The Comparison of Different Methods of Texture Analysis for Their Efficacy for Land Use Classification in Satellite Imagery

被引:100
作者
Kupidura, Przemyslaw [1 ]
机构
[1] Warsaw Univ Technol, Fac Geodesy & Cartog, PL-00661 Warsaw, Poland
关键词
satellite imagery; classification; texture analysis; GLCM; mathematical morphology; granulometric analysis; Laplace filter;
D O I
10.3390/rs11101233
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The paper presents a comparison of the efficacy of several texture analysis methods as tools for improving land use/cover classification in satellite imagery. The tested methods were: gray level co-occurrence matrix (GLCM) features, Laplace filters and granulometric analysis, based on mathematical morphology. The performed tests included an assessment of the classification accuracy performed based on spectro-textural datasets: spectral images with the addition of images generated using different texture analysis methods. The class nomenclature was based on spectral and textural differences and included the following classes: water, low vegetation, bare soil, urban, and two (coniferous and deciduous) forest classes. The classification accuracy was assessed using the overall accuracy and kappa index of agreement, based on the reference data generated using visual interpretation of the images. The analysis was performed using very high-resolution imagery (Pleiades, WorldView-2) and high-resolution imagery (Sentinel-2). The results show the efficacy of selected GLCM features and granulometric analysis as tools for providing textural data, which could be used in the process of land use/cover classification. It is also clear that texture analysis is generally a more important and effective component of classification for images of higher resolution. In addition, for classification using GLCM results, the Random Forest variable importance analysis was performed.
引用
收藏
页数:20
相关论文
共 38 条
[1]   COMBINING LAPLACIAN IMAGES OF DIFFERENT SPATIAL-FREQUENCIES (SCALES) - IMPLICATIONS FOR REMOTE-SENSING IMAGE-ANALYSIS [J].
AHEARN, SC .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1988, 26 (06) :826-831
[2]  
[Anonymous], 1962, IEEE Transactions on Information Theory
[3]  
[Anonymous], ROBOT VISION
[4]  
Banko G., 1998, REV ASSESSING ACCURA
[5]   AN INVESTIGATION OF THE TEXTURAL CHARACTERISTICS ASSOCIATED WITH GRAY-LEVEL COOCCURRENCE MATRIX STATISTICAL PARAMETERS [J].
BARALDI, A ;
PARMIGGIANI, F .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1995, 33 (02) :293-304
[6]  
Bekkari Aissam, 2012, Image and Signal Processing. Proceedings 5th International Conference, ICISP 2012, P17, DOI 10.1007/978-3-642-31254-0_3
[7]   Random Forest Variable Importance Spectral Indices Scheme for Burnt Forest Recovery MonitoringMultilevel RF-VIMP [J].
Boonprong, Sornkitja ;
Cao, Chunxiang ;
Chen, Wei ;
Bao, Shanning .
REMOTE SENSING, 2018, 10 (06)
[8]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[9]   Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification [J].
Cheng, Gong ;
Li, Zhenpeng ;
Han, Junwei ;
Yao, Xiwen ;
Guo, Lei .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (11) :6712-6722
[10]   A REVIEW OF ASSESSING THE ACCURACY OF CLASSIFICATIONS OF REMOTELY SENSED DATA [J].
CONGALTON, RG .
REMOTE SENSING OF ENVIRONMENT, 1991, 37 (01) :35-46