小麦(Triticumaestivum)是在大平原南部种植的主要谷类作物。这种作物面临各种害虫,可能影响其发育并降低产量。例如,蚜虫是小麦的重要害虫,他们的管理依赖于杀虫剂,这会影响捕食蚜虫的自然捕食者的可持续性和生物多样性。球藻,通常被称为甲虫夫人,是小麦最丰富的天然捕食者。这些天敌有助于蚜虫的自然捕食,这可以减少使用过量的农药进行蚜虫管理。通常,这些天敌的视觉观察是在害虫采样过程中进行的;然而,这既耗时又需要体力劳动,这可能是昂贵的。需要一种基于机器学习方法的自动化系统或检测模型来检测这些昆虫,以减少不必要的农药应用和手工劳动成本。然而,开发自动化系统或计算机视觉模型来自动检测这些天敌需要图像来训练和验证这种尖端技术。为了解决这个研究问题,我们收集了这个数据集,其中包括图像和标签注释,以帮助研究人员和学生开发这项技术,使小麦种植者和科学受益,以了解昆虫学自动化的能力。我们使用移动设备收集了一个数据集,其中包括小麦图像上的各种球虫。该数据集由2,133张图像组成,标准尺寸为640×640像素,可用于训练和开发用于机器学习目的的检测模型。此外,数据集包括可用于YOLO系列或其他系列中的训练模型的注释标签,已被证明可以检测农作物中的小昆虫。我们的数据集将增加对昆虫学中机器学习能力的理解,精准农业,教育,和作物病虫害管理决策。
Wheat (Triticum aestivum) is a major
cereal crop planted in the Southern Great Plains. This crop faces diverse pests that can affect their development and reduce yield productivity. For example, aphids are a significant pest in wheat, and their management relies on pesticides, which affect the sustainability and biodiversity of natural predators that prey on aphids. Coccinellids, commonly named lady beetles, are the most abundant natural predators of wheat. These natural enemies contribute to the natural predation of aphids, which can reduce the use of excessive pesticides for aphid management. Usually, visual observations of these natural enemies are performed during pest sampling; however, it is time-consuming and requires manual labor, which can be expensive. An automation system or detection models based on machine learning approaches that can detect these insects is needed to reduce unnecessary pesticide applications and manual labor costs. However, developing an automation system or computer vision models that automatically detect these natural enemies requires imagery to train and validate this cutting-edge technology. To solve this research problem, we collected this dataset, which includes images and label annotations to help researchers and students develop this technology that can benefit wheat growers and science to understand the capabilities of automation in Entomology. We collected a dataset using mobile devices, which included a diverse range of coccinellids on wheat images. The dataset consists of 2,133 images with a standard size of 640 × 640 pixels, which can be used to train and develop detection models for machine learning purposes. In addition, the dataset includes annotated labels that can be used for training models within the YOLO family or others, which have been proven to detect small insects in crops. Our dataset will increase the understanding of machine learning capabilities in entomology, precision agriculture, education, and crop pest management decisions.