Constrained Energy Minimization Research Articles

A Generalized Complex-Valued Constrained Energy Minimization Scheme for the Arctic Sea Ice Extraction Aided With Neural Algorithm

Due to the significant role of sea ice in the Arctic-related research, developing high-precision and robust Arctic sea ice extraction techniques for multi-source remote-sensing images encounters a great challenge. In the light of the constrained energy minimization scheme, this article provides a generalized complex-valued constrained energy minimization (GCVCEM) scheme for the Arctic sea ice extraction with strong robustness and accessible implementation. Given the fact that the image extraction process is easily disturbed by noise in real-life application scenarios, a modified Newton integration (MNI) neural algorithm with the noise-tolerance ability and high extraction accuracy is proposed to aid the GCVCEM scheme. Its key idea is to add an error integration feedback term on the basis of the Newton–Raphson iterative (NRI) algorithm to resist noise perturbation on the solution process of the GCVCEM scheme for high-precision and robust extraction of the Arctic sea ice. Besides, the corresponding convergence analyses and robustness proofs on the proposed MNI neural algorithm are furnished. To evaluate the extraction performance of the proposed MNI neural algorithm, multiple comparative experiments with different sea ice observation images and different noise workspaces are performed. Both the visualized and quantitative experimental results substantiate the superiorities of the proposed MNI neural algorithm aided the GCVCEM scheme for the Arctic sea ice extraction.

Constrained Energy Minimization Anomaly Detection for Hyperspectral Imagery via Dummy Variable Trick

CEM has shown great success in subpixel target detection. This article develops a DVT to extend CEM to CEM-AD and shows that CEM-AD also enjoys the same success in anomaly detection (AD). Its idea converts a known specific target signature <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$d$ </tex-math></inline-formula> imposed on CEM into an unknown specific target signature to develop an SBR-CEM as a UST-CEM which serves as a liaison to derive the desired CEM-AD without prior knowledge of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$d$ </tex-math></inline-formula> . Surprisingly, the derived CEM-AD turns out to be a sample correlation matrix <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> -based AD, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula> -AD in correspondence to the well-known sample covariance matrix <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -based AD developed by Reed-Xiaoli, RX-AD. To further improve CEM-AD, an LRaSMD model introduced by GoDec and its SC are further incorporated into CEM-AD where two new versions of SC, FSC and VSC, are particularly designed to enhance AD. Finally, to effectively evaluate AD performance, recently developed 3-D ROC curve-derived detection measures are used for comparative studies and analyses.

Deep Constrained Energy Minimization for Hyperspectral Target Detection

Deep Constrained Energy Minimization for Hyperspectral Target Detection

Global to Local: A Hierarchical Detection Algorithm for Hyperspectral Image Target Detection

Hyperspectral image (HSI) has received considerable attention in the field of target detection due to its powerful ability to capture the spectral information of land covers, and plenty of detection algorithms have been explored. However, these methods generally leverage the difference between the spectrum of the target to be detected and the background spectrum to accomplish target detection, and so are susceptible to the problem of spectral variability. In this article, we propose a global-to-local hierarchical detection algorithm for HSI (G2LHTD). Firstly, extended morphological attribute profile (EMAP) is first used to model global spatial texture information from HSI. Subsequently, a diverse-direction constrained energy minimization (D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CEM) detector is developed to consider the spatial information within eight neighborhoods around each pixel in HSI, yielding comprehensive local spatial information. More substantially, to effectively discriminate the neighborhood information in diverse directions, we devise an adaptive neighborhood feature aggregation (ANFA) strategy, which will comprehensively evaluate the significance of neighborhood information in diverse directions. As a result, the spatial features of HSI can be comprehensively considered for hyperspectral target detection (HTD). Extensive experiments, conducted on four standard datasets, demonstrate the effectiveness of the proposed method. The codes of this work will be available at https://github.com/zhonghaocheng/G2LHTD_Master for the sake of reproducibility.

