Garcia Millan V.E., Sanchez Azofeifa G.A., Malvarez G.C., More G., Pons X., Yamanaka-Ocampo M. (2013) Effects of topography on the radiometry of CHRIS/PROBA images of successional stages within tropical dry forests. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 6: 1584-1595.EnllaçDoi: 10.1109/JSTARS.2013.2259471
In the present paper, the effect of shadows in the classification of three successional stages of a tropical dry forest (TDF) in Mexico, using hyperspectral and multi-angular CHRIS/PROBA images, is evaluated. An algorithm based on the cosine of the angle of solar incidence on the terrain is applied to correct the effect of topography on CHRIS/PROBA reflectances. Previous to the removal of shadows caused by topography, CHRIS/PROBA images were atmospherically corrected in BEAM software. Vegetation maps of the study site were generated using non-parametric decision trees, defining four main classes: late, intermediate and early stages of forest succession within a tropical dry forest, and riparian forests. By comparing the vegetation maps before and after shadow removal in CHRIS/PROBA spectral data, it was observed that the late stage of succession and riparian forests are overestimated for the non-corrected images while intermediate and early stages of succession are underestimated. Errors in classification are more important for the large CHRIS/PROBA viewing angles. Therefore, the removal of shadows caused by topography is necessary for an accurate classification of successional stages in tropical dry forests. © 2013 IEEE.
Paneque-Gálvez J., Mas J.-F., Moré G., Cristóbal J., Orta-Martínez M., Luz A.C., Guèze M., Macía M.J., Reyes-García V. (2013) Enhanced land use/cover classification of heterogeneous tropical landscapes using support vector machines and textural homogeneity. International Journal of Applied Earth Observation and Geoinformation. 23: 372-383.EnllaçDoi: 10.1016/j.jag.2012.10.007
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 (30 m), 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 different depending on land use/cover classes. Early-growth/degraded forests, pastures, grasslands and savanna were the classes most improved, especially with the SVM radial basis function and SVM sigmoid classifiers, though with both classifiers all land use/cover classes were mapped with producer's and user's accuracies of ~90%. Our classification approach seems very well suited to accurately map land use/cover of heterogeneous landscapes, thus having great potential to contribute to climate change mitigation schemes, conservation initiatives, and the design of management plans and rural development policies. © 2012 Elsevier B.V.
Dona't d'alta al Newsletter per rebre totes les novetats del CREAF al teu e-mail.
© 2016 CREAF | Avís legal