摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑发表了关于人工智能的新研究结果。根据NewsRx编辑来自内布拉斯加州林肯的新闻，该研究指出，"成像、计算机视觉和自动化的进步已经彻底改变了各个领域，包括基于实地的高通量植物表型(FHTPP)"。这项研究的财政支持者包括美国农业文化部。我们的新闻记者从Ne Braska-Lincoln大学的研究中获得了一句话：“这种整合可以快速准确地测量植物性状。深度卷积神经网络(DCNNs)已经成为FHTPP的一个非常有用的工具，特别是在作物分段识别作物背景-这对性状分析至关重要。然而，十个DCNN的有效性取决于大型标记数据集的可用性。”本文提出了一种基于bagging的深度学习方法,并在玉米nu-spidercam数据集上进行了实验,结果表明,该方法在预测精度和速度上优于传统的机器学习和深度学习模型.它比阈值法提高了40%，比传统机器学习提高了11%，预测时间和可获得的训练时间明显缩短。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news originating from Lincoln, Nebraska , by NewsRx editors, the research stated, “Advancements in imaging, computer vis ion, and automation have revolutionized various fields, including field-based hi gh-throughput plant phenotyping (FHTPP).” Financial supporters for this research include United States Department of Agric ulture. Our news correspondents obtained a quote from the research from University of Ne braska-Lincoln: “This integration allows for the rapid and accurate measurement of plant traits. Deep Convolutional Neural Networks (DCNNs) have emerged as a po werful tool in FHTPP, particularly in crop segmentationidentifying crops from t he background-crucial for trait analysis. However, the effectiveness of DCNNs of ten hinges on the availability of large, labeled datasets, which poses a challen ge due to the high cost of labeling. In this study, a deep learning with bagging approach is introduced to enhance crop segmentation using high-resolution RGB i mages, tested on the NU-Spidercam dataset from maize plots. The proposed method outperforms traditional machine learning and deep learning models in prediction accuracy and speed. Remarkably, it achieves up to 40% higher Inter section-over-Union (IoU) than the threshold method and 11% over co nventional machine learning, with significantly faster prediction times and mana geable training duration.”
NETL
NSTL