Institute of Artificial Intelligence, University of Georgia, Athens, GA 30602, USA.
Bio-Sensing and Instrumentation Laboratory, College of Engineering, University of Georgia, Athens, GA 30602, USA.
Sensors (Basel). 2022 May 12;22(10):3688. doi: 10.3390/s22103688.
The total boll count from a plant is one of the most important phenotypic traits for cotton breeding and is also an important factor for growers to estimate the final yield. With the recent advances in deep learning, many supervised learning approaches have been implemented to perform phenotypic trait measurement from images for various crops, but few studies have been conducted to count cotton bolls from field images. Supervised learning models require a vast number of annotated images for training, which has become a bottleneck for machine learning model development. The goal of this study is to develop both fully supervised and weakly supervised deep learning models to segment and count cotton bolls from proximal imagery. A total of 290 RGB images of cotton plants from both potted (indoor and outdoor) and in-field settings were taken by consumer-grade cameras and the raw images were divided into 4350 image tiles for further model training and testing. Two supervised models (Mask R-CNN and S-Count) and two weakly supervised approaches (WS-Count and CountSeg) were compared in terms of boll count accuracy and annotation costs. The results revealed that the weakly supervised counting approaches performed well with RMSE values of 1.826 and 1.284 for WS-Count and CountSeg, respectively, whereas the fully supervised models achieve RMSE values of 1.181 and 1.175 for S-Count and Mask R-CNN, respectively, when the number of bolls in an image patch is less than 10. In terms of data annotation costs, the weakly supervised approaches were at least 10 times more cost efficient than the supervised approach for boll counting. In the future, the deep learning models developed in this study can be extended to other plant organs, such as main stalks, nodes, and primary and secondary branches. Both the supervised and weakly supervised deep learning models for boll counting with low-cost RGB images can be used by cotton breeders, physiologists, and growers alike to improve crop breeding and yield estimation.
总铃数是棉花育种中最重要的表型性状之一，也是种植者估计最终产量的重要因素。随着深度学习的最新进展，许多监督学习方法已经被用于从各种作物的图像中进行表型性状测量，但很少有研究致力于从田间图像中计数棉花铃。监督学习模型需要大量标注的图像进行训练，这已成为机器学习模型开发的瓶颈。本研究的目的是开发完全监督和弱监督的深度学习模型，以从近景图像中分割和计数棉花铃。通过消费级相机共拍摄了 290 张盆栽（室内和室外）和田间环境下棉花植株的 RGB 图像，原始图像被分为 4350 个图像块，用于进一步的模型训练和测试。在棉花铃计数精度和标注成本方面，比较了两种监督模型（Mask R-CNN 和 S-Count）和两种弱监督方法（WS-Count 和 CountSeg）。结果表明，弱监督计数方法表现良好，WS-Count 和 CountSeg 的 RMSE 值分别为 1.826 和 1.284，而完全监督模型的 RMSE 值分别为 1.181 和 1.175，当图像块中的棉花铃数量少于 10 个时。在数据标注成本方面，弱监督方法比监督方法在棉花铃计数方面至少节省 10 倍的成本。在未来，本研究开发的深度学习模型可以扩展到其他植物器官，如主茎、节点以及一级和二级分支。棉花育种者、生理学家和种植者都可以使用低成本的 RGB 图像进行监督和弱监督的棉花铃计数深度学习模型，以改进作物育种和产量估计。
