Background High throughput non-destructive phenotyping is emerging as a significant approach for phenotyping germplasm and breeding populations for the identification of superior donors, elite lines, and QTLs. Detection and counting of spikes, the grain bearing organs of wheat, is critical for phenomics of a large set of germplasm and breeding lines in controlled and field conditions. It is also required for precision agriculture where the application of nitrogen, water, and other inputs at this critical stage is necessary. Further, counting of spikes is an important measure to determine yield. Digital image analysis and machine learning techniques play an essential role in non-destructive plant phenotyping analysis. Results In this study, an approach based on computer vision, particularly object detection, to recognize and count the number of spikes of the wheat plant from the digital images is proposed. For spike identification, a novel deep-learning network, SpikeSegNet, has been developed by combining two proposed feature networks: Local Patch extraction Network (LPNet) and Global Mask refinement Network (GMRNet). In LPNet, the contextual and spatial features are learned at the local patch level. The output of LPNet is a segmented mask image, which is further refined at the global level using GMRNet. Visual (RGB) images of 200 wheat plants were captured using LemnaTec imaging system installed at Nanaji Deshmukh Plant Phenomics Centre, ICAR-IARI, New Delhi. The precision, accuracy, and robustness (F1 score) of the proposed approach for spike segmentation are found to be 99.93%, 99.91%, and 99.91%, respectively. For counting the number of spikes, "analyse particles"-function of imageJ was applied on the output image of the proposed SpikeSegNet model. For spike counting, the average precision, accuracy, and robustness are 99%, 95%, and 97%, respectively. SpikeSegNet approach is tested for robustness with illuminated image dataset, and no significant difference is observed in the segmentation performance. Conclusion In this study, a new approach called as SpikeSegNet has been proposed based on combined digital image analysis and deep learning techniques. A dedicated deep learning approach has been developed to identify and count spikes in the wheat plants. The performance of the approach demonstrates that SpikeSegNet is an effective and robust approach for spike detection and counting. As detection and counting of wheat spikes are closely related to the crop yield, and the proposed approach is also non-destructive, it is a significant step forward in the area of non-destructive and high-throughput phenotyping of wheat.

中文翻译：

---

SpikeSegNet——一种深度学习方法，利用带有沙漏的编码器-解码器网络从视觉成像中对小麦植物进行穗分割和计数。

背景 高通量非破坏性表型分析正在成为一种重要的种质表型分析方法和育种种群，用于鉴定优质供体、优良品系和 QTL。穗粒的检测和计数是小麦的含粒器官，对于控制和田间条件下大量种质和育种系的表型组学至关重要。精准农业也需要在这个关键阶段应用氮、水和其他投入物。此外，尖峰计数是确定产量的重要措施。数字图像分析和机器学习技术在无损植物表型分析中发挥着重要作用。结果在这项研究中，一种基于计算机视觉的方法，特别是目标检测，提出从数字图像中识别和统计小麦植株的穗数。对于尖峰识别，一种新颖的深度学习网络 SpikeSegNet 是通过结合两个提议的特征网络开发的：局部补丁提取网络 (LPNet) 和全局掩码细化网络 (GMRNet)。在 LPNet 中，上下文和空间特征是在局部补丁级别学习的。LPNet 的输出是一个分段的掩码图像，使用 GMRNet 在全局级别进一步细化。使用安装在新德里 ICAR-IARI 的 Nanaji Deshmukh 植物表型组学中心的 LemnaTec 成像系统捕获了 200 株小麦植物的视觉 (RGB) 图像。所提出的尖峰分割方法的精度、准确度和鲁棒性（F1 分数）分别为 99.93%、99.91% 和 99.91%。为了计算尖峰的数量，imageJ 的“分析粒子”功能应用于所提出的 SpikeSegNet 模型的输出图像。对于尖峰计数，平均精度、准确度和稳健性分别为 99%、95% 和 97%。SpikeSegNet 方法在光照图像数据集上进行了鲁棒性测试，在分割性能上没有观察到显着差异。结论 在这项研究中，基于数字图像分析和深度学习技术的结合，提出了一种称为 SpikeSegNet 的新方法。已经开发出一种专门的深度学习方法来识别和计算小麦植物中的尖峰。该方法的性能表明，SpikeSegNet 是一种有效且稳健的尖峰检测和计数方法。由于小麦穗的检测和计数与作物产量密切相关，