Recently, a series of collaborative representation (CR) methods have attracted much attention for hyperspectral images classification. In this article, two CR-based dynamic ensemble selection (DES) methods using multiview kernel collaborative subspace clustering (MVKCSC) and random subspace MVKCSC (RSMVKCSC) are proposed. In order to combine spectral and spatial information to construct a region of competence (RoC), the multiview learning strategy is used in the general DES method. Compared with traditional clustering methods, the MVC can more effectively utilize multifeature information. Moreover, a new method of constructing the Laplacian matrix using kernel CR coefficients is proposed for clustering based on subspace clustering and CR theory. This method is called MVKCSC, which can obtain the clustering results by using kernel CR self-representation coefficients. In addition, to increase the diversity of samples, the random subspace method (RSM) and MVKCSC are combined for RMVKCSC. Moreover, the algorithm can obtain better clustering results by constraining samples and features simultaneously. The effectiveness of the proposed methods is validated using three hyperspectral data sets with few samples. The experimental results show that both DES-MVKCSC and DES-RSMVKCSC outperform their single classifier counterparts. In particular, the proposed methods provide superior performance compared with the state-of-the-art DES methods.
30 August 2024 in IEEE Transactions on Geoscience and Remote Sensing
A novel approach is proposed in this study that combines superpixel (SP) segmentation and multi-classifier ensemble learning to address the limited availability of labeled samples in coastal wetland land cover classification. Firstly, the SP segmentation techniques is employed to partition unknown samples into multiple homogeneous regions, thereby facilitating the effective capture of spatial information pertaining to land cover. Subsequently, a multi-classifier ensemble learning strategy is employed within these regions to process the samples, effectively leading to a reduction in classification errors and an improvement in accuracy. To enhance the performance of semi-supervised learning (SSL), a sample iteration selection metric is introduced to optimize the training samples based on the consistency of sample types within homogeneous regions and the results obtained from the multi-classifier ensemble, thus enhancing the reliability of pseudo-labels. Additionally, multi-scale SP segmentation is utilized to augment the ensemble strategy for samples in order to reduce the necessity for hyperparameter adjustments and increase the automation and reliability of the model. Overall, the accuracy of coastal wetland classification is improved by this approach, while simultaneously mitigating the complexity of SSL in terms of hyperparameter tuning. The effectiveness of the proposed approach has been assessed through experiments conducted on three GF-5 hyperspectral images of coastal wetlands in China. In particular, the proposed methods provide superior performance compared with the state-of-the-art classification methods.
24 March 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Recently, kernel collaborative representation classification (KCRC) has shown its outstanding performance in dealing with the problem of linear inseparability in hyperspectral remote sensing image classification. Meanwhile, ensemble learning has attracted great attention in improving the performance of a single classifier. Aiming at the limitation of a single classifier, bagging algorithm based on KCRC(KCRC-bagging) is presented in this article. The KCRC-bagging method uses bootstrap to increase the diversity of base classifiers, thus improving the classification accuracy and generalization performance. In order to reduce the scale of ensemble, a diversity-driven multikernel collaborative representation classifier ensemble approach (DIV-KCRC) is proposed. DIV-KCRC verifies the effectiveness of the representation classifier with the pair of diversity measures, and classifiers with high accuracy and diversity are selected to improve the classification performance and efficiency of the ensemble system. Three real hyperspectral data sets were applied to prove the validity of the proposed method. The experimental results demonstrate that both KCRC-bagging and DIV-KCRC can yield better classification performance than their corresponding base classifiers. In particular, DIV-KCRC provides more reliable classification results than KCRC-bagging.
31 January 2023 in IEEE Transactions on Geoscience and Remote Sensing
Hyperspectral unmixing with tensor models has received great attention in recent years. A tensor-based decomposition method can effectively represent the structural feature of hyperspectral images; however, the obtained results may be physically uninterpretable. To overcome this limitation, a novel adaptive hypergraph regularized multilayer sparse tensor factorization (AHGMLSTF) algorithm is proposed. First, a modified hypergraph is incorporated into tensor factorization, and the modified hypergraph uses spectral angle distance (SAD) instead of Euclidean distance to construct hyperedges to better represent the joint spatial and spectral information. Then the hypergraph is constructed adaptively by hyperedges of k neighborhoods. Second, the concept of multi-layer decomposition is introduced to explore the hierarchical features of hyperspectral images, and a sparse constraint is imposed on each layer to make the unmixing results more consistent with the physical mechanism of mixed spectral pixels. With these constraints, the proposed method established a spectral-spatial joint tensor decomposition model that represents not only the local neighborhood similarity but also the heterogeneity of adjacent edges. Experiments on simulated data and real hyperspectral data demonstrate the effectiveness of the proposed method.
19 August 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Recently, collaborative representation classifiers have been extensively studied as an essential method for the hyperspectral image. However, how to comprehensively utilize the classification advantages of multiple collaborative classifiers has not been well investigated. In this article, two new dynamic ensemble learning methods using local weighted residual (LWR-DEL) and double-weighted residual (DWR-DEL) of multicollaborative representation classifiers are proposed. First, the dynamic ensemble learning method based on clustering is utilized to introduce prior knowledge for the collaborative representation classifier. Then, with prior knowledge, the local weights of each classifier for a different region of competence are obtained. To consider the global information of hyperspectral data, the K-nearest neighbor algorithm is adopted to achieve validation samples with global information. The global weights for each classifier can be obtained and then used to constrain the locally weighted residuals. Similar to LWR-DEL, the global information is also used to constrain residual, and then double-weighted constrained residual fusion obtains the final classifier result. The effectiveness of the proposed methods is validated using three hyperspectral data sets. The experimental results show that both LWR-DEL and DWR-DEL outperform their single-classifier counterparts. In particular, the proposed methods provide superior performance compared with the state-of-the-art methods.
The study of vegetation phenology changes is important because it is a sensitive indicator of climate change, affecting the exchange of carbon, energy and water fluxes between the land and the atmosphere. Previous studies have focused on the effects of climatic factors among environmental factors on vegetation phenology, thus the effects of non-climatic factors among environmental factors have not been well quantified. This study endeavors to scrutinize the spatiotemporal inconsistency in the start-of-season (SOS) and the end-of-season (EOS) on the Tibetan Plateau (TP) and to quantify the effects of environmental factors on phenology. To this end, the Moderate-resolution Imaging Spectroradiomater (MODIS) Normalized Difference Vegetation Index (NDVI) data from 2001 to 2018 and four common used methods were employed to extract SOS and EOS, and the site data was used to select the most appropriate phenology results. The Geodetector model was used to assess and measure the explanatory power of different environmental factors. The research results indicate that temperature exerts a more substantial impact on phenology than precipitation on TP. non-climatic factors such as longitude, latitude, and elevation are more influential in determining the distribution of phenological trends than climatic factors. Among these non-climatic factors, latitude has the most prominent effect on the trends of SOS. Furthermore, non-climatic factors exhibit a stronger effect on SOS, whereas EOS is more susceptible to climatic factors and less influenced by non-climatic factors. These discoveries bear great significance in comprehending the intricate outcomes of regional changes on vegetation phenology and enhancing phenology models.