地球信息科学学报 ›› 2015, Vol. 17 ›› Issue (3): 353-360.doi: 10.3724/SP.J.1047.2015.00353

• • 上一篇    下一篇

Landsat-8影像的LDA模型变化检测

李杨1(), 江南1,*(), 侍昊2, 邵华3   

  1. 1. 南京师范大学 虚拟地理环境教育部重点实验室,南京,210023
    2. 江苏省环境监测中心,南京,210036
    3. 南京工业大学测绘学院,南京 210009
  • 收稿日期:2014-08-25 修回日期:2014-11-28 出版日期:2015-03-10 发布日期:2015-03-10
  • 通讯作者: 江南 E-mail:skys1017@163.com;njiang@njnu.edu.cn
  • 作者简介:

    作者简介:李 杨(1984- ),女,博士生,研究方向为遥感与地理信息系统。E-mail:skys1017@163.com

  • 基金资助:
    环保公益性行业科研专项(201309037);高分辨率对地观测系统重大专项(05-Y30B02-9001-13/15-WX2);江苏省环境监测科研基金项目(1315)

Change Detection and Analysis of Landsat-8 Image Based on LDA Model

LI Yang1(), JIANG Nan1,*(), SHI Hao2, SHAO Hua3   

  1. 1. Key Laboratory of VGE, Ministry of Education, Nanjing Normal University, Nanjing 210023, China
    2. Jiangsu Provincial Environmental Monitoring Center, Nanjing 210036, China
    3. Department of Geomatics Engineering, Nanjing University of Technology, Nanjing 210009, China
  • Received:2014-08-25 Revised:2014-11-28 Online:2015-03-10 Published:2015-03-10
  • Contact: JIANG Nan E-mail:skys1017@163.com;njiang@njnu.edu.cn
  • About author:

    *The author: SHEN Jingwei, E-mail:jingweigis@163.com

摘要:

变化检测一直是遥感研究领域的热点,随着遥感技术的不断发展,新型数据源不断涌现,使传统遥感变化检测方法面临新的挑战。本文以Landsat-8影像为主要数据源,使用影像分割算法,设计2期遥感影像的文档-单词映射,将影像中所有的像元作为视觉单词,利用LDA模型将影像文档从单词空间转换到主题空间进行表达。在此基础上,结合实地调查对变化区域进行检测和验证,形成一套面向对象的LDA模型变化检测方法。研究表明:基于图斑的分析可有效消除以像元尺度进行变化检测产生的椒盐现象;利用LDA模型构建的变化检测方法能较好地实现影像文档特征的统一表达,有效去除2期影像相同地物因光谱差异导致的变化误检验;与差值法和波谱角等常规遥感变化检测方法相比,该方法能有效地减少错漏判,提高遥感影像变化检测的正确率,为中高分辨率遥感影像的变化检测提供新思路。

关键词: Landsat-8, 变化检测, 面向对象, LDA模型, 词袋模型

Abstract:

Change detection with remote sensing images plays an important role in land cover mapping. With the development of science and technology, a series of new remote sensing data sources have become available, and have been significantly improved, which also brings a great challenge to the traditional remote sensing change detection methods. Unlike the other traditional methods for change detection, the present work uses Latent Dirichlet Allocation model (LDA) in learning middle-level semantic topics instead of low-level features from remote sensing images. In this paper, we use the pixels of two remote sensing images as the basic unit, while the image segments are used as the documents in the object-based image analysis methods. Firstly, we try to extract some features from these remote sensing images, such as the spectral and textural features. Then, we work on organizing the local features from these two images to obtain visual words and construct the bag of words model (BOWM) representation. Based on this, the LDA model is utilized to reveal the underlying topics, which are used to detect the change of the study area. Every document of remote sensing images has a specific topic distribution, which is related to the reference data of the study area. In this process, the pseudo changes and actual changes of these two remote sensing images can be distinguished by the topic distributions of the documents. Compared with traditional pixel-level change detection methods,the method of LDA-based model is less influenced by the spectral variance of two images, which avoids the “salt and pepper” effect by using object-based analysis method. The effectiveness of LDA-based model change detection approach was verified in experiments with the accuracy to be 85.35%, and it is also compared with techniques using Spectral Angle Mapper and Image differencing. The result shows that our studies provide a good approach to improve the accuracy and reduce the mistake rate of change detection between two images. Our work indicates that LDA model-based approach is superior to the traditional methods and the proposed method is applicable to the analysis of change area detection using Landsat-8 images.

Key words: Landsat-8, change detection, object-oriented, LDA model, the bag of words model