Wang Nan, Liu Hongbo, Li Yicheng, Zhou Weijun, Ding Mingquan
The Key Laboratory for Quality Improvement of Agricultural Products of Zhejiang Province, College of Advanced Agricultural Sciences, Zhejiang A&F University, Linan, Hangzhou 311300, China.
Institute of Crop Science and Zhejiang Key Laboratory of Crop Germplasm, Zhejiang University, Hangzhou 310058, China.
Plants (Basel). 2023 Sep 20;12(18):3328. doi: 10.3390/plants12183328.
Rapeseed is a significant oil crop, and the size and length of its pods affect its productivity. However, manually counting the number of rapeseed pods and measuring the length, width, and area of the pod takes time and effort, especially when there are hundreds of rapeseed resources to be assessed. This work created two state-of-the-art deep learning-based methods to identify rapeseed pods and related pod attributes, which are then implemented in rapeseed pots to improve the accuracy of the rapeseed yield estimate. One of these methods is YOLO v8, and the other is the two-stage model Mask R-CNN based on the framework Detectron2. The YOLO v8n model and the Mask R-CNN model with a Resnet101 backbone in Detectron2 both achieve precision rates exceeding 90%. The recognition results demonstrated that both models perform well when graphic images of rapeseed pods are segmented. In light of this, we developed a coin-based approach for estimating the size of rapeseed pods and tested it on a test dataset made up of nine different species of and one of L. The correlation coefficients between manual measurement and machine vision measurement of length and width were calculated using statistical methods. The length regression coefficient of both methods was 0.991, and the width regression coefficient was 0.989. In conclusion, for the first time, we utilized deep learning techniques to identify the characteristics of rapeseed pods while concurrently establishing a dataset for rapeseed pods. Our suggested approaches were successful in segmenting and counting rapeseed pods precisely. Our approach offers breeders an effective strategy for digitally analyzing phenotypes and automating the identification and screening process, not only in rapeseed germplasm resources but also in leguminous plants, like soybeans that possess pods.
油菜是一种重要的油料作物，其豆荚的大小和长度会影响产量。然而，人工计数油菜籽豆荚的数量并测量豆荚的长度、宽度和面积既费时又费力，尤其是在需要评估数百份油菜籽资源时。这项工作创建了两种基于深度学习的先进方法来识别油菜籽豆荚及相关豆荚属性，然后将其应用于油菜籽种植中，以提高油菜籽产量估计的准确性。其中一种方法是YOLO v8，另一种是基于Detectron2框架的两阶段模型Mask R-CNN。YOLO v8n模型和Detectron2中带有Resnet101主干的Mask R-CNN模型的精确率均超过90%。识别结果表明，在对油菜籽豆荚的图形图像进行分割时，这两种模型都表现良好。鉴于此，我们开发了一种基于硬币的方法来估计油菜籽豆荚的大小，并在由9种不同品种的 和1种 组成的测试数据集上进行了测试。使用统计方法计算了长度和宽度的人工测量与机器视觉测量之间的相关系数。两种方法的长度回归系数均为0.991，宽度回归系数为0.989。总之，我们首次利用深度学习技术识别油菜籽豆荚的特征，同时建立了油菜籽豆荚数据集。我们提出的方法成功地精确分割和计数了油菜籽豆荚。我们的方法为育种者提供了一种有效的策略，不仅可用于油菜种质资源，还可用于具有豆荚的豆科植物（如大豆）的数字表型分析以及识别和筛选过程的自动化。
