Enhanced land use/cover classification of heterogeneous tropical landscapes using support vector machines and textural homogeneity

• Published in: International journal of applied earth observation and geoinformation 2013-08, Vol.23, p.372-383
• Main Authors: Paneque-Gálvez, Jaime, Mas, Jean-François, Moré, Gerard, Cristóbal, Jordi, Orta-Martínez, Martí, Luz, Ana Catarina, Guèze, Maximilien, Macía, Manuel J., Reyes-García, Victoria
• Format: Article
• Language: English
• Subjects: Applied geophysics; Bolivian Amazon; Earth sciences; Earth, ocean, space; Exact sciences and technology; Hybrid classification; Internal geophysics; k-Nearest neighbor; Remote sensing; SVM; Texture; Thematic classification comparison
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2012.10.007

► We used Landsat imagery to classify land use/cover over a large, highly heterogeneous tropical area. ► SVM classifiers outperformed other parametric, non-parametric, and hybrid classifiers. ► Textural homogeneity led to the greatest improvements in classification. ► SVM classifiers maximized the usefulness of textural homogeneity and attained overall, producer's, and user's accuracies of ∼90%. ► Our classification approach seems very well suited to accurately map land use/cover of heterogeneous landscapes. Land use/cover classification is a key research field in remote sensing and land change science as thematic maps derived from remotely sensed data have become the basis for analyzing many socio-ecological issues. However, land use/cover classification remains a difficult task and it is especially challenging in heterogeneous tropical landscapes where nonetheless such maps are of great importance. The present study aims at establishing an efficient classification approach to accurately map all broad land use/cover classes in a large, heterogeneous tropical area, as a basis for further studies (e.g., land use/cover change, deforestation and forest degradation). Specifically, we first compare the performance of parametric (maximum likelihood), non-parametric (k-nearest neighbor and four different support vector machines – SVM), and hybrid (unsupervised–supervised) classifiers, using hard and soft (fuzzy) accuracy assessments. We then assess, using the maximum likelihood algorithm, what textural indices from the gray-level co-occurrence matrix lead to greater classification improvements at the spatial resolution of Landsat imagery (30m), and rank them accordingly. Finally, we use the textural index that provides the most accurate classification results to evaluate whether its usefulness varies significantly with the classifier used. We classified imagery corresponding to dry and wet seasons and found that SVM classifiers outperformed all the rest. We also found that the use of some textural indices, but particularly homogeneity and entropy, can significantly improve classifications. We focused on the use of the homogeneity index, which has so far been neglected in land use/cover classification efforts, and found that this index along with reflectance bands significantly increased the overall accuracy of all the classifiers, but particularly of SVM. We observed that improvements in producer's and user's accuracies through the inclusion of homogeneity were d