光学学报, 2020, 40 (15): 1528003, 网络出版: 2020-08-05   

多层感知卷积神经网络的国产多光谱影像分类 下载: 1169次

Domestic Multispectral Image Classification Based on Multilayer Perception Convolutional Neural Network
作者单位
1 长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012
2 中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
3 吉林省国土资源调查规划研究院, 吉林 长春 130061
摘要
联合像元谱段信息与空间结构特征,提出一种适用于多光谱遥感影像像素级分类的多层感知卷积神经网络(MPCNet),并基于吉林1号光谱卫星(Jilin-1GP)影像,在印度纳西克研究区对地表覆盖分类算法进行性能测试。为保证实验的高可靠性,在相同时间段结合Landsat8、Sentinel-2A及HJ-1A影像进行同步分类来定性与定量评估。除此之外,选取三个当前流行算法支持向量机(SVM)、LightGBM、浅层卷积神经网络(CNN)进行算法性能比较。实验结果表明,在Jilin-1GP影像上的总体分类精度可达94.0%~95.8%,Kappa系数达到0.932~0.948。相比准确率较高的浅层CNN,MPCNet的总体分类精度提升3.7个百分点。
Abstract
In this study, a multilayer perception convolutional neural network (MPCNet) was proposed for the pixel-level classification of multispectral remote sensing images, which combines the spectral information and spatial structure features of pixels. The performance of a land-cover-classification algorithm was tested based on the Jilin-1 spectral satellite (Jilin-1GP) images in the Nashik research area, India. To ensure high reliability of the experiment, the Landsat8, Sentinel-2A, and HJ-1A images were used within the same time interval for synchronized classification to perform qualitative and quantitative evaluations. Moreover, three current popular algorithms, namely, support vector machine(SVM), LightGBM, and shallow convolutional neural network(CNN), were selected to compare the algorithm performance. The experimental results indicate that the overall classification accuracy on the Jilin-1GP images can reach 94.0%-95.8%, and the Kappa coefficient can reach 0.932-0.948. The overall classification accuracy of the MPCNet increase by 3.7 percentage compared with that of the shallow CNN, which exhibits high accuracy.

朱瑞飞, 马经宇, 李竺强, 王栋, 安源, 钟兴, 高放, 孟祥玉. 多层感知卷积神经网络的国产多光谱影像分类[J]. 光学学报, 2020, 40(15): 1528003. Ruifei Zhu, Jingyu Ma, Zhuqiang Li, Dong Wang, Yuan An, Xing Zhong, Fang Gao, Xiangyu Meng. Domestic Multispectral Image Classification Based on Multilayer Perception Convolutional Neural Network[J]. Acta Optica Sinica, 2020, 40(15): 1528003.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!