Urban Surface Water Mapping from VHR Images Based on Superpixel Segmentation and Target Detection

Surface water is a fundamental resource in urban environments. Monitoring the spatio-temporal distribution of urban surface water from remotely sensed images is crucial for urban planning and management. Unfortunately, due to the limitation of spatial resolution, the method based on low&#x002F;medium resolution images is difficult to extract small water bodies accurately. Recently, very high resolution (VHR) images have shown considerable potential for urban compositions mapping. However, fewer spectral bands, shadows, and high spectral heterogeneity of VHR images hinder the application of traditional methods. In this study, we proposed an urban surface water mapping method called sparse superpixel-based water extraction (SSWE) from VHR images. The method includes three steps: (1) clustering water bodies into sparse targets at the object level by an improved scale-adaptive simple non-iterative clustering (SA-SNIC) superpixel segmentation; (2) generating new bands with additional spectral, spatial, and derived features, to increase the dimensions of original data and enhance the separability between water bodies and background covers; (3) constructing a positive-negative constrained energy minimization (PNCEM) multi-target sparse detector to highlight the water bodies while suppressing shadows. The proposed method was applied to GF-2 multispectral images of four cities in China. The results showed that SSWE achieved the highest accuracy compared with other methods, with an average OA of 98.91&#x0025; and an average kappa coefficient of 0.942. Furthermore, the separability analysis also indicated that SSWE could effectively distinguish urban water bodies from shadows and other land covers. And stable results can be acquired by the suggested parameters and thresholds of SSWE.

Aeromagnetic and Landsat-8 data interpretation for structural and hydrothermal alteration mapping along the Central and Southern Eastern Desert boundary, Egypt

Pan-African basement rocks cover the study area along the boundary between Central and Southern Eastern Desert with small exposed sedimentary sequences. Several vein-type gold mineralization with hydrothermal alteration zones have long been known in the study area. Aeromagnetic and remote sensing imagery data were integrated for mapping the structural elements and hydrothermal alteration zones related to gold mineralization. By aeromagnetic imagery inspection, the structural complexity and porphyry intrusions density maps have been effectively constructed by applying Enhanced Center for Exploration Targeting (CET) techniques. Major NW shear zones along with NNW-SSE, WNW-ESE, NS, and NE-SW are the main trends controlling gold mineralization. On the other hand, applying band ratios and constrained energy minimization (CEM) technique on Landsat-8 data pointed out alteration minerals associated with the hydrothermal fluids. Calcite, sericite, and chlorite are the common alteration minerals detected, while goethite and epidote are less common in alteration zones of the area under study. A combination of CET structural complexity, circular features, and alteration zones produced a potential mineralization map pointing out numerous prospective zones for mineralizing gold. The predictive map was validated by projecting the known gold prospects at the study area, reflecting an agreement between the known gold occurrences and the higher classes of the predictive zone. The discussed techniques in the current research can be adopted as a direct indicator for structural mapping and detecting the alteration zones related to gold mineralization elsewhere.

Detection and Classification of Rice Infestation with Rice Leaf Folder (Cnaphalocrocis medinalis) Using Hyperspectral Imaging Techniques

The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.

Camouflaged Target Detection Based on Snapshot Multispectral Imaging

The spectral information contained in the hyperspectral images (HSI) distinguishes the intrinsic properties of a target from the background, which is widely used in remote sensing. However, the low imaging speed and high data redundancy caused by the high spectral resolution of imaging spectrometers limit their application in scenarios with the real-time requirement. In this work, we achieve the precise detection of camouflaged targets based on snapshot multispectral imaging technology and band selection methods in urban-related scenes. Specifically, the camouflaged target detection algorithm combines the constrained energy minimization (CEM) algorithm and the improved maximum between-class variance (OTSU) algorithm (t-OTSU), which is proposed to obtain the initial target detection results and adaptively segment the target region. Moreover, an object region extraction (ORE) algorithm is proposed to obtain a complete target contour that improves the target detection capability of multispectral images (MSI). The experimental results show that the proposed algorithm has the ability to detect different camouflaged targets by using only four bands. The detection accuracy is above 99%, and the false alarm rate is below 0.2%. The research achieves the effective detection of camouflaged targets and has the potential to provide a new means for real-time multispectral sensing in complex scenes.