计算机应用 ›› 2018, Vol. 38 ›› Issue (7): 1888-1892.DOI: 10.11772/j.issn.1001-9081.2017122905

• 人工智能 • 上一篇    下一篇

基于空谱融合网络的高光谱图像分类方法

欧阳宁1,2, 朱婷2, 林乐平1,2   

  1. 1. 认知无线电与信息处理省部共建教育部重点实验室(桂林电子科技大学), 广西 桂林 541004;
    2. 桂林电子科技大学 信息与通信学院, 广西 桂林 541004
  • 收稿日期:2017-12-12 修回日期:2018-03-01 出版日期:2018-07-10 发布日期:2018-07-12
  • 通讯作者: 林乐平
  • 作者简介:欧阳宁(1972-),男,湖南宁远人,教授,硕士,主要研究方向:数字图像处理、智能信息处理;朱婷(1991-),女,江苏宿迁人,硕士研究生,主要研究方向:模式识别、深度学习;林乐平(1980-),女,广西桂平人,副教授,博士,主要研究方向:机器学习、智能信息处理、图像处理。
  • 基金资助:
    国家自然科学基金资助项目(61661017,61362021);广西自然科学基金资助项目(2017GXNSFBA198212,2014GXNSFDA118035,2016GXNSFAA38014);广西科技创新能力与条件建设计划项目(桂科能1598025-21);桂林科技开发项目(20150103-6);中国博士后科学基金资助项目(2016M602923XB);桂林电子科技大学研究生教育创新计划资助项目(2016YJCXB02);认知无线电与信息处理重点实验室基金资助项目(CRKL160104,CRKL150103,2011KF11)。

Hyperspectral image classification method based on spatial-spectral fusion network

OUYANG Ning1,2, ZHU Ting2, LIN Leping1,2   

  1. 1. Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education(Guilin University of Electronic Technology), Guilin Guangxi 541004, China;
    2. School of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
  • Received:2017-12-12 Revised:2018-03-01 Online:2018-07-10 Published:2018-07-12
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61661017,61362021), the Natural Science Foundation of Guangxi (2017GXNSFBA198212, 2014GXNSFDA118035, 2016GXNSFAA38014), the Scientific and Technological Innovation Ability and Condition Construction Plan of Guangxi (GUIKENENG 1598025-21), the Scientific and Technological Development Program of Guilin (20150103-6), the China Postdoctoral Science Foundation (2016M602923XB), the Innovation Project for Graduate Education in Guilin University of Electronic Technology (2016YJCXB02), the Fund of the Key Laboratory of Cognitive Radio and Information Processing of Ministry of Education (CRKL160104, CRKL150103, 2011KF11).

摘要: 针对高光谱图像分类中提取的空-谱特征表达能力弱及维数较高的问题,提出一种基于空-谱融合网络(SSF-Net)的高光谱图像分类方法。首先,利用双通道卷积神经网络(Two-CNN)同时提取高光谱图像的光谱和空间特征;其次,使用多模态压缩双线性池化(MCB)将所提取的多模态特征向量的外积投射到低维空间,以此产生空-谱联合特征。该特征融合网络,既可以分析光谱特征和空间特征向量中元素之间的复杂关系,同时也避免对光谱和空间向量直接进行外积计算,造成维数过高、计算困难的问题。最终实验表明,与现有基于神经网络的分类方法相比,所提出的高光谱图像分类算法能够获得更高的像元分类精度,表明该网络所提取的空-谱联合向量对高光谱图像具有更强的特征表达能力。

关键词: 空-谱融合网络, 多模态压缩双线性池化, 特征融合, 外积, 高光谱图像分类

Abstract: Concerning the problem that the extracted spatial-spectral features have the shortcoming of weak representation ability and high dimensionality, a HyperSpectral Image (HSI) classification method based on Spatial-Spectral Fusion Network (SSF-Net) was proposed. Firstly, a Two-channel Convolutional Neural Network (Two-CNN) was used to extract the features of spectral domain and spatial domain for HSI respectively. Secondly, Multimodal Compact Bilinear pooling (MCB) was employed to project the outer product of extracted multimodal features to the low dimensional space for producing jointly spatial-spectral features. The fusion network could not only analyze the complex relationship between elements in spectral and spatial eigenvectors, but also avoid directly computing the outer product of spectral and spatial vectors, resulting in high dimension and high computation times. The experimental results show that, compared with the state-of-the-art neural network based classification methods, the proposed algorithm can obtain higher pixel classification accuracy. It indicates that the spatial-spectral joint vector extracted by the proposed network has stronger representation ability.

Key words: Spatial-Spectral Fusion Network (SSF-Net), multimodal compact bilinear pooling, feature fusion, outer product, HyperSpectral Image (HSI) classification

中图分类号: