Abstract
There is a large amount of remote sensing data available for land use and land cover (LULC) classification and thus optimizing selection of remote sensing variables is a great challenge. Although many methods such as Jeffreys–Matusita (JM) distance and random forests (RF) have been developed for this purpose, the existing methods ignore correlation and information duplication among remote sensing variables. In this study, a novel approach was proposed to improve the measures of potential class separability for the selection of remote sensing variables by taking into account correlations among the variables. The proposed method was examined with a total of thirteen spectral variables from a Gaofen-1 image, three class separability measures including JM distance, transformed divergence and B-distance and three classifiers including Bayesian discriminant (BD), Mahalanobis distance (MD) and RF for classification of six LULC types at the East Dongting Lake of Hunan, China. The results showed that (1) The proposed approach selected the first three spectral variables and resulted in statistically stable classification accuracies for three improved class separability measures. That is, the classification accuracies using three or more spectral variables statistically did not significantly differ from each other at a significant level of 0.05; (2) The statistically stable classification accuracies obtained by integrating MD and BD classifiers with the improved class separability measures were also statistically not significantly different from those by RF; (3) The numbers of the selected spectral variables using the improved class separability measures to create the statistically stable classification accuracies by MD and BD classifiers were much smaller than those from the original class separability measures and RF; and (4) Three original class separability measures and RF led to similar ranks of importance of the spectral variables, while the ranks achieved by the improved class separability measures were different due to the consideration of correlations among the variables. This indicated that the proposed method more effectively and quickly selected the spectral variables to produce the statistically stable classification accuracies compared with the original class separability measures and RF and thus improved the selection of the spectral variables for the classification.
Highlights
Classification of land use and land cover (LULC) types using images is a basic and important application of remote sensing technologies and substantial research has been conducted
The proposed method was investigated using three class separability measures including JM distance, divergence and B-distance based on 13 spectral variables from a GF-1 image with three classifiers including Bayesian discriminant (BD), Mahalanobis distance (MD) and random forests (RF) for classification of six LULC types at the East
The results showed that (1) By selecting the first three spectral variables, the proposed approach resulted in the statistically stable classification accuracies for all the improved class separability measures at the significant level of 0.05; (2) The statistically stable classification accuracies obtained by integrating MD
Summary
Classification of land use and land cover (LULC) types using images is a basic and important application of remote sensing technologies and substantial research has been conducted. Accurately classifying remotely sensed images into LULC maps is still challenging [1,2,3,4,5]. This study focused on exploring the development of a novel method that can be used to improve the selection of remote sensing variables for image classification of LULC types given other factors such as a study area, a data set, a classifier, etc., are held constant. Selection of remote sensing variables greatly varies depending on available bands or channels from airborne and space borne sensors. In addition to the bands from sensors, a large number of remote sensing variables can be derived by conducting various image enhancements and transformations, including image ratios, vegetation indices, image transformations, textural or contextual features and data fusion [1,2,6]. Principal component analysis, minimum noise fraction transform, decision boundary feature extraction, wavelet transform, Fourier analysis or transform and spectral mixture analysis can be used to create remote sensing variables and to reduce data redundancy [7,8,9,10]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
