Search

As the most important city in China, Beijing has experienced an economic soar, large-scale population growth and eco-environment changes in the last 20 years. Evaluating climate- and human-induced vegetation changes could reveal the relationship of vegetation-climate-human activities and provide important insights for the coordination of economic growth and environmental protection. Based on a long-term MODIS vegetation index dataset, meteorological data (temperature, precipitation) and impervious surface data, the Theil-Sen regression and the Mann-Kendall method are used to estimate vegetation change trends in this study and the residual analysis is utilized to distinguish the impacts of climate factors and human activities on vegetation restoration and degradation from 2000 to 2019 in Beijing. Our results show that the increasing vegetation areas account for 80.2% of Beijing. The restoration of vegetation is concentrated in the urban core area and mountainous area, while the degradation of vegetation is mainly concentrated in the suburbs. In recent years, the vegetation in most mountainous areas has changed from restoration to significant restoration, indicating that the growth of mountain vegetation has continued to restore. We also found that in the process of urban expansion, vegetation browning occurred in 53.1% of the urban built-up area, while vegetation greening occurred in the remaining area. We concluded that precipitation is the main climatic factor affecting the growth of vegetation in Beijing's mountainous areas through correlation analysis. Human activities have significantly promoted the vegetation growth in the northern mountainous area thanks to the establishment of environmental protection areas. The negative correlation between vegetation and the impervious surface tends to gradually expand outwards, which is consistent with the trend of urban expansion. The positive correlation region remains stable, but the positive correlation is gradually enhanced. The response of vegetation to urbanization demonstrated a high degree of spatial heterogeneity. These findings indicated that human activities played an increasingly important role in influencing vegetation changes in Beijing. [ABSTRACT FROM AUTHOR]

In the process of urbanization, water bodies bear considerable anthropogenic pressure, resulting in a reduction of their surface area in most instances. Nevertheless, in contrast to many other regions, the Lixiahe region in Jiangsu Province, located in China's eastern plain, has experienced a continuous expansion of water bodies over the past few decades amid rapid urbanization. Using Landsat images spanning from 1975 to 2023, this study analyzed changes in water resources and the growth of impervious surfaces during urbanization. The findings revealed that the area of impervious surfaces in the region increased from 227.1 km2 in 1975 to 1883.1 km2 in 2023. Natural wetland suffered significant losses, declining from 507.2 km2 in 1975 to near disappearance by the year 2000, with no significant recovery observed thereafter. Simultaneously, the water area expanded from 459.3 km2 in 1975 to 2373.1 km2 in 2023, primarily propelled by the significant contribution of aquaculture ponds, accounting for 2175.0 km2 or 91.7% of the total water area. Driver analysis revealed that these changes were found to be influenced by factors such as population, economy, demand, and policies. However, alongside the economic development brought by urbanization, negative impacts such as lake shrinkage, eutrophication, and increased flood risks have emerged. The Lixiahe region, as a relatively underdeveloped part of Jiangsu Province, faces the challenge of striking a balance between economic growth and environmental conservation. [ABSTRACT FROM AUTHOR]

Denoising serves as a critical preprocessing step for the subsequent analysis of the hyperspectral image (HSI). Due to their high computational efficiency, low-rank-based denoising methods that project the noisy HSI into a low-dimensional subspace identified by certain criteria have gained widespread use. However, methods employing second-order statistics as criteria often struggle to retain the signal of the small targets in the denoising results. Other methods utilizing high-order statistics encounter difficulties in effectively suppressing noise. To tackle these challenges, we delve into a novel criterion to determine the projection subspace, and propose an innovative low-rank-based method that successfully preserves the spectral characteristic of small targets while significantly reducing noise. The experimental results on the synthetic and real datasets demonstrate the effectiveness of the proposed method, in terms of both small-target preservation and noise reduction. [ABSTRACT FROM AUTHOR]

The extraction of photovoltaic (PV) panels from remote sensing images is of great significance for estimating the power generation of solar photovoltaic systems and informing government decisions. The implementation of existing methods often struggles with complex background interference and confusion between the background and the PV panels. As a result, the completeness and edge clarity of PV panel extraction results are compromised. Moreover, most previous studies have overlooked the unique color characteristics of PV panels. To alleviate these deficiencies and limitations, a method for extracting photovoltaic panels from high-resolution optical remote sensing images guided by prior knowledge (PKGPVN) is proposed. Firstly, aiming to address the problems related to missed extractions and background misjudgments, a Photovoltaic Index (PVI) based on visible images in the three-band is constructed to serve as prior knowledge to differentiate between PV panels and non-PV panels. Secondly, in order to strengthen information interaction between shallow features and deep features and enhance the accuracy and integrity of results, a Residual Convolution Hybrid Attention Module (RCHAM) is introduced into the skip-connection of the encoding–decoding structure. Finally, for the purpose of reducing the phenomenon of blurred edges, a multilevel Feature Loss (FL) function is designed to monitor the prediction results at different scales. Comparative experiments are conducted with seven methods, including U-Net, on publicly available datasets. The experimental results show that our PKGPVN achieves superior performance in terms of evaluation metrics such as IoU (above 82%), Precision (above 91%), Recall (above 89%), and F1-score (above 90%) on the AIR-PV dataset. Additionally, the ablation experiments illustrate the effectiveness of our key parts. The proposed method reduces the phenomena of missed extractions and background misjudgments effectively while producing highly accurate results with clear boundaries. [ABSTRACT FROM AUTHOR]

Thick cloud and shadows have a significant impact on the availability of optical remote sensing data. Although various methods have been proposed to address this issue, they still have some limitations. First, most approaches rely on a single clear reference image as complementary information, which becomes challenging when the target image has large missing areas. Secondly, the existing methods that can utilize multiple reference images require the complementary data to have high temporal correlation, which is not suitable for situations where the difference between the reference image and the target image is large. To overcome these limitations, a flexible spatiotemporal deep learning framework based on generative adversarial networks is proposed for thick cloud removal, which allows for the use of three arbitrary temporal images as references. The framework incorporates a three-step encoder that can leverage the uncontaminated information from the target image to assimilate the reference images, enhancing the model's ability to handle reference images with diverse temporal differences. A series of simulated and real experiments on Landsat 8 and Sentinel 2 data is performed to demonstrate the effectiveness of the proposed method. The proposed method is especially applicable to small/large-scale regions with reference images that are significantly different from the target image. [ABSTRACT FROM AUTHOR]

Target detection is an important area in the applications of hyperspectral remote sensing. Due to the full use of information of the target and background, target detection algorithms based on the statistical characteristics of an image are always occupy a dominant position in the field of hyperspectral target detection. From the perspective of statistical information, we firstly presented detailed discussions on the key factors affecting the target detection results, including data origin, target size, spectral variability of target, and the number of bands. Further, we gave the corresponding strategies for several common situations in the practical target detection applications. [ABSTRACT FROM AUTHOR]

