This repository describes the Maize Tassel Detection and Counting (MTDC) dataset presented in our work:
Maize tassels detection: a benchmark of the state of the art
Hongwei Zou1, Hao Lu1, Yanan Li2, Liang Liu1, Zhiguo Cao1
1School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China
2School of Computer Science and Engineering, Wuhan Institute of Technology
Plant Methods, 2020
The MTDC dataset extends our previous MTC dataset with bounding box annotations that enable the evaluation of object detection frameworks.
- 361 field images collected from 4 experimental fields across China: Zhengzhou, Henan Province, China, Taian, Shandong Province, China, Gucheng, Hebei Province, China, and Jalaid, Sinkiang Autonomous Region, China.
- Six cultivars of maize plants: Jundan No.20, Nongda, No.108, Wuyue No.3, Zhengdan No.32, Jidan No.20, and Tianlong No.9.
- 13,562 bounding boxes annotations.
- The dataset is captured in the field with realistic visual challenges.
*Each image is associated with a standalone ".mat" annotation file that records the position of bounding boxes. The ".mat" files are created in Matlab.
If you find our dataset useful for your research, please cite:
@article{zou2020maize,
title={Maize tassels detection: a benchmark of the state of the art},
author={Zou, Hongwei and Lu, Hao and Li, Yanan and Liu, Liang and Cao, Zhiguo},
journal={Plant Methods},
volume={16},
number={1},
pages={1--15},
year={2020},
publisher={Springer}
}
The dataset is restricted to academic purposes only. If you are interested in comericial use of the data, please contact Prof. Zhiguo Cao (zgcao@hust.edu.cn).