WheatPheno

WheatPheno

DataSet

The WheatPheno dataset includes images of different wheat varieties, nitrogen levels, and five phenology stages. It is a large-scale DL dataset constructed for crop phenology classification. Images were processed by annotation, augmentation, and partition. First, the raw images were annotated into five stages based on the Biologische Bundesanstalt, Bundessortenamt und Chemische Industrie (BBCH) scale (Meier et al., 2009). The five stages included the jointing to the booting stage (J-B), heading stage (H), flowering stage (F), grain filling stage (G-F), and mature stage (M).

Study Area and Data Collection

The study area is located at the Baima Experimental Station (119°18′71″E, 31°62′00″N) of Nanjing Agricultural University in China. A total of 240 RGB cameras (Reolink K2, Reolink Digital Technology Co., Ltd, China) were installed to continuously monitor the winter wheat phenophase. Each camera was mounted on an iron pole at 2 m above the ground, and the shooting angle was 45° from the horizon. Each camera automatically monitored four plots' areas every hour from March 6 to May 25, 2021, and March 1 to May 26, 2022. All camera images were sent to a server in real time through a wireless transmission module.

imgStudyArea

WheatPheno Dataset Overview


Summary Statistics
  • 320K Quality Images
  • 5 Phenology Stages
  • 2 Years
  • 160/210 Wheat Varieties
  • 2/3 Nitrogenous levels
  • 2/3 Repetitions
Phenology Stage
Variety Distribution

Variety Overview

Camera ID
Variety
Springing characteristics
Year
No Data
Total 0

Example

Citation

If you find this work useful for your research, please consider citing our paper:

@article{zhang2024phenonet,
  title={PhenoNet: A two-stage lightweight deep learning framework for real-time wheat phenophase classification},
  author={Zhang, Ruinan and Jin, Shichao and Zhang, Yuanhao and Zang, Jingrong and Wang, Yu and Li, Qing and Sun, Zhuangzhuang and Wang, Xiao and Zhou, Qin and Cai, Jian and others},
  journal={ISPRS Journal of Photogrammetry and Remote Sensing},
  volume={208},
  pages={136--157},
  year={2024},
  publisher={Elsevier}
}