The characteristics of high dimensionality, strong band correlation, and high information redundancy make band selection become a necessary step for efficient processing of hyperspectral images. In this paper, a new band selection method based on connection centre evolution (CCE) is proposed, named n -nearest neighbour CCE band selection (NNCCEBS). First, according to CCE, we measure the band similarity under different observation scales by iteratively calculating the connectivity at different scales. Therefore, NNCCEBS can achieve multi-scale band selection, and is able to complete it at one time. Next, to avoid the selected bands being aggregated, an n -nearest neighbour similarity matrix is introduced, which only retains the connectivity of n -nearest bands for a band. By doing so, the new method is less sensitive to the parameter settings, and can select more accurate band centres. Experiments on real hyperspectral datasets prove the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Clouds often contaminate remote sensing images, which leads to missing land feature information and subsequent application degradation. Low-rank tensor completion has shown great potential in the reconstruction of multi-temporal remote sensing images. However, existing methods ignore different low-rank properties in the spatial and temporal dimensions, such that they cannot utilize spatial and temporal information adequately. In this paper, we propose a new frequency spectrum-modulated tensor completion method (FMTC). First, remote sensing images are rearranged as third-order spatial–temporal tensors for each band. Then, Fourier transform (FT) is introduced in the temporal dimension of the rearranged tensor to generate a spatial–frequential tensor. In view of the fact that land features represent low-frequency components and fickle clouds represent high-frequency components in the time domain, we chose adaptive weights for the completion of different low-rank spatial matrixes, according to the frequency spectrum. Then, Invert Fourier Transform (IFT) was implemented. Through this method, the joint low-rank spatial–temporal constraint was achieved. The simulated data experiments demonstrate that FMTC is applicable on different land-cover types and different missing sizes. With real data experiments, we have validated the effectiveness and stability of FMTC for time-series remote sensing image reconstruction. Compared with other algorithms, the performance of FMTC is better in quantitative and qualitative terms, especially when considering the spectral accuracy and temporal continuity. [ABSTRACT FROM AUTHOR]

The dynamic variation in the water surfaces of the river networks within the Qinghai-Tibet Plateau affects the water resource availability for downstream ecosystems and human activities. Small rivers (with a river width less than 30 m) are an important component of this network, but are difficult to map in the Qinghai-Tibet Plateau. Firstly, the width of most rivers is very narrow, at around 20 m, which appears as only one or two pixels in Sentinel-2 images and thus is susceptible to salt-and-pepper noise. Secondly, local mountain shadows, cloud shadows, and snow pixels have spectral characteristics similar to those of rivers, leading to misclassification. Therefore, we propose an automated small river mapping (ASRM) method based on Sentinel-2 imagery to address these two difficulties. A preprocessing procedure was designed to remove the salt-and-pepper noise and enhance the linear characteristic of rivers with specific widths. A flexible digital elevation model (DEM)-based post-processing was then imposed to remove the misclassifications caused by mountain shadows, cloud shadows, and snow pixels. The ASRM results achieved an overall accuracy of 87.5%, outperforming five preexisting remote sensing-derived river network products. The proposed ASRM method has shown great potential for small river mapping in the entire Qinghai-Tibet Plateau. [ABSTRACT FROM AUTHOR]

Automatic detection of information changes in the visual environment is crucial for individual survival. Researchers use the oddball paradigm to study the brain's response to frequently presented (standard) stimuli and occasionally presented (deviant) stimuli. The component that can be observed in the difference wave is called visual mismatch negativity (vMMN), which is obtained by subtracting event-related potentials (ERPs) evoked by the deviant from ERPs evoked by the standard. There are three hypotheses to explain the vMMN. The sensory fatigue (or refractoriness) hypothesis considers that weakened neural activity caused by repetition results in decreased ERPs of the standard. The memory trace hypothesis proposes that vMMN results from increased responses to the deviant. The predictive coding hypothesis attributes the difference to enhanced responses for deviants and suppression for standards. However, when distinguishing between these effects, previous researchers did not consider the effect of low-level features on the vMMN. In this experiment, we used face sequences composed of different emotions (e.g., neutral and fearful face) and presented an oddball sequence, a reverse oddball sequence, and an equiprobable sequence to participants. The deviant of the oddball sequence was subtracted from the standard of the oddball sequence, the reverse oddball sequence, and the same type of stimulus of the equiprobable sequence to get oddball-vMMN (vMMN1), reverse oddball-vMMN (vMMN2), and equiprobable-vMMN (vMMN3), respectively. The results showed no significant difference between vMMN2 and vMMN3 in 100–350 ms following stimulus onset, while the vMMN effect was significant, indicating that the probability of the standard did not affect vMMN, which supported the memory trace hypothesis. Additionally, the fearful-related vMMN were more negative than the neutral-related vMMN within the range of 100–150 ms, suggesting a negative bias. We analyzed the source location of different vMMNs. There was no significant difference in brain regions between different vMMNs. Time-frequency analysis showed that the deviant had stronger theta-band oscillatory than the standard (visual mismatch oscillatory responses, vMORs). However, there was no difference between vMORs2 and vMORs3, indicating that vMORs reflect an enhanced response to the deviant in terms of neural oscillation, supporting the memory trace hypothesis. [ABSTRACT FROM AUTHOR]

Individuals can perceive the mean emotion or mean identity of a group of faces. It has been considered that individual representations are discarded when extracting a mean representation; for example, the "element-independent assumption" asserts that the extraction of a mean representation does not depend on recognizing or remembering individual items. The "element-dependent assumption" proposes that the extraction of a mean representation is closely connected to the processing of individual items. The processing mechanism of mean representations and individual representations remains unclear. The present study used a classic member-identification paradigm and manipulated the exposure time and set size to investigate the effect of attentional resources allocated to individual faces on the processing of both the mean emotion representation and individual representations in a set and the relationship between the two types of representations. The results showed that while the precision of individual representations was affected by attentional resources, the precision of the mean emotion representation did not change with it. Our results indicate that two different pathways may exist for extracting a mean emotion representation and individual representations and that the extraction of a mean emotion representation may have higher priority. Moreover, we found that individual faces in a group could be processed to a certain extent even under extremely short exposure time and that the precision of individual representations was relatively poor but individual representations were not discarded. [ABSTRACT FROM AUTHOR]

Recently, the volume-gradient-based band selection (VGBS) method has attracted more and more attention in the field of band selection. It is a ranking-based unsupervised algorithm which applies the sequential backward selection strategy to successively remove the most abundant band. The key finding of VGBS is that the band redundancy corresponds to the volume gradient matrix with respect to hyperspectral images. However, we have found that VGBS requires to update the gradient matrix after each band removal, which includes the calculation of the matrix inverse, determinant, and multiplication, and thus is time-consuming when the number of bands is large. In this letter, we first find that the norm of the row of the gradient matrix has a one-to-one correspondence to the diagonal element of the covariance matrix of the image. Further, we develop a recursive formula to calculate the inverse of the covariance matrix. The experimental results show the effectiveness of the method, i.e., we can reduce the computational complexity of VGBS with an order of magnitude. [ABSTRACT FROM AUTHOR]

As one of the most important algorithms in target detection, constrained energy minimization (CEM) has been widely used and developed in recent years. However, it is easy to verify that the target detection result of CEM varies with the data origin, which is apparently unreasonable since the distribution of the target of interest is objective and, therefore, unrelated to the selection of data origin. The clever eye (CE) algorithm tries to solve this problem by adding the data origin as a new variable from the perspective of the filter output energy. However, due to the nonconvexity of the objective function, CE can only obtain locally optimal solutions by using the gradient ascent method. In this article, we find a striking conclusion that there exists an analytical solution for CE that corresponds to the solution of a linear equation and further prove that all the solutions of the linear equation are globally optimal. [ABSTRACT FROM AUTHOR]

When perceivers view multiple facial expressions shown concurrently, they can quickly and precisely extract the mean emotion from the set. Yet it is not clear how many faces in the set contribute to summary judgments, and how the variance among them influences this process. To address these questions, we used the subset manipulation and varied emotion variance of faces in the sets across three experiments. Sets containing sixteen faces, or a subset of faces randomly selected from the sixteen-face display were presented, and participants judged the average emotion of each face set on a continuous scale. Results showed that when emotion variance was relatively large (Experiments 1 & 2), only two faces in the set contributed to ensemble representations. In Experiment 3 where the emotion variance was smaller, around three to four faces were likely sampled. However, when directly comparing results from Experiments 2 and 3, there was no strong evidence supporting the impact of variance in averaging efficiency. Altogether, these new results suggest that the process of averaging multiple emotional facial expressions can be explained by capacity-limited subsampling. The claim that ensemble representations are capacity unlimited or can overcome the bottlenecks in visual perception might need to be reconsidered. [ABSTRACT FROM AUTHOR]

