A training sample refining method is proposed to improve the classification performance of very high-spatial resolution (VHR) remote sensing images. The proposed approach involves three major steps. First, for a given image, an initial sample set with a limited number for each class is prepared manually. Second, neighboring pixels around each available labeled pixel are gradually distinguished by an adaptive extension algorithm. When an iterative extension around the available pixel is terminated, the neighboring pixels that are within the extended region are taken into account as candidate training samples. The candidate training sample is then used to refine the signature of each initial sample. Third, when the whole available labeled pixels are scanned and processed pixel-by-pixel in the above manner, the revised training sample set is trained specially for a supervised classifier for classification. Three VHR remote sensing images with limited initial samples are used for evaluating different classifiers and advanced methods based on spatial–spectral features to investigate the feasibility and performance of the proposed approach. Higher classification performance and accuracies are obtained by our proposed approach with respect to the classification maps based on the initial training sample set and an existing method that improves the initial training set by a regular window.
Classification of multi-source data has recently gained significant attention, as accuracies can often be improved by incorporating complementary information extracted in single and multi-sensor scenarios. Supervised approaches to classification of multi-source remote sensing data are dependent on the availability of representative labeled data, which are often limited relative to the dimensionality of the data for training. To address this problem, in this paper, we propose a new framework in which active learning (AL) and semi-supervised learning (SSL) strategies are combined for multi-source classification of hyperspectral images. First, the spatial-spectral features are represented via the redundant discrete wavelet transform (RDWT). Then, the spatial context provided by the hierarchical segmentation algorithm (HSEG) in conjunction with an unsupervised pruning strategy is exploited to combine AL and SSL. Finally, SVM classification is performed due to the high dimensionality of the feature space. The proposed framework is validated with two benchmark hyperspectral data sets. Higher classification accuracies are obtained by the proposed framework with respect to other state-of-the-art active learning classification approaches.