Reinhardt Piskackova Theresa, Reberg-Horton Chris, Richardson Robert J, Austin Robert, Jennings Katie M, Leon Ramon G
Department of Crop and Soil Science, North Carolina State University, Raleigh, NC 276957620, USA.
Department of Horticulture, North Carolina State University, Raleigh, NC 276957609, USA.
Plants (Basel). 2020 May 15;9(5):635. doi: 10.3390/plants9050635.
Weed emergence models have the potential to be important tools for automating weed control actions; however, producing the necessary data (e.g., seedling counts) is time consuming and tedious. If similar weed emergence models could be created by deriving emergence data from images rather than physical counts, the amount of generated data could be increased to create more robust models. In this research, repeat RGB images taken throughout the emergence period of L. and (L.) Irwin and Barneby underwent pixel-based spectral classification. Relative cumulative pixels generated by the weed of interest over time were used to model emergence patterns. The models that were derived from cumulative pixel data were validated with the relative emergence of true seedling counts. The cumulative pixel model for and accounted for 92% of the variation in relative emergence of true counts. The results demonstrate that a simple image analysis approach based on time-dependent changes in weed cover can be used to generate weed emergence predictive models equivalent to those produced based on seedling counts. This process will help researchers working on weed emergence models, providing a new low-cost and technologically simple tool for data collection.
杂草出土模型有潜力成为自动化杂草控制行动的重要工具；然而，生成必要的数据（如幼苗计数）既耗时又繁琐。如果能通过从图像而非实际计数中获取出土数据来创建类似的杂草出土模型，那么生成的数据量就可以增加，从而创建更强大的模型。在本研究中，在L.和（L.）Irwin及Barneby的整个出土期拍摄的重复RGB图像进行了基于像素的光谱分类。随着时间推移，由感兴趣的杂草产生的相对累积像素被用于模拟出土模式。从累积像素数据得出的模型通过真实幼苗计数的相对出土情况进行了验证。和的累积像素模型解释了真实计数相对出土变化的92%。结果表明，基于杂草覆盖随时间变化的简单图像分析方法可用于生成与基于幼苗计数产生的模型等效的杂草出土预测模型。这一过程将有助于从事杂草出土模型研究的人员，为数据收集提供一种新的低成本且技术简单的工具。
