激光与光电子学进展, 2021, 58 (8): 0810010, 网络出版: 2021-04-12   

基于多特征融合和混合卷积网络的高光谱图像分类 下载: 967次

Hyperspectral Images Classification Based on Multi-Feature Fusion and Hybrid Convolutional Neural Networks
作者单位
河南理工大学测绘与国土信息工程学院, 河南 焦作454000
摘要
针对三维卷积网络在训练样本较少时对高光谱图像的分类精度不理想问题,提出了一种高效的基于多特征融合和混合卷积网络的分类模型。首先,对高光谱图像进行降维处理后用三维卷积层提取深层空谱联合特征。然后,引入残差连接并通过特征图连接和逐像素相加进行多特征融合,实现特征重用、增强信息传递。最后,用二维卷积层对提取的特征进行空间信息强化,实现图像分类。实验结果表明,在三个公开高光谱数据集Indian Pines、Salinas和University of Pavia中分别用标记样本的5%、1%、1%作为训练样本时,本模型的分类精度分别为97.09%、99.30%、97.60%,可以有效提升小样本情况下的高光谱图像分类效果。
Abstract
Aiming at the problem that the classification accuracy of hyperspectral images is not ideal when the amount of training samples of three-dimensional convolutional network is limited, an efficient classification model based on multi-feature fusion and hybrid convolutional neural networks is proposed in this paper. First, after the dimensionality reduction processing is performed on hyperspectral images, the three-dimensional convolutional layer is used to extract deep hierarchical spatial-spectral joint features. Then, the residual connection is introduced to perform multi-feature fusion through feature map concatenation and pixel-wise addition to realize feature reuse and enhance information transmission. Finally, a two-dimensional convolutional layer is used to enhance the spatial information of the extracted features and realize image classification. The experimental results show that in the three publicly available hyperspectral data sets Indian Pines, Salinas and University of Pavia, 5%, 1% and 1% of the labeled samples are used as training data, respectively, the classification accuracy of the model is 97.09%, 99.30% and 97.60%, respectively, which can effectively improve the classification accuracy of hyperspectral images for under small sample condition.

冯凡, 王双亭, 张津, 王春阳. 基于多特征融合和混合卷积网络的高光谱图像分类[J]. 激光与光电子学进展, 2021, 58(8): 0810010. Fan Feng, Shuangting Wang, Jin Zhang, Chunyang Wang. Hyperspectral Images Classification Based on Multi-Feature Fusion and Hybrid Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2021, 58(8): 0810010.

本文已被 5 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!