Arid
基于卷积网络的沙漠腹地绿洲植物群落自动分类方法
其他题名Automatic Classification Method of Oasis Plant Community in Desert Hinterland Based on VGGNet and ResNet Models
尼加提·卡斯木1; 师庆东2; 刘素红3; 比拉力·依明1; 李浩1
来源期刊农业机械学报
ISSN1000-1298
出版年2019
卷号50期号:1页码:217-225
中文摘要为解决沙漠腹地绿洲遥感图像植物群落背景较易混淆,仅用传统的基于像元光谱信息的图像处理方法未能充分利用其图像特征信息,使得提取效果不佳的问题,针对地物类内特征复杂、类间边界模糊的特点,以连续分布的区域为研究对象,提出了一种基于深度卷积神经网络(Convolutional neural network,CNN)的高分辨率遥感影像植物群落自动分类方法.切分无人机影像获得规则块图像,利用基于CNN的VGGNet和ResNet模型分别对块图像的特征进行抽象与学习,以自动获取更加深层抽象、更具代表性的图像块深层特征,从而实现对植物群落分布区域的提取,以原图像与结果图像叠加的形式输出植物群落自动分类结果.采用了不同梯度的样本数量作为训练样本,利用文中提出的方法分析了不同梯度的训练样本数量对自动分类结果的影响.实验结果表明,训练样本数量对分类精度具有明显的影响;提高其泛化能力后,ResNet50模型与VGG19模型的建模精度从86.00%、83.33%分别提升到92.56%、90.29%;ResNet50模型分类精度为83.53%~91.83%,而VGG19模型分类精度为80.97%~89.56%,与传统的监督分类方法比较,深度卷积网络明显提高了分类精度.分类结果表明,训练样本数量不低于200时,基于CNN的ResNet50模型表现出最佳的分类结果.
英文摘要In order to solve the problem of remote sensing image plant community background, only the traditional image processing method based on pixel spectral information fails to make full use of its image feature information, which makes the extraction effect poor. Aiming at the complex features of plant species and the blurring of inter-class boundaries, the continuous distribution of regions was taken as the research object. A high-resolution remote sensing image plant community automatic classification based on the convolutional neural network(CNN) was proposed. The UAV images were segmented to obtain regular block images, and the features of block images were abstracted and learned by CNN-based VGGNet and ResNet models to automatically acquire deeper abstract and more representative image block deep features. The extraction of the plant community distribution area was performed to output the automatic classification results of the plant community in the form of superposition of the original image and the result image. The number of samples with different gradients was used as the training sample. The influence of the number of training samples with different gradients on the automatic classification results was analyzed by the proposed method. The experimental results showed that the number of training samples had a significant impact on the classification accuracy. After improving its generalization ability, the modeling accuracy of ResNet50 model and VGG19 model was improved from 86.00% and 83.33% to 92.56% and 90.29%, respectively. The classification accuracy of ResNet50 model was varied from 83.53% to 91.83%, while the classification accuracy of the VGG19 model was varied from 80.97% to 89.56%. Compared with the traditional supervised classification method, the deep convolution network significantly improved the classification accuracy. Through the analysis of classification result, it was found that the number of training samples should not be less than 200, and the CNN-based ResNet50 model showed the best classification results.
中文关键词沙漠腹地 ; 植物群落 ; 自动分类 ; CNN深度卷积网络 ; VGGNet模型 ; ResNet模型
英文关键词desert hinterland plant community automatic classification CNN deep convolutional network VGGNet model ResNet model
语种中文
国家中国
收录类别CSCD
WOS类目GEOSCIENCES MULTIDISCIPLINARY
WOS研究方向Geology
CSCD记录号CSCD:6419113
来源机构新疆大学 ; 北京师范大学
资源类型期刊论文
条目标识符http://119.78.100.177/qdio/handle/2XILL650/239356
作者单位1.新疆大学干旱生态环境研究所;;新疆大学, ;;绿洲生态教育部重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046;
2.新疆大学;;新疆大学资源与环境科学学院, 绿洲生态教育部重点实验室;;, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046;
3.北京师范大学, 环境遥感与数字城市北京市重点实验室, 北京 100875, 中国
推荐引用方式
GB/T 7714
尼加提·卡斯木,师庆东,刘素红,等. 基于卷积网络的沙漠腹地绿洲植物群落自动分类方法[J]. 新疆大学, 北京师范大学,2019,50(1):217-225.
APA 尼加提·卡斯木,师庆东,刘素红,比拉力·依明,&李浩.(2019).基于卷积网络的沙漠腹地绿洲植物群落自动分类方法.农业机械学报,50(1),217-225.
MLA 尼加提·卡斯木,et al."基于卷积网络的沙漠腹地绿洲植物群落自动分类方法".农业机械学报 50.1(2019):217-225.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[尼加提·卡斯木]的文章
[师庆东]的文章
[刘素红]的文章
百度学术
百度学术中相似的文章
[尼加提·卡斯木]的文章
[师庆东]的文章
[刘素红]的文章
必应学术
必应学术中相似的文章
[尼加提·卡斯木]的文章
[师庆东]的文章
[刘素红]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。