Zhao Jiangsan, Kaga Akito, Yamada Tetsuya, Komatsu Kunihiko, Hirata Kaori, Kikuchi Akio, Hirafuji Masayuki, Ninomiya Seishi, Guo Wei
Graduate School of Agriculture and Life Sciences, The University of Tokyo, Tokyo, Japan.
Institute of Crop Sciences, National Agriculture and Food Research Organization, Tsukuba, Ibaraki, Japan.
Plant Phenomics. 2023;5:0026. doi: 10.34133/plantphenomics.0026. Epub 2023 Mar 15.
Developing automated soybean seed counting tools will help automate yield prediction before harvesting and improving selection efficiency in breeding programs. An integrated approach for counting and localization is ideal for subsequent analysis. The traditional method of object counting is labor-intensive and error-prone and has low localization accuracy. To quantify soybean seed directly rather than sequentially, we propose a P2PNet-Soy method. Several strategies were considered to adjust the architecture and subsequent postprocessing to maximize model performance in seed counting and localization. First, unsupervised clustering was applied to merge closely located overcounts. Second, low-level features were included with high-level features to provide more information. Third, atrous convolution with different kernel sizes was applied to low- and high-level features to extract scale-invariant features to factor in soybean size variation. Fourth, channel and spatial attention effectively separated the foreground and background for easier soybean seed counting and localization. At last, the input image was added to these extracted features to improve model performance. Using 24 soybean accessions as experimental materials, we trained the model on field images of individual soybean plants obtained from one side and tested them on images obtained from the opposite side, with all the above strategies. The superiority of the proposed P2PNet-Soy in soybean seed counting and localization over the original P2PNet was confirmed by a reduction in the value of the mean absolute error, from 105.55 to 12.94. Furthermore, the trained model worked effectively on images obtained directly from the field without background interference.
开发自动化大豆种子计数工具将有助于在收获前自动进行产量预测，并提高育种计划中的选择效率。一种用于计数和定位的集成方法对于后续分析是理想的。传统的目标计数方法劳动强度大、容易出错且定位精度低。为了直接而非顺序地量化大豆种子，我们提出了一种P2PNet-Soy方法。我们考虑了几种策略来调整架构和后续的后处理，以在种子计数和定位方面最大化模型性能。首先，应用无监督聚类来合并位置相近的重复计数。其次，将低级特征与高级特征相结合以提供更多信息。第三，将不同内核大小的空洞卷积应用于低级和高级特征，以提取尺度不变特征，从而考虑大豆大小的变化。第四，通道和空间注意力有效地分离了前景和背景，以便更轻松地进行大豆种子计数和定位。最后，将输入图像添加到这些提取的特征中以提高模型性能。我们以24个大豆种质为实验材料，使用上述所有策略，在从一侧获得的单个大豆植株的田间图像上训练模型，并在从另一侧获得的图像上对其进行测试。通过将平均绝对误差值从105.55降低到12.94，证实了所提出的P2PNet-Soy在大豆种子计数和定位方面优于原始的P2PNet。此外，训练后的模型在直接从田间获得的无背景干扰的图像上有效工作。
