Search

To generate a high-spatial-resolution hyperspectral (HHS) image from a high-spatial-resolution multispectral (HMS) image, both spatial information and spectral information should be considered simultaneously if we want to build a more accurate mapping from HMS to HHS. To this end, a spectral and spatial jointed spectral super-resolution method is proposed in this letter using an end-to-end learning strategy for each subspace with the cluster-based multibranch backpropagation neural network (BPNN). More specifically, in addition to the spectra similarity, a modified superpixel segmentation is introduced to jointly take spatial contextual information into account, and a new framework with it is given. Comparisons on the Columbia University Automated Vision Environment (CAVE) data set show that our proposed method outperforms other relative state-of-the-art methods more than 0.3 in the root mean squared error (RMSE) and more than 1.0 in the spectral angle mapper (SAM) index. Especially, an exemplary application is demonstrated using the synchronized observation data collected by the multispectral and hyperspectral sensors mounted on the HJ-1A satellite at the same time.

Anomalies in remote sensing images are generally reflected in two aspects of spatial and spectral ones, as for the anomaly detection of sea surface using multispectral or hyperspectral images, spectral information is more important. To this end, a novel spectral anomaly detection method based on dictionary optimization is proposed in this letter. More specifically, the normal scene is first defined to distinguish the anomaly. Then, without any assumption about the distribution of anomaly, a spectral dictionary is formulated and derived theoretically with optimization to express the normal scenes. Using the sparse and low-rank constraints, the alternating direction method of multiplier (ADMM) is employed to solve the above optimization in the spectral domain. Finally, for a given sea-surface image to be detected, the error matrix that cannot be fully expressed by the optimized spectral dictionary is regarded as anomalies. It shows certain generality for various kinds of spectral anomalies on the sea surface. Taking multispectral images obtained by the HY-1C satellite as an example, comparisons with related state-of-the-art methods demonstrate that our proposed method achieves the best anomaly detection performance not only for oil-spill pollution but also for algae pollution.

High-spatial hyperspectral (HH) image reconstruction using both high-spatial multispectral (HM) image and low-spatial hyperspectral (LH) image over the same scene is widely used in many real applications. Nevertheless, the pair of HM image and LH image over the same scene is hard to obtain. To solve this problem, a new HH image reconstruction method using spectral library-based dictionary learning (named as HIRSL) is proposed in this paper, only from one HM image. The above reconstruction problem is formulated in the framework of sparse representation, as an estimation of the band matching matrix, the spectral dictionary, and the sparse coefficients. More specifically, a band matching method is proposed for mapping the common spectral library to a specific spectral library corresponding to the reconstructed HH image in spectral domain. Then, an efficient spectral dictionary learning method is proposed for the construction of spectral dictionary using the matched specific spectral library, which avoids the dependence of the LH image over the same scene. Finally, the sparse coefficients of the HM image with respect to the learned spectral dictionary are estimated using the alternating direction method of multipliers without nonnegative constraint. Comparison results on simulated and real data sets with the relative state-of-the-art methods demonstrate that even only using one HM image, our proposed method achieves a comparable reconstruction quality of high-spatial hyperspectral image both in spatial and spectral domains.

Land-cover classification in polarimetric synthetic aperture radar images is a vital technique that has been developed for years. The Wishart distribution, which the polarimetric coherence matrix obeys, has been researched to design the well-known Wishart classifier. This model is appropriate for homogeneous scenes, but it usually fails in reality when a category consists of several subcategories or clusters. Therefore, a simple but powerful sample-merging strategy is proposed to generate representative subcenters, based on a dissimilarity measure. In addition, a weighted likelihood-ratio criterion is also proposed to further improve the performance of the Wishart distribution-based classification, based on the Wishart test statistic. Two experiments on EMISAR and UAVSAR data sets confirm that combining the proposed strategies can achieve better results than can the Wishart classifier and the other existing methods.

Cloud and snow detection has significant remote sensing applications, while they share similar low-level features due to their consistent color distributions and similar local texture patterns. Thus, accurately distinguishing cloud from snow in pixel level from satellite images is always a challenging task with traditional approaches. To solve this shortcoming, in this letter, we proposed a deep learning system to classify cloud and snow with fully convolutional neural networks in pixel level. Specifically, a specially designed fully convolutional network was introduced to learn deep patterns for cloud and snow detection from the multispectrum satellite images. Then, a multiscale prediction strategy was introduced to integrate the low-level spatial information and high-level semantic information simultaneously. Finally, a new and challenging cloud and snow data set was labeled manually to train and further evaluate the proposed method. Extensive experiments demonstrate that the proposed deep model outperforms the state-of-the-art methods greatly both in quantitative and qualitative performances.

