sunflower-density-estimation-2024", filename="05.07.2024/10m/DJI_0670.JPG", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: JPEG, TIFF

Example file: `05.07.2024/10m/DJI_0670.JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/503e2f4f-1850-595f-acef-dd628faec8b5
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/503e2f4f-1850-595f-acef-dd628faec8b5
- Over MCP: `get_schema_card` with id `503e2f4f-1850-595f-acef-dd628faec8b5` at https://api.scigantic.com/mcp

## Related topics

- [TIFF datasets](https://scigantic.com/topics/tiff)
- [JPEG datasets](https://scigantic.com/topics/jpeg)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
