Search

As an essential reprocessing method, dimensionality reduction (DR) can reduce the data redundancy and improve the performance of hyperspectral image (HSI) classification. A novel unsupervised DR framework with feature interpretability, which integrates both band selection (BS) and spatial noise reduction method, is proposed to extract low-dimensional spectral–spatial features of HSI. We proposed a new neighborhood grouping normalized matched filter (NGNMF) for BS, which can reduce the data dimension while preserving the corresponding spectral information. An enhanced 2-D singular spectrum analysis (E2DSSA) method is also proposed to extract the spatial context and structural information from each selected band, aiming to decrease the intraclass variability and reduce the effect of noise in the spatial domain. The support vector machine (SVM) classifier is used to evaluate the effectiveness of the extracted spectral–spatial low-dimensional features. Experimental results on three publicly available HSI datasets have fully demonstrated the efficacy of the proposed NGNMF-E2DSSA method, which has surpassed a number of state-of-the-art DR methods. [ABSTRACT FROM AUTHOR]

Singular spectral analysis (SSA) has recently been successfully applied to feature extraction in hyperspectral image (HSI), including conventional (1-D) SSA in spectral domain and 2-D SSA in spatial domain. However, there are some drawbacks, such as sensitivity to the window size, high computational complexity under a large window, and failing to extract joint spectral–spatial features. To tackle these issues, in this article, we propose superpixelwise adaptive SSA (SpaSSA), that is superpixelwise adaptive SSA for exploiting local spatial information of HSI. The extraction of local (instead of global) features, particularly in HSI, can be more effective for characterizing the objects within an image. In SpaSSA, conventional SSA and 2-D SSA are combined and adaptively applied to each superpixel derived from an oversegmented HSI. According to the size of the derived superpixels, either SSA or 2-D singular spectrum analysis (2D-SSA) is adaptively applied for feature extraction, where the embedding window in 2D-SSA is also adaptive to the size of the superpixel. Experimental results on the three datasets have shown that the proposed SpaSSA outperforms both SSA and 2D-SSA in terms of classification accuracy and computational complexity. By combining SpaSSA with the principal component analysis (SpaSSA-PCA), the accuracy of land-cover analysis can be further improved, outperforming several state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Accurate mapping of impervious surface distribution is important but challenging. Integrating optical and SAR data to improve urban impervious surface estimation has recently shown promising performance. Further investigation and development on this multisensory approach are conducted in this study. A novel multiple kernel learning (MKL) framework is proposed to integrate heterogeneous features from Landsat-8 and Sentinel-1A data effectively. A linearly weighted combination of basic kernels built using each group of features is learned as the optimal kernel, while the hyperparameters and the weight of each basic kernel are determined simultaneously by using the differential evolution algorithm. Then, the optimal kernel is embedded into the support vector regression algorithm, and the impervious surface abundance of the study area is estimated by applying the developed multiple kernel support vector regression (MKSVR) model. The impervious surface ground truth at a subpixel level is derived from a high-resolution image by means of object-oriented classification. The experimental results indicate that the synergistic use of optical and dual-pol SAR data by employing MKSVR achieves a noteworthy improvement for impervious surface estimation compared to that using optical image alone, the root mean square error is decreased by 4.30%, and the coefficient of determination (R2) is increased by 9.47%, and that the incorporation of optical and SAR does not guarantee the improved performance, simply stacking all features of multisource data into a vector is not a good choice, and the MKL is a powerful tool to apply as demonstrated by the experiments conducted in this study. [ABSTRACT FROM AUTHOR]

Balancing exploration and exploitation according to evolutionary states is crucial to meta-heuristic search (M-HS) algorithms. Owing to its simplicity in theory and effectiveness in global optimization, gravitational search algorithm (GSA) has attracted increasing attention in recent years. However, the tradeoff between exploration and exploitation in GSA is achieved mainly by adjusting the size of an archive, named K\textrm {best} , which stores those superior agents after fitness sorting in each iteration. Since the global property of K\textrm {best} remains unchanged in the whole evolutionary process, GSA emphasizes exploitation over exploration and suffers from rapid loss of diversity and premature convergence. To address these problems, in this paper, we propose a dynamic neighborhood learning (DNL) strategy to replace the K\textrm {best} model and thereby present a DNL-based GSA (DNLGSA). The method incorporates the local and global neighborhood topologies for enhancing the exploration and obtaining adaptive balance between exploration and exploitation. The local neighborhoods are dynamically formed based on evolutionary states. To delineate the evolutionary states, two convergence criteria named limit value and population diversity, are introduced. Moreover, a mutation operator is designed for escaping from the local optima on the basis of evolutionary states. The proposed algorithm was evaluated on 27 benchmark problems with different characteristic and various difficulties. The results reveal that DNLGSA exhibits competitive performances when compared with a variety of state-of-the-art M-HS algorithms. Moreover, the incorporation of local neighborhood topology reduces the numbers of calculations of gravitational force and thus alleviates the high computational cost of GSA. [ABSTRACT FROM PUBLISHER]