Hyperspectral images (HSIs) usually contain hundreds of spectral bands. When they are used for classification tasks, HSIs may suffer from the curse of high dimensionality. To address this problem, the essential procedures of dimension reduction and feature extraction (FE) are employed. In this letter, we propose an FE method for HSIs using low-rank representation with neighborhood preserving regularization (LRR_NP). The proposed method can simultaneously employ locally spatial similarity and the spectral space structure, which comprises a union of multiple low-rank subspaces. The framework of LRR can structurally represent the union structure of a spectral space. Because spatial neighbor pixels always share high similarity in a feature space, an NP regularization item is introduced into the framework of LRR to consider the locally spatial correlation. Classification experiments are conducted on real HSI data sets; the results demonstrate that the features that are extracted by LRR_NP are more discriminative than the state-of-art methods, including both unsupervised methods and supervised methods.

Hyperspectral images (HSIs) have been used in a wide range of fields, such as agriculture, food safety, mineralogy, and environment monitoring, but being corrupted by various kinds of noise limits its efficacy. Low-rank representation (LRR) has proved its effectiveness in the denoising of HSIs. However, it just employs local information for denoising, which results in ineffectiveness when local noise is heavy. In this paper, we propose an approach of group low-rank representation (GLRR) for the HSI denoising. In our GLRR, a corrupted HSI is divided into overlapping patches, the similar patches are combined into a group, and the group is reconstructed as a whole using LRR. The proposed method enables the exploitation of both the local similarity within a patch and the nonlocal similarity across the patches in a group simultaneously. The additional nonlocally similar patches can bring in extra structural information to the corrupted patches, facilitating the detection of noise as outliers. LRR is applied to the group of patches, as the uncorrupted patches enjoy intrinsic low-rank structure. The effectiveness of the proposed GLRR method is demonstrated qualitatively and quantitatively by using both simulated and real-world data in experiments.

A number of earthquakes have occurred in recent years, posing a challenge to Earth observation techniques. Owing to the all-weather response capability, synthetic aperture radar (SAR) has become a key tool for collapse interpretation. As the requirement for multitemporal data is usually not satisfied in practice, interpretation using only postevent SAR imagery is indispensable for emergency rescue. Despite being found that texture has a relationship with building damage, only a few texture measures have been adopted using simple threshold criteria. To fully explore the spatial contextual information in very high resolution (VHR) SAR images, there are two questions that should be discussed: 1) Which textural features are helpful for collapse assessment? 2) How do diverse imaging configurations influence the interpretation? In response, five texture descriptors are used for the stricken area texture extraction in this paper, and a random forests classifier is applied to identify the building collapse level. It was found that most of the gray-level histogram features perform quite well, and several other primitive features, such as the isolated bright points originating from scattered rubble, can also help to discriminate different collapse levels. Moreover, the experiments with data from the Yushu earthquake of April 14, 2010, indicated that spatial detail quality is the key for texture interpretation, and the span image can be considered as an appropriate choice when VHR PolSAR data are available. The optimal interpretation results (with an overall accuracy of 84.7%) were obtained using the 122 proposed measures in a VHR X-band image.

Furfural content in oil is a valuable indicator of cellulose paper degradation and is widely utilized in aging assessment for power transformers. However, with the same aging degree of insulation paper, the actual furfural content in oil is influenced by temperature because furfural partitioning behavior in the oil-paper insulation system of power transformers changes with temperature. Thus, correction of the temperature effect on furfural partitioning is crucial for accurate assessment of the aging of power transformers. In this research, oil-paper samples with different furfural contents were prepared through an accelerated thermal aging test. A furfural equilibrium experiment was conducted at different temperatures to construct a furfural partitioning diagram. The mass fraction of furfural in oil and paper was calculated. Results showed that the mass fraction of furfural in oil increases with temperature rising and aging deepening, which means that furfural tends to migrate from paper to oil at high temperatures and deep aging conditions. The change in furfural partitioning between oil and paper at different temperatures causes a deviation in paper aging assessment. To correct the temperature effect on furfural partitioning, a furfural correction factor was developed to normalize furfural contents in oil at different temperatures to a reference temperature. The furfural correction factor was verified by experimental data and then introduced into the relation between degree of polymerization of paper and furfural content of oil. Verification results showed that the corrected equation can enhance the accuracy of paper aging estimation at different temperatures. The findings of this work indicated temperature effect on furfural partitioning should be considered when determining the furfural thresholds and evaluating the aging condition of power transformers.

Furfural analysis is considered as a reliable method to estimate aging of cellulose insulation paper and is widely applied in assessing the condition of field transformers. However, the actual concentration of furfural in insulating oil is influenced by oil replacement, and the correction method is seldom studied. In this research, an accelerated thermal aging test of oil-paper samples was conducted at 130 °C for 35 days. Insulating oil was replaced at early, middle, and late aging stages to investigate furfural loss during the oil replacement process and its effects on assessing the aging of insulation paper. Results showed that furfural in oil obviously declined after oil replacement, which caused a severe error in paper aging evaluation. To correct furfural loss, the furfural correction factor, which is defined as the ratio of the furfural content in oil after oil replacement to the furfural content before oil replacement, was introduced into the furfural analysis method. The parameters and influencing factors of the furfural correction function were researched. The furfural correction function was verified using experimental data obtained under laboratory conditions and field data collected from 44 in-service transformers. The results showed that the furfural correction function effectively corrects furfural loss during oil replacement and improves the accuracy of estimating paper aging. Finally, the furfural correction function was extended to the operating conditions of field transformers.

In this letter, a comprehensive study of the mapping of building collapse levels by the use of postearthquake synthetic aperture radar (SAR) images is addressed. Although previous studies have successfully quantified the collapse level by the use of postevent SAR, the types of features that are of benefit to the final accuracy still remain unknown. This letter takes the Yushu earthquake as a case study to contribute in two key areas. First, the Chinese dual-band airborne SAR mapping system (CASMSAR), which collected very-high-resolution X-band and P-band images (0.50 and 1.1 m, respectively) by interferometric and polarimetric modes, is comprehensively evaluated for the first time. Second, to discriminate intact and fallen structures, multiconfiguration SAR data features are analyzed, including 40 polarimetric, 3 interferometric, and 138 texture features. Furthermore, a random-forest decision framework is introduced to quantify the importance score of each feature and to improve the discrimination accuracy. The CASMSAR experiment results indicate that the texture is recommended as a powerful input to quantify the extent of building collapse in Yushu.

Superresolution mapping can predict the spatial location of land cover classes within mixed pixels based on the spatial dependence assumption. We propose a novel superresolution mapping method via multidictionary-based sparse representation, which is robust to noise in both the learning and class-allocation process. In the proposed method, the subpixel number belonging to each class is obtained according to the degree of spectral distortion, and the distribution modes of different classes are treated discriminatorily. The subpixel classification is performed according to the normalized reconstruction errors by the learned multiple distribution dictionaries. The experimental results show that the proposed method has improved accuracy and robustness for real imagery.

A super-resolution (SR) method based on compressive sensing (CS), structural self-similarity (SSSIM), and dictionary learning is proposed for reconstructing remote sensing images. This method aims to identify a dictionary that represents high resolution (HR) image patches in a sparse manner. Extra information from similar structures which often exist in remote sensing images can be introduced into the dictionary, thereby enabling an HR image to be reconstructed using the dictionary in the CS framework. We use the K-Singular Value Decomposition method to obtain the dictionary and the orthogonal matching pursuit method to derive sparse representation coefficients. To evaluate the effectiveness of the proposed method, we also define a new SSSIM index, which reflects the extent of SSSIM in an image. The most significant difference between the proposed method and traditional sample-based SR methods is that the proposed method uses only a low-resolution image and its own interpolated image instead of other HR images in a database. We simulate the degradation mechanism of a uniform 2 × 2 blur kernel plus a downsampling by a factor of 2 in our experiments. Comparative experimental results with several image-quality-assessment indexes show that the proposed method performs better in terms of the SR effectivity and time efficiency. In addition, the SSSIM index is strongly positively correlated with the SR quality.