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

Provider
Weijia Li; Hugging Face mirror by Project-AgML
License
CC-BY-4.0 (source)
Size
5 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/Project-AgML/litchi_fruit_detection)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.19364014
Category
Agriculture & Environment
Source
https://huggingface.co/datasets/Project-AgML/litchi_fruit_detection

About this dataset

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.

How to load this dataset in Python

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

Data structure

File types in sampled files: Parquet

Files

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

Analyze this dataset without downloading it

On Scigantic, Litchi-UAV: Drone Images of Litchi Fruit in Dense Canopies with 39,415 Bounding Boxes, Guangzhou, China (AgML Mirror) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Agriculture & Environment datasets