Detection and analysis of wheat spikes using Convolutional Neural Networks.
Detection and analysis of wheat spikes using Convolutional Neural Networks.
复制标题
DOI：
10.1186/s13007-018-0366-8
复制
发表时间：
2018
期刊：
影响因子：
5.1
通讯作者：
Miklavcic SJ
中科院分区：
文献类型：
--
作者：
Hasan MM;Chopin JP;Laga H;Miklavcic SJ
近年来，由于有可能实现对农田的高通量分析，通过遥感进行农田表型分析受到越来越多的关注。沿着各种技术的发展，机器学习方法在图像分析中的应用增强了对多种作物性状进行定量评估的潜力。为了小麦育种的目的，评估小麦穗作为籽粒器官的产量，是一种有用的粮食产量的替代措施。因此，能够从麦田图像中检测和表征穗是小麦育种管道中用于选择高产品种的重要组成部分。 我们应用了深度学习方法来准确检测、计数和分析小麦穗，以进行产量估计。我们已经测试了一组图像的麦田试验，包括10个品种进行三种肥料处理的方法。这些图像是在一个季节内拍摄的，使用安装在陆基成像平台上的高清晰度RGB相机，并从倾斜角度观察小麦地块。通过手动注释所有尖峰区域，已准确标记了现场图像的子集。然后，这个被称为SPIKE的注释数据集被用来训练四个基于区域的卷积神经网络（R-CNN），这些网络将小麦地块的图像作为输入，并准确地检测和计数每个地块中的穗区域。CNN还输出每个图的尖峰密度和分类概率。使用相同的R-CNN架构，基于在不同生长阶段捕获的四个不同的训练和测试图像数据集生成了四个不同的模型。尽管具有挑战性的现场成像条件，例如，在可变照明条件、高尖峰遮挡和复杂背景下，四个R-CNN模型在不同的测试图像集上实现了从88到100的平均检测精度。然后选择最稳健的R-CNN模型，其精度最高，研究了10个小麦品种和3个处理的穗产量的变化。SPIKE数据集和训练的CNN是本文的主要贡献。有了本文提出的SPIKE数据集等良好的训练数据集，深度学习技术可以在复杂的麦田图像中实现高精度的尖峰检测和计数。所提出的鲁棒R-CNN模型已在不同生长阶段捕获的尖峰图像上进行了训练，并针对更广泛的现场场景进行了优化。它准确地量化了我们研究的10个品种的产量差异，以及它们各自对肥料处理的反应。我们还观察到，其他R-CNN模型表现出更专业的性能。我们公开提供的数据集和R-CNN模型有可能通过促进高产品种的高通量选择而使植物育种者受益匪浅。本文的在线版本（10.1186/s13007-018-0366-8）包含补充材料，可供授权用户使用。
Field phenotyping by remote sensing has received increased interest in recent years with the possibility of achieving high-throughput analysis of crop fields. Along with the various technological developments, the application of machine learning methods for image analysis has enhanced the potential for quantitative assessment of a multitude of crop traits. For wheat breeding purposes, assessing the production of wheat spikes, as the grain-bearing organ, is a useful proxy measure of grain production. Thus, being able to detect and characterize spikes from images of wheat fields is an essential component in a wheat breeding pipeline for the selection of high yielding varieties. We have applied a deep learning approach to accurately detect, count and analyze wheat spikes for yield estimation. We have tested the approach on a set of images of wheat field trial comprising 10 varieties subjected to three fertilizer treatments. The images have been captured over one season, using high definition RGB cameras mounted on a land-based imaging platform, and viewing the wheat plots from an oblique angle. A subset of in-field images has been accurately labeled by manually annotating all the spike regions. This annotated dataset, called SPIKE, is then used to train four region-based Convolutional Neural Networks (R-CNN) which take, as input, images of wheat plots, and accurately detect and count spike regions in each plot. The CNNs also output the spike density and a classification probability for each plot. Using the same R-CNN architecture, four different models were generated based on four different datasets of training and testing images captured at various growth stages. Despite the challenging field imaging conditions, e.g., variable illumination conditions, high spike occlusion, and complex background, the four R-CNN models achieve an average detection accuracy ranging from 88 to across different sets of test images. The most robust R-CNN model, which achieved the highest accuracy, is then selected to study the variation in spike production over 10 wheat varieties and three treatments. The SPIKE dataset and the trained CNN are the main contributions of this paper. With the availability of good training datasets such us the SPIKE dataset proposed in this article, deep learning techniques can achieve high accuracy in detecting and counting spikes from complex wheat field images. The proposed robust R-CNN model, which has been trained on spike images captured during different growth stages, is optimized for application to a wider variety of field scenarios. It accurately quantifies the differences in yield produced by the 10 varieties we have studied, and their respective responses to fertilizer treatment. We have also observed that the other R-CNN models exhibit more specialized performances. The data set and the R-CNN model, which we make publicly available, have the potential to greatly benefit plant breeders by facilitating the high throughput selection of high yielding varieties. The online version of this article (10.1186/s13007-018-0366-8) contains supplementary material, which is available to authorized users.
登录
查看更多内容
影响因子：
5.1
作者：
Qiongyan L;Cai J;Berger B;Okamoto M;Miklavcic SJ
通讯作者：
Miklavcic SJ
影响因子：
9.2
作者：
Perez-Sanz F;Navarro PJ;Egea-Cortines M
通讯作者：
Egea-Cortines M
影响因子：
5.1
作者：
Barre, Pierre;Stoever, Ben C.;Steinhage, Volker
通讯作者：
Steinhage, Volker
影响因子：
3
作者：
Kovalchuk, Nataliya;Laga, Hamid;Haefele, Stephan M.
通讯作者：
Haefele, Stephan M.
影响因子：
5
作者：
Holman, Fenner H.;Riche, Andrew B.;Hawkesford, Malcolm J.
通讯作者：
Hawkesford, Malcolm J.