Weed classification in grasslands using convolutional neural networks
Weed classification in grasslands using convolutional neural networks
复制标题
使用卷积神经网络对草原杂草进行分类
DOI：
10.1117/12.2530092
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Smith L
中科院分区：
文献类型：
--
作者：
Smith L
自动识别和选择性喷洒草地中的杂草（如船坞）可以提供非常显著的长期生态效益和成本效益。虽然机器视觉（与适当的自动化接口）提供了实现这一目标的有效手段，但由于图像的复杂性，相关的挑战是艰巨的。这是由诸如图像中船坞的百分比低、诸如三叶草的其他植物的存在以及照明水平的变化等因素造成的。在这里，这些挑战是通过卷积神经网络（CNN）的应用程序来解决的图像包含草和码头;草，码头和白色三叶草。比较了常规训练的CNN和使用“迁移学习”训练的CNN的性能。这是针对越来越小的数据集进行的，以评估每种方法在无法获得大量训练数据的项目中的可行性。结果表明，CNN提供了相当大的改进，比以前的方法分类杂草在草。虽然以前的工作报告了大约83%的最佳准确率，但在这里，传统训练的CNN对于两类数据集达到了95.6%的准确率，对于三类数据集（即码头，三叶草和草）达到了94.9%。有趣的是，使用迁移学习，每个类只有50个样本，仍然可以提供大约84%的准确率。这对于农业企业来说是非常有希望的，因为收集和处理大量数据的成本很高，还没有能够使用神经网络模型。因此，CNN的使用，特别是当结合迁移学习时，是草地杂草分类的一种非常强大的方法，值得进一步研究。
Automatic identification and selective spraying of weeds (such as dock) in grass can provide very significant long-term ecological and cost benefits. Although machine vision (with interface to suitable automation) provides an effective means of achieving this, the associated challenges are formidable, due to the complexity of the images. This results from factors such as the percentage of dock in the image being low, the presence of other plants such as clover and changes in the level of illumination. Here, these challenges are addressed by the application of Convolutional Neural Networks (CNNs) to images containing grass and dock; and grass, dock and white clover. The performance of conventionally- trained CNNs and those trained using ‘Transfer Learning’ was compared. This was done for increasingly small datasets, to assess the viability of each approach for projects where large amounts of training data are not available. Results show that CNNs provide considerable improvements over previous methods for classification of weeds in grass. While previous work has reported best accuracies of around 83%, here a conventionally-trained CNN attained 95.6% accuracy for the two-class dataset, with 94.9% for the three-class dataset (i.e. dock, clover and grass). Interestingly, use of Transfer learning, with as few as 50 samples per class, still provides accuracies of around 84%. This is very promising for agricultural businesses that, due to the high cost of collecting and processing large amounts of data, have not yet been able to employ Neural Network models. Therefore, the employment of CNNs, particularly when incorporating Transfer Learning, is a very powerful method for classification of weeds in grassland, and one that is worthy of further research.
影响因子：
8.3
作者：
F. K. Evert;J. Samsom;G. Polder;M. Vijn;H. V. Dooren;A. Lamaker;G. V. D. Heijden;C. Kempenaar;T. V. D. Zalm;L. Lotz
通讯作者：
F. K. Evert;J. Samsom;G. Polder;M. Vijn;H. V. Dooren;A. Lamaker;G. V. D. Heijden;C. Kempenaar;T. V. D. Zalm;L. Lotz
牧场阔叶杂草检测
DOI：
10.1109/icivc.2018.8492831
发表时间：
2018
期刊：
2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
影响因子：
--
作者：
Wenhao Zhang;M. Hansen;T. Volonakis;Melvyn L. Smith;Lyndon N. Smith;Jim Wilson;Graham Ralston;L. Broadbent;G. Wright
通讯作者：
G. Wright