# Drone Images of Rice Panicles with Bounding Boxes: 2,193 4K Frames and 5,701 Augmented Images, Gazipur, Bangladesh (East West University, AgML Mirror)

## Facts

- Provider: Mohammad Rifat Ahmmad Rashid, Md. Shafayat Hossain, Md Fahim, Md. Shajibul Islam, Tahzib E-Alindo and Rizvee Hassan Prito (East West University, Bangladesh); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/ndb6t28xbk?version=4)
- Size: 5 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/rice_panicle_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/ndb6t28xbk.4
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/rice_panicle_detection
- Page: https://scigantic.com/archive/6ce78382-be40-5868-9e27-357ae1120ec7
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

Drone-based rice panicle detection images from rice fields in Gazipur, Bangladesh. Frames were extracted from 4K drone video and every panicle (the grain-bearing head of the rice plant) was annotated with a semi-automatic process combining manual and deep-learning labeling. The raw configuration holds 2,193 images with 40,672 boxes; the augmented configuration holds 5,701 images with 122,222 boxes. Useful for panicle counting, rice yield estimation, crop monitoring and heading-stage detection from UAV imagery. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/rice_panicle_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 Mohammad Rifat Ahmmad Rashid, Md. Shafayat Hossain, Md Fahim, Md. Shajibul Islam, Tahzib E-Alindo and Rizvee Hassan Prito et al. and the DOI 10.17632/ndb6t28xbk.4.

## Load the data

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

## Data structure

File types in sampled files: Parquet

Example file: `augmented/train-00000-of-00002.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/6ce78382-be40-5868-9e27-357ae1120ec7
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/6ce78382-be40-5868-9e27-357ae1120ec7
- Over MCP: `get_schema_card` with id `6ce78382-be40-5868-9e27-357ae1120ec7` 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)
