摘要
机器人和机器学习的新闻编辑每日新闻-机器人的新研究-机器人和D自动化是一篇报道的主题。根据NewsRx记者在智利兰卡瓜的新闻报道，研究表明：“近年来，在水果种植中使用机器人和自主系统的兴趣越来越大。这些系统使用检测和分割算法为计算机提供解释和与植物互动的方式，从而使评估和收获任务自动化。”这项研究的财政支持来自FONDEQUIP项目。新闻记者从奥希金斯大学的研究中获得了一句话：“这种算法需要一个数据集来训练机器学习算法，但大多数类型的水果缺乏公开可用的数据集。我们介绍了一个用于樱桃检测和分割的新的高分辨率数据集Cherry CO。该数据集包含3006个标记图像是在樱桃植物中采集的。图像是在各种条件下拍摄的，以应对这种环境中的大多数挑战。每个樱桃都被手动标记，以考虑位置、SHA PE和类别，并考虑成熟度、健康状态和位置等方面。本信详细描述了数据采集、处理规范和数据集的统计分析。此外，我们研究和评估了几个深度神经网络，为Cherr Y检测提供了一个基准，在大多数网络中实现了高性能，最明显的是YOLOv7.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics - Robotics an d Automation is the subject of a report. According to news reporting originating in Rancagua, Chile, by NewsRx journalists, research stated, “In recent years, t here has been an increasing interest in using robotics and autonomous systems fo r fruit farming. These systems use detection and segmentation algorithms to prov ide computers with a way to interpret and interact with plants, thus allowing th em to automatize assessment and harvesting tasks.” Financial support for this research came from FONDEQUIP project. The news reporters obtained a quote from the research from O’Higgins University, “This type of algorithm requires a dataset to train a machine learning algorith m, but most types of fruits lack a publicly available dataset. We present Cherry CO, a novel, high-resolution dataset for cherry detection and segmentation. Thi s dataset contains 3,006 labeled images that were acquired in a cherry plantatio n. The images were taken in various conditions to account for most challenges in this environment. Each cherry was manually labeled to account for location, sha pe and classes, taking into account aspects such as ripeness, health state and l ocation. This letter presents a detailed description of data acquisition, annota tion specifications and statistical analysis of the dataset. In addition, we tra ined and evaluated several Deep Neural Networks to provide a benchmark for cherr y detection, achieving high performance with most networks, most notably YOLOv7. ”
NETL
NSTL