Coffee production estimation is an essential task for coffee farmers in terms of money investment and planning time. In Colombia, the traditional methodology to estimate the total amount of cherry coffee beans is through direct measurements in the field; leave out the cherry beans collected of coffee production (destructive sampling). The cherry coffee dropped in this process cannot be harvest by the producer. In this sense, we found several shortcomings in this methodology as counting errors in the sampling process, insufficient coffee bean samples, significant expenses of costs and time, and coffee beans losses. To handle these issues, we propose a classic Computer Vision (CV) approach to detect cherry beans in coffee trees. This approach substitutes the destructive counting method as a first step to estimate coffee production. To evaluate the CV proposed, seven coffee farmers counted the number of cherry beans on 600 images of coffee trees (castillo, bourbon, and caturra varieties) by human visual perception (ground truth). From evaluations of coffee farmers, we computed statistical measures like precision, recall and, F1-score. The CV system achieved the best results for bourbon coffee trees with 0.594 of precision; 0.669 of total relevant cherry beans correctly classified.

就金钱投资和计划时间而言，估算咖啡产量是咖啡农的一项重要任务。在哥伦比亚，传统的估算樱桃咖啡豆总量的方法是通过实地直接测量得出的。省略咖啡生产中收集的樱桃豆（破坏性采样）。在此过程中掉落的樱桃咖啡无法由生产者收获。从这个意义上讲，我们发现了该方法的一些缺陷，例如计数采样过程中的错误，咖啡豆样品不足，大量的成本和时间开销以及咖啡豆的损失。为了解决这些问题，我们提出了一种经典的计算机视觉（CV）方法来检测咖啡树中的樱桃豆。这种方法将破坏性计数方法替代为估算咖啡产量的第一步。为了评估建议的CV，七名咖啡种植者通过人类视觉感知（地面真相）对600棵咖啡树（卡斯蒂略，波旁威士忌和卡图拉变种）图像上的樱桃豆数量进行了计数。通过对咖啡农的评估，我们计算了统计指标，例如精度，召回率和F1得分。CV系统以0.594的精度获得了波旁咖啡树的最佳结果；正确分类的所有相关樱桃豆中的0.669。