Torres-Lomas Efrain, Lado-Bega Jimena, Garcia-Zamora Guillermo, Diaz-Garcia Luis
Department of Viticulture and Enology, University of California Davis, Davis, CA 95616, USA.
Soil and Water Department, Universidad de la Republica, Montevideo 11400, Uruguay.
Plant Phenomics. 2024 Jun 27;6:0202. doi: 10.34133/plantphenomics.0202. eCollection 2024.
Grape cluster architecture and compactness are complex traits influencing disease susceptibility, fruit quality, and yield. Evaluation methods for these traits include visual scoring, manual methodologies, and computer vision, with the latter being the most scalable approach. Most of the existing computer vision approaches for processing cluster images often rely on conventional segmentation or machine learning with extensive training and limited generalization. The Segment Anything Model (SAM), a novel foundation model trained on a massive image dataset, enables automated object segmentation without additional training. This study demonstrates out-of-the-box SAM's high accuracy in identifying individual berries in 2-dimensional (2D) cluster images. Using this model, we managed to segment approximately 3,500 cluster images, generating over 150,000 berry masks, each linked with spatial coordinates within their clusters. The correlation between human-identified berries and SAM predictions was very strong (Pearson's = 0.96). Although the visible berry count in images typically underestimates the actual cluster berry count due to visibility issues, we demonstrated that this discrepancy could be adjusted using a linear regression model (adjusted = 0.87). We emphasized the critical importance of the angle at which the cluster is imaged, noting its substantial effect on berry counts and architecture. We proposed different approaches in which berry location information facilitated the calculation of complex features related to cluster architecture and compactness. Finally, we discussed SAM's potential integration into currently available pipelines for image generation and processing in vineyard conditions.
葡萄串的结构和紧实度是影响病害易感性、果实品质和产量的复杂性状。这些性状的评估方法包括视觉评分、人工方法和计算机视觉，其中计算机视觉是最具扩展性的方法。现有的大多数用于处理葡萄串图像的计算机视觉方法通常依赖于传统分割或机器学习，需要大量训练且泛化能力有限。分割一切模型（SAM）是一种在海量图像数据集上训练的新型基础模型，无需额外训练即可实现自动目标分割。本研究展示了开箱即用的SAM在识别二维（2D）葡萄串图像中单个浆果方面的高精度。使用该模型，我们成功分割了约3500张葡萄串图像，生成了超过150,000个浆果掩码，每个掩码都与它们所在葡萄串内的空间坐标相关联。人工识别的浆果与SAM预测之间的相关性非常强（皮尔逊相关系数 = 0.96）。尽管由于可见性问题，图像中可见的浆果数量通常会低估实际的葡萄串浆果数量，但我们证明可以使用线性回归模型来调整这种差异（调整后相关系数 = 0.87）。我们强调了葡萄串成像角度的至关重要性，指出其对浆果数量和结构有重大影响。我们提出了不同的方法，其中浆果位置信息有助于计算与葡萄串结构和紧实度相关的复杂特征。最后，我们讨论了SAM潜在地整合到当前可用的葡萄园条件下图像生成和处理管道中的情况。
