Araaf Raka Thoriq, Minn Arkar, Ahamed Tofael
Graduate School of Science and Technology, University of Tsukuba, 1-1-1 Tennodai, Tsukuba 305-8577, Japan.
Institute of Life and Environmental Sciences, University of Tsukuba, 1-1-1 Tennodai, Tsukuba 305-8577, Japan.
Sensors (Basel). 2024 Dec 16;24(24):8018. doi: 10.3390/s24248018.
Global warming and extreme climate conditions caused by unsuitable temperature and humidity lead to coffee leaf rust () diseases in coffee plantations. Coffee leaf rust is a severe problem that reduces productivity. Currently, pesticide spraying is considered the most effective solution for mitigating coffee leaf rust. However, the application of pesticide spray is still not efficient for most farmers worldwide. In these cases, pruning the most infected leaves with leaf rust at coffee plantations is important to help pesticide spraying to be more efficient by creating a more targeted, accessible treatment. Therefore, detecting coffee leaf rust is important to support the decision on pruning infected leaves. The dataset was acquired from a coffee farm in Majalengka Regency, Indonesia. Only images with clearly visible spots of coffee leaf rust were selected. Data collection was performed via two devices, a digital mirrorless camera and a phone camera, to diversify the dataset and test it with different datasets. The dataset, comprising a total of 2024 images, was divided into three sets with a ratio of 70% for training (1417 images), 20% for validation (405 images), and 10% for testing (202 images). Images with leaves infected by coffee leaf rust were labeled via LabelImg with the label "CLR". All labeled images were used to train the YOLOv5 and YOLOv8 algorithms through the convolutional neural network (CNN). The trained model was tested with a test dataset, a digital mirrorless camera image dataset (100 images), a phone camera dataset (100 images), and real-time detection with a coffee leaf rust image dataset. After the model was trained, coffee leaf rust was detected in each frame. The mean average precision (mAP) and recall for the trained YOLOv5 model were 69% and 63.4%, respectively. For YOLOv8, the mAP and recall were approximately 70.2% and 65.9%, respectively. To evaluate the performance of the two trained models in detecting coffee leaf rust on trees, 202 original images were used for testing with the best-trained weight from each model. Compared to YOLOv5, YOLOv8 demonstrated superior accuracy in detecting coffee leaf rust. With a mAP of 73.2%, YOLOv8 outperformed YOLOv5, which achieved a mAP of 70.5%. An edge device was utilized to deploy real-time detection of CLR with the best-trained model. The detection was successfully executed with high confidence in detecting CLR. The system was further integrated into pruning solutions for Arabica coffee farms. A pruning device was designed using Autodesk Fusion 360 and fabricated for testing on a coffee plantation in Indonesia.
全球变暖和由不适宜的温度和湿度引起的极端气候条件导致咖啡种植园出现咖啡叶锈病。咖啡叶锈病是一个严重问题，会降低产量。目前，喷洒农药被认为是减轻咖啡叶锈病的最有效解决方案。然而，对于全球大多数农民来说，农药喷洒的应用仍然效率不高。在这些情况下，在咖啡种植园修剪感染叶锈病最严重的叶子对于提高农药喷洒效率很重要，因为这样可以进行更有针对性、更易操作的处理。因此，检测咖啡叶锈病对于支持修剪感染叶子的决策很重要。该数据集来自印度尼西亚马贾冷卡县的一个咖啡农场。只选择了咖啡叶锈病斑点清晰可见的图像。通过数码无反相机和手机相机这两种设备进行数据收集，以使数据集多样化并使用不同数据集进行测试。该数据集共有2024张图像，按70%用于训练（1417张图像）、20%用于验证（405张图像）和10%用于测试（202张图像）的比例分为三组。感染咖啡叶锈病的叶子的图像通过LabelImg标记为“CLR”。所有标记图像都通过卷积神经网络（CNN）用于训练YOLOv5和YOLOv8算法。使用测试数据集、数码无反相机图像数据集（100张图像）、手机相机数据集（100张图像）以及咖啡叶锈病图像数据集进行实时检测，对训练好的模型进行测试。模型训练完成后，在每一帧中检测到了咖啡叶锈病。训练好的YOLOv5模型的平均精度均值（mAP）和召回率分别为69%和63.4%。对于YOLOv8，mAP和召回率分别约为70.2%和65.9%。为了评估这两个训练好的模型在检测树上咖啡叶锈病方面的性能，使用202张原始图像，用每个模型训练效果最好的权重进行测试。与YOLOv5相比，YOLOv8在检测咖啡叶锈病方面表现出更高的准确率。YOLOv8的mAP为73.2%，优于YOLOv5，后者的mAP为70.5%。利用边缘设备部署使用训练效果最好的模型对咖啡叶锈病进行实时检测。在检测咖啡叶锈病时成功地以高置信度执行了检测。该系统进一步集成到阿拉比卡咖啡农场的修剪解决方案中。使用Autodesk Fusion 360设计了一种修剪设备，并制作出来在印度尼西亚的一个咖啡种植园进行测试。