Building detection in high spatial resolution optical remote sensing images is important for city planning, navigation, population estimation and many other applications. Although many methods have been proposed, building detection is still a challenging problem due to complex scenes and small or arbitrarily orientated buildings. Moreover, most algorithms detect rotated buildings with horizontal bounding boxes leading to many background pixels being preserved in the final detection, which is not beneficial for post-processing. To address these problems, we present the U-Rotation Detection Network (U-RDN), which can effectively detect buildings with arbitrarily orientated detection bounding boxes. First, the U-Rotation Region Proposal Network (U-RRPN) is proposed to generate rotated proposals through rotated anchors. Then, a Rotation Fast-Region Convolutional Neural Network (RFast-RCNN) is performed, which extracts fixed-size features from rotated proposals and utilizes them to obtain fine-detections. For extracting fixed-size features from rotated proposals, we propose Auto Mask Region-Of-Interest Align (AM-ROI Align). The AM-ROI Align not only reduces abundant noise but also preserves the proper information of an object in ROI. Experimental results using the public building dataset, SpaceNet, show that our method can detect buildings with skewed bounding boxes and has a state-of-the-art performance compared with other algorithms. [ABSTRACT FROM AUTHOR]

The super-resolution problem for hyperspectral images is currently one of the most challenging topics in remote sensing. Increasingly effective methods have been presented to solve this ill-posed problem under certain circumstances. In this article, we propose a new approach named the spectral-spatial network (SSN), which can effectively increase spatial resolution while keeping spectral information. The SSN consists of two sections: a spatial section and a spectral section that contribute to enhancing spatial resolution and preserving spectral information, respectively. The spatial section is proposed to learn end-to-end mapping between single-band images, from low-resolution and high-resolution hyperspectral images. In this section, we enhance the traditional sub-pixel convolutional layer by adding a maximum variance principle that can realize nonlinear fitting through piecewise linearization. The spectral section aims to fine-tune spectral caves to keep the spectral signature with a spectral angle error loss function. In order to make the SSN converge quickly, we also develop a corresponding three-step training method. The experimental results on two databases, with both indoor and outdoor scenes, show that our proposed method performs better than the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We examined the processing capacity and the role of emotion variance in ensemble representation for multiple facial expressions shown concurrently. A standard set size manipulation was used, whereby the sets consisted of 4, 8, or 16 morphed faces each uniquely varying along a happy-angry continuum (Experiment 1) or a neutral-happy/angry continuum (Experiments 2 & 3). Across the three experiments, we reduced the amount of emotion variance in the sets to explore the boundaries of this process. Participants judged the perceived average emotion from each set on a continuous scale. We computed and compared objective and subjective difference scores, using the morph units and post-experiment ratings, respectively. Results of the subjective scores were more consistent than the objective ones across the first two experiments where the variance was relatively large, and revealed each time that increasing set size led to a poorer averaging ability, suggesting capacity limitations in establishing ensemble representations for multiple facial expressions. However, when the emotion variance in the sets was reduced in Experiment 3, both subjective and objective scores remained unaffected by set size, suggesting that the emotion averaging process was unlimited in these conditions. Collectively, these results suggest that extracting mean emotion from a set composed of multiple faces depends on both structural (attentional) and stimulus-related effects. [ABSTRACT FROM AUTHOR]

The linear operator has been widely used to detect targets of interest in multispectral/hyperspectral images, and is usually able to achieve good performance when the target is linearly separable from the background. However, when dealing with a complex scene, it is hard to find a single projection direction, along which the target can be well distinguished from all the background objects. Therefore, we propose a piecewise linear strategy (PLS) for target detection, which is based on the assumption that the desired target is generally linearly separable from each background object. PLS first divides the whole background into several partitions, and then detects the individual target for each partition by using a commonly used linear detector. Experiments with simulated and real-world multispectral/hyperspectral images show that PLS can acquire a nonlinear detection result and can outperform state-of-the-art target detection operators. [ABSTRACT FROM PUBLISHER]

