ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2014, Vol. 51 ›› Issue (9): 1911-1918.doi: 10.7544/issn1000-1239.2014.20140199

所属专题: 2014深度学习

• 人工智能 • 上一篇    下一篇

基于DBN模型的遥感图像分类

吕启1,窦勇1,牛新1,徐佳庆1,夏飞2   

  1. 1(国防科学技术大学计算机学院并行与分布处理国防科技重点实验室 长沙 410073);2(海军工程大学电子工程学院 武汉 430033) (lvqi@nudt.edu.cn)
  • 出版日期: 2014-09-01
  • 基金资助: 
    基金项目:国家自然科学基金项目(61125201,61202127)

Remote Sensing Image Classification Based on DBN Model

Lü Qi1, Dou Yong1, Niu Xin1, Xu Jiaqing1, Xia Fei2   

  1. 1(National Laboratory for Parallel and Distributed Processing, School of Computer, National University of Defense Technology, Changsha 410073);2(Electronic Engineering College, Naval University of Engineering, Wuhan 430033)
  • Online: 2014-09-01

摘要: 遥感图像分类是地理信息系统(geographic information system, GIS)的关键技术,对城市规划与管理起到十分重要的作用.近年来,深度学习成为机器学习领域的一个新兴研究方向.深度学习采用模拟人脑多层结构的方式,对数据从低层到高层渐进地进行特征提取,从而发掘数据在时间与空间上的规律,进而提高分类的准确性.深度信念网络(deep belief network, DBN)是一种得到广泛研究与应用的深度学习模型,它结合了无监督学习和有监督学习的优点,对高维数据具有较好的分类能力.提出一种基于DBN模型的遥感图像分类方法,并利用RADARSAT-2卫星6d的极化合成孔径雷达(synthetic aperture radar, SAR)图像进行了验证.实验表明,与支持向量机(SVM)及传统的神经网络(NN)方法相比,基于DBN模型的方法可以取得更好的分类效果.

关键词: 遥感图像, 合成孔径雷达, 地物分类, 深度学习, 受限玻尔兹曼机, 深度信念网络

Abstract: Remote sensing image classification is one of the key technologies in geographic information system (GIS), and it plays an important role in modern urban planning and management. In the field of machine learning, deep learning is springing up in recent years. By mimicking the hierarchical structure of human brain, deep learning can extract features from lower level to higher level gradually, and distill the spatio-temporal regularizes of input data, thus improve the classification performance. Deep belief network (DBN) is a widely investigated and deployed deep learning model. It combines the advantages of unsupervised and supervised learning, and can archive good classification performance for high-dimensional data. In this paper, a remote sensing image classification method based on DBN model is proposed. This is one of the first attempts to apply deep learning approach to urban detailed classification. Six-day high-resolution RADARSAT-2 polarimetric synthetic aperture radar (SAR) data were used for evaluation. Experimental results show that the proposed method can outperform SVM (support vector machine) and traditional neural network (NN).

Key words: remote sensing image, synthetic aperture radar(SAR), land cover classification, deep learning, restricted Boltzmann machine (RBM), deep belief network (DBN)

中图分类号: