| 基于混合3D-2D CNN的多时相遥感农作物分类 |
| |
| 引用本文： | 卢元兵,李华朋,张树清.基于混合3D-2D CNN的多时相遥感农作物分类[J].农业工程学报,2021,37(13):142-151. |
| |
| 作者姓名： | 卢元兵 李华朋 张树清 |
| |
| 作者单位： | 1. 中国科学院东北地理与农业生态研究所，长春 130102; 2. 中国科学院大学，北京 100049; |
| |
| 基金项目： | 国家重点研发计划项目（2016YFB0502300）；国家自然科学基金项目（41671397） |
| |
| 摘 要： | 准确的农作物分类图是农业监测和粮食安全评估的重要数据来源,针对传统的深度学习模型在多时相农作物遥感分类方面精度较低的问题,该研究将卷积维度单一的卷积神经网络(Convolutional Neural Networks,CNN)进行改进,提出了一种混合三维和二维卷积的神经网络识别模型(HybridThreeDimensionalandTwoDimensionalConvolutional Neural Networks,3D-2D CNN)。该模型首先通过多个三维卷积层提取时空特征,其次将输出的特征降维压缩后通过二维卷积层执行空域特征分析,最后将高层特征图展平后通过全连接层进行类别预测。试验以Landsat8多时相影像为数据源,将美国加利福尼亚州北部研究区的地块按照2:2:6分层随机划分为训练集、验证集和测试集。试验结果表明3D-2DCNN对13种农作物分类的总体精度(89.38%)、宏平均F1值(84.21%)和Kappa系数(0.881)均优于三维卷积神经网络(Three Dimensional Convolutional Neural Networks,3D-CNN)、二维卷积神经网络(Two Dimensional Convolutional Neural Networks,2D-CNN)、支持向量机(Support Vector Machines,SVM)和随机森林(Random Forest,RF)等方法,并在参数量和收敛时间方面比3D CNN大幅度减小。同时,在较小样本训练集下3D-2D CNN仍表现最优。该模型综合利用空间-光谱-时间特征并具有较高的分类精度和较强的鲁棒性,这为解决多时相遥感农作物分类问题提供了一个有效且可行的方案。
|
| 关 键 词： | 遥感 农作物 多时相地块 分类 深度学习 卷积神经网络 |
| 收稿时间： | 2020/12/2 0:00:00 |
| 修稿时间： | 2021/6/29 0:00:00 |
Multi-temporal remote sensing based crop classification using a hybrid 3D-2D CNN model |
| |
| Lu Yuanbing,Li Huapeng,Zhang Shuqing.Multi-temporal remote sensing based crop classification using a hybrid 3D-2D CNN model[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(13):142-151. |
| |
| Authors: | Lu Yuanbing Li Huapeng Zhang Shuqing |
| |
| Institution: | 1. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China; 2. University of Chinese Academy of Sciences, Beijing 100049, China; |
| |
| Abstract: | Reliable and accurate classification of crop types can greatly contribute to data sources in agricultural monitoring and food security. Remote sensing can be used to rapidly and accurately extract the planting areas and distribution of main crops, thereby optimizing the spatial pattern of crops, grain production, and management. However, it is extremely difficult to identify and then map different types of crops with high accuracy and efficiency, especially for traditional machine learning. The reason is that there are highly complex and heterogeneous spectral data in crop space on time-series remote sensing images. Fortunately, three-dimensional convolution neural networks (3D CNN) are suitable for the spatio-temporal information in the time-series remote sensing imagery. Nevertheless, the high complexity of the 3D CNN model often requires a large number of training samples. In this study, a novel hybrid classification model (called 3D-2D CNN) was proposed to integrate 3D CNN and two-dimensional convolution neural networks (2D CNN) in the trade-off among accuracy, efficiency, and ground sample acquisition. The specific procedure was as follows. The spatio-temporal features were first extracted from the multiple 3D convolutional layers, then the output features were compressed for the spatial feature analysis in the 2D convolutional layer, and finally the high-level maps of features were flattened to predict the category in the fully connected layer. Batch normalization was performed on the input data of each layer to accelerate the network convergence. As such, the complex structure of the original 3D CNN was reduced, while the capacity of 3D-2D CNN remained in spatio-temporal feature extraction. Taking northern California, USA, as the study area, Landsat8 multi-temporal images were utilized as the remote sensing data source in the test to verify the model. Landsat images presented specific characteristics, compared with the natural. The spectral and texture features of the same type varied greatly along with the imaging time and conditions. California agricultural investigation was used as sampling data. Accordingly, the land plots in the study area were randomly divided into a training, validation, and test region, according to 20%:20%:60% stratification, where the training and validation sample datasets were randomly selected. Since the overflow easily occurred, when the training dataset was limited in actual work, it was necessary for the deep learning model to require a large number of data samples to train a CNN. Correspondingly, two small sample sets of different proportions were randomly selected from the training sample set of 50% and 25% to verify the feasibility of the model. The trained models were then used to predict the test region. The experimental results showed that the overall accuracy (89.38%), macro-average F1 value (84.21%), and Kappa coefficient (0.881) of 3D-2D CNN for 13 crop classifications performed better than other deep learning, including 3D CNN and 2D CNN, as well as traditional machine learning, such as Support Vector Machines (SVM) and Random Forest (RF). It should be mentioned that the proposed 3D-2D CNN also achieved the best performance in the small training set, where the highest recognition rate of classification was obtained, compared with the benchmark models. Meanwhile, the convergence time of 3D-2D CNN was reduced greatly, compared with the 3D CNN, thanks to a significant reduction of parameters. It was found that there was a greater effect of temporal features of crops that were hidden in multi-temporal remote sensing imagery on CNN classification, compared with texture features. Consequently, the highest accuracy and strongest robustness were obtained in the 3D-2D CNN model, due mainly to the comprehensive utilization of spatial-temporal-spectrum features. The finding can provide a highly effective and novel solution to crop classification from multi-temporal remote sensing. |
| |
| Keywords: | remote sensing crops multi-temporal field parcel classification deep learning CNN |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