Based on the multiplicative update rule of nonnegative matrix factorization (NMF), we add the nonnegative constraint of endmember matrix to the objective function of iterative constrained endmembers (ICE), and propose a simple multiplicative update rule for ICE, named NMF-ICE. Our method avoids the use of quadratic programming method in ICE, therefore can greatly improve the computational efficiency. Experiments using both simulated and real hyperspectral data show that NMF-ICE is effective in endmember generation. [ABSTRACT FROM AUTHOR]

The constrained energy minimization (CEM) and matched filter (MF) are two most frequently used target detection algorithms in the remotely sensed community. In this paper, we first introduce an augmented CEM (ACEM) by adding a N-dimensional band consisting of 1’s. According to a recently published conclusion that CEM can always achieve a better performance by adding any linearly independent bands, ACEM is better than CEM. Further, we prove that ACEM is mathematically equivalent to MF. As a result, we can conclude that the classical matched filter (MF) is always superior to the CEM operator. [ABSTRACT FROM PUBLISHER]

In the field of unsupervised band selection, both robustness and efficiency are of great importance. In this article, we propose a new unsupervised band selection method termed graph representation based band selection (GRBS), which is expected to be insensitive to noisy bands and computationally inexpensive. In GRBS, bands are treated as the nodes of graph in high-dimensional space and centres of the band clusters are considered as the ideal choice. Interestingly, different from other clustering-based band selection methods, GRBS does not involve band clustering. Instead, it employs an easily computed criterion function to select the desired bands, which greatly improves the efficiency. The experiments demonstrate that GRBS has a promising performance and outperforms the compared methods in terms of both accuracy and efficiency. [ABSTRACT FROM PUBLISHER]

Simplex volume is the most commonly used parameter for endmember extraction. However, when outliers exist in the image, the maximum-volume-criterion (MVC)-based methods tend to extract them as endmembers. Those outlier endmembers could be either physically meaningless or not representative enough for prevalent land covers. This is the biggest bottleneck preventing MVC-based methods from being extended from theoretical analysis to practical applications. This is mainly due to the limitation of the simplex volume formula itself, which is only determined by simplex vertices and completely ignoring the statistics of the data cloud. Usually, the simplex with vertices containing outliers has a larger volume than the one with vertices only containing true endmembers; thus, outliers are more favorably extracted as endmembers. Usually, the outliers are distributed in the direction of low information content. When extracted endmembers contain outliers, the overall information content (OIC) of the data cloud projected onto the endmember subspace will be definitely reduced. Motivated by this fact, we present the concept of statistical volume and develop a new endmember extraction method, which is named statistical volume analysis (SVA). The algorithm simultaneously utilizes the geometrical property of the simplex and the statistical characteristic of the projected data in the endmember subspace. Therefore, SVA not only can find a simplex with a large volume but also can get a large OIC of the projected data. Experiments with both simulated and real data show that SVA can compete with state-of-the-art methods in extracting endmembers of prevalent land covers. Moreover, it is capable of avoiding extracting outliers as endmembers. [ABSTRACT FROM AUTHOR]

Background: The occurrence of acute ischemic stroke in cancer patients is not unusual. In clinical practice, acute ischemic stroke with cancer usually cannot be diagnosed promptly due to lack of specific markers. But for cancer patients, advanced prevention, accurate diagnosis and proper treatment of acute ischemic stroke are very important. The aim of the present study was to investigate the clinical and neuroimaging features of acute ischemic stroke in patients with cancer. Methods: We conducted a retrospective review of all cancer-associated acute ischemic stroke patients (n = 46) admitted to the Affiliated Hospital of Academy of Military Medical Sciences between October 2011 and March 2015. A group of non-cancer acute ischemic stroke patients (n = 50) at the same period were selected randomly as control. The clinical and neuroimaging data were collected and compared between the 2 groups. Results: Patients with cancer-associated stroke (CS) had a lower body mass index (23.26 ± 3.70 vs. 24.88 ± 2.83, p = 0.021) compared to non-cancer stroke (NC) patients. A lower proportion of CS patients suffered from hypertension (45.7 vs. 68.0%, p = 0.039) and hyperlipidemia (10.9 vs. 72.0%, p = 0.000) than the NC group. A higher proportion of CS patients had deep vein catheter (24.0 vs. 0%) before the onset of stoke than that of the NC group. Levels of hemoglobin, albumin and triglyceride were lower in CS groups compared with that of the NC group (p < 0.05). The prothrombin time, international normalized ratio, D-dimer and fibrinogen levels were significantly higher in the CS group than in the NC group (p < 0.05). As to the neuroimaging patterns, disperse lesions (OR 7.01; 95% CI 1.17-42.12; p < 0.05) was independently associated with CS. Conclusions: Cancer-associated ischemic stroke was different form conventional ischemic stroke in the aspect of clinical and neuroimaging manifestation. This phenomenon might be because of the embolic etiology of CS. These features together could become a clue to CS. [ABSTRACT FROM AUTHOR]

In this paper, we introduced major challenges in mapping croplands, settlements, water and wetlands, and discussed challenges in the use of multi-temporal and multi-sensor data. We then summarized some of the on-going efforts in improving qualities of global land cover maps. Existing technologies provide sufficient data for better map making if extra efforts can be made instead of harmonizing and integrating various global land cover products. Developing and selecting better algorithms, including more input variables (new types of data or features) for classification, having representative training samples are among conventional measures generally believed effective in improving mapping accuracies at local scales. We pointed out that data were more important in improving mapping accuracies than algorithms. Finally, we proposed a new paradigm for global land cover mapping, which included a view of vegetation classes based on their types and form, canopy cover and height. The new paradigm suggests that a universally applicable training sample set is not only possible but also effective in improving land cover classification at the continental and global scales. To ensure an easy transition from traditional land cover mapping to the new paradigm, we recommended that an all-in-one data management and analysis system be constructed. [ABSTRACT FROM AUTHOR]

Fast Independent Component Analysis (FastICA) is the commonly used feature extraction method for non-Gaussian structure data and it is often used in multispectral/hyperspectral image processing. However, FastICA requires all pixels to be involved at each iteration. Therefore, it is a very time-consuming method when the total number of iterations is large. In this study, we propose an equivalent algebraic method for FastICA when selecting kurtosis as a non-Gaussian index. We name this new method principal kurtosis analysis (PKA). The feature extraction result of PKA is equivalent to that of FastICA when considering kurtosis as the measurement of non-Gaussianity. Similar to FastICA, PKA also applies the fixed-point iteration method to search for extreme kurtosis directions. However, when computing the projected direction in the iteration process, PKA only requires a co-kurtosis tensor and not all of the pixels. Therefore, this reduces the time complexity. The proposed algorithm (PKA) has been applied on multispectral and hyperspectral images and shows its time advantage in the experiments. [ABSTRACT FROM AUTHOR]

How to find the representative bands is a key issue in band selection for hyperspectral data. Very often, unsupervised band selection is associated with data clustering, and the cluster centers (or exemplars) are considered ideal representatives. However, partitioning the bands into clusters may be very time-consuming and affected by the distribution of the data points. In this letter, we propose a new band selection method, i.e., exemplar component analysis (ECA), aiming at selecting the exemplars of bands. Interestingly, ECA does not involve actual clustering. Instead, it prioritizes the bands according to their exemplar score, which is an easy-to-compute indicator defined in this letter measuring the possibility of bands to be exemplars. As a result, ECA is of high efficiency and immune to distribution structures of the data. The experiments on real hyperspectral data set demonstrate that ECA is an effective and efficient band selection method. [ABSTRACT FROM PUBLISHER]

