Moreover, our proposed method reduces misclassifications between certain vegetation types, and improves identification of the impervious type. Experimental results show that our proposed method achieves a classification accuracy of 84.40% on the entire validation dataset in China, improving the previous state-of-the-art accuracies obtained by RF and SVM by 4.50% and 4.20%, respectively. Our major innovation is a hybrid approach that includes three major components: (1) a deep convolutional neural network (CNN)-based classifier that extracts high-resolution features from Google Earth imagery (2) traditional machine learning classifiers (i.e., Random Forest (RF) and Support Vector Machine (SVM)) that are based on spectral features extracted from 30-m Landsat data and (3) an ensemble decision maker that takes all different features into account. In this work, we improved the land cover classification accuracy by integrating free and public high-resolution Google Earth images (HR-GEI) with Landsat Operational Land Imager (OLI) and Enhanced Thematic Mapper Plus (ETM+) imagery. However, despite substantial efforts in recent decades, large-scale 30-m land cover maps still suffer from relatively low accuracy in terms of land cover type discrimination (especially for the vegetation and impervious types), due to limits in relation to the data, method, and design of the workflow. Land use and land cover maps provide fundamental information that has been used in different kinds of studies, ranging from climate change to city planning.
0 kommentar(er)
