智慧农业（中英文）2020，Vol.2Issue(3)：61-74,14.DOI:10.12133/j.smartag.2020.2.3.202007-SA002
利用图像和机器学习检测大豆作物幼苗期玉米杂苗
Distinguishing Volunteer Corn from Soybean at Seedling Stage Using Images and Machine Learning
摘要
Abstract
Volunteer corn in soybean fields are harmful as they disrupt the benefits of corn-soybean rotation. Volun-teer corn does not only reduce soybean yield by competing for water, nutrition and sunlight, but also interferes with pest control (e.g., corn rootworm). It is therefore critical to monitor the volunteer corn in soybean at the crop seed-ling stage for better management. The current visual monitoring method is subjective and inefficient. Technology progress in sensing and automation provides a potential solution towards the automatic detection of volunteer corn from soybean. In this study, corn and soybean were planted in pots in greenhouse to mimic field conditions. Color images were collected by using a low-cost Intel RealSense camera for five successive days after the germination. In-dividual crops from images were manually cropped and subjected to image segmentation based on color threshold coupled with noise removal to create a dataset. Shape (i. e., area, aspect ratio, rectangularity, circularity, and eccen-tricity), color (i.e., R, G, B, H, S, V, L, a, b, Y, Cb, and Cr) and texture (coarseness, contrast, linelikeness, and direc-tionality) features of individual crops were extracted. Individual feature's weights were ranked with the top 12 rele-vant features selected for this study. The 12 features were fed into three feature-based machine learning algorithms:support vector machine (SVM), neural network (NN) and random forest (RF) for model training. Prediction preci-sion values on the test dataset for SVM, NN and RF were 85.3％, 81.6％, and 82.0％, respectively. The dataset (with-out feature extraction) was fed into two deep learning algorithms—GoogLeNet and VGG-16, resulting into 96.0％and 96.2％ accuracies, respectively. The more satisfactory models from feature-based machine learning and deep learning were compared. VGG-16 was recommended for the purpose of distinguishing volunteer corn from soybean due to its higher detection accuracy, as well as smaller standard deviation (STD). This research demonstrated RGB images, coupled with VGG-16 algorithm could be used as a novel, reliable (accuracy>96％), and simple tool to de-tect volunteer corn from soybean. The research outcome helps provide critical information for farmers, agronomists, and plant scientists in monitoring volunteer corn infestation conditions in soybean for better decision making and management.关键词
玉米-大豆轮作/玉米杂苗/图像处理/机器学习/深度学习/支持向量机(SVM)Key words
corn and soybean rotation/volunteer corn/image processing/machine learning/deep learning/supportvector machine (SVM)分类
农业科技引用本文复制引用
Paulo FLORES,张昭,Jithin MATHEW,Nusrat JAHAN,John STENGER..利用图像和机器学习检测大豆作物幼苗期玉米杂苗[J].智慧农业（中英文）,2020,2(3):61-74,14.基金项目
NDSU-AES Project(FARG005348) （FARG005348）