The N-FINDR, developed by Winter, is one of the most widely used algorithms for endmember extraction for hyperspectral images. N-FINDR usually needs an outer loop to control the stopping rule and two inner loops for pixel replacement, so it suffers from computational inefficiency, particularly when the size of the remote-sensing image is large. Recently, geometric unmixing using a barycentric coordinate has become a popular research field in hyperspectral remote sensing. According to Cramer’s rule, a barycentric coordinate estimated by the ratios of simplex volumes is equivalent to a least-squares solution of a linear mixture model. This property implies a brand new strategy for endmember extraction. In other words, we can deduce endmembers by comparison only of abundances derived from a least-squares approach rather than a complicated volume comparison in N-FINDR. Theoretical analysis shows that the proposed method has the same performance as N-FINDR but with much lower computational complexity. In the experiment using real hyperspectral data, our method outperforms several other N-FINDR-based methods in terms of computing times. [ABSTRACT FROM AUTHOR]

Band selection (BS) plays an important role in the dimensionality reduction of hyperspectral data. However, as to the existing BS methods, few are specially designed for target detection. In this letter, we combine the target detection and BS process together and put forward a new BS method for target detection, named least absolute shrinkage and selection operator (LASSO)-based BS (LBS). Interestingly, by using a linear regression model with L1 regularization (LASSO model), LBS transforms the discrete BS problem into the continuous optimization problem, which cannot only avoid the complicated subset selection process but also evaluate the importance of all the bands simultaneously. The experiments on real hyperspectral data demonstrate that LBS is a very effective BS method for target detection. [ABSTRACT FROM PUBLISHER]

Most unsupervised band selection methods take the information of bands into account, but few of them pay attention to the quality of bands. In this paper, by combining idea of noise-adjusted principal components (NAPCs) with a state-of-art band selection method [maximum determinant of covariance matrix (MDCM)], we define a new index \mbiQ to quantitatively measure the quality of the hyperspectral data cube. Both signal-to-noise ratios (SNRs) and correlation of bands are simultaneously considered in \mbiQ. Based on the new index defined in this article, we propose an unsupervised band selection method called minimum noise band selection (MNBS). Taking the quality (\mbiQ) of the data cube as selection criterion, MNBS tries to find the bands with both high SNRs and low correlation (high \mbiQ). The subset selection method, sequential backward selection (SBS), is used in MNBS to improve the search efficiency. Some comparative experiments based on simulated as well as real hyperspectral data are conducted to evaluate the performance of MNBS in this study. The experimental results show that the bands selected by MNBS are always more effective than those selected by other methods in terms of classification. [ABSTRACT FROM PUBLISHER]

In the field of unsupervised band selection, minimum linear prediction (LP) error is a commonly used criterion function. To avoid the large computational complexity, sequential forward selection (SFS) is often employed for subset search in LP-based methods. In this article, we propose a highly efficient LP-based band selection method termed autocorrelation matrix-based band selection (ACMBS), which adopts the sequential backward selection (SBS) as subset search strategy. Interestingly, the LP error is finally transformed into the inverse of the autocorrelation matrix in ACMBS. Thus the computational complexity of ACMBS is significantly reduced. Moreover, we further improve the accuracy of ACMBS by employing relative error, instead of absolute error, as a cost function which is invariant to the magnitude of bands. The results of the experiment show that ACMBS is quite efficient and outperforms the other compared methods in terms of classification accuracy as well. [ABSTRACT FROM PUBLISHER]

Target detection has recently drawn considerable interest in hyperspectral image processing. People tend to exclude corrupted or badly damaged bands before applying the target detection algorithm to the data for better detection results. In this letter, it is proved that adding any band independent of the original image, even a noisy band, would be always beneficial to the performance of constrained energy minimization in terms of output energy. Finally, several tests are conducted to further justify our viewpoint. [ABSTRACT FROM PUBLISHER]