1Department of Mechanical Engineering, Iowa State University, Ames, IA, USA
2Department of Computer Science, Iowa State University, Ames, IA, USA
3CSIRO Agriculture and Food, St. Lucia, QLD, Australia
4School of Agriculture and Food Sciences, Te University of Queensland, Gatton, QLD 4343, Australia
5Queensland Alliance for Agriculture and Food Innovation (QAAFI), Te University of Queensland, Gatton, QLD, Australia
6Queensland Alliance for Agriculture and Food Innovation (QAAFI), Te University of Queensland, Warwick, QLD, Australia
7Department of Agronomy, Iowa State University, Ames, IA, USA
8International Field Phenomics Research Laboratory, Institute for Sustainable Agro-Ecosystem Services, Graduate School of Agricultural and Life Sciences, Te University of Tokyo, Tokyo, Japan
Received 26 Dec 2018 |
Accepted 30 May 2019 |
Published 27 Jun 2019 |
The yield of cereal crops such as sorghum (Sorghum bicolor L. Moench) depends on the distribution of crop-heads in varying branching arrangements. Therefore, counting the head number per unit area is critical for plant breeders to correlate with the genotypic variation in a specific breeding field. However, measuring such phenotypic traits manually is an extremely labor-intensive process and suffers from low efficiency and human errors. Moreover, the process is almost infeasible for large-scale breeding plantations or experiments. Machine learning-based approaches like deep convolutional neural network (CNN) based object detectors are promising tools for efficient object detection and counting. However, a significant limitation of such deep learning-based approaches is that they typically require a massive amount of hand-labeled images for training, which is still a tedious process. Here, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images. We demonstrate that it is possible to significantly reduce human labeling effort without compromising final model performance ( between human count and machine count is 0.88) by using a semitrained CNN model (i.e., trained with limited labeled data) to perform synthetic annotation. In addition, we also visualize key features that the network learns. This improves trustworthiness by enabling users to better understand and trust the decisions that the trained deep learning model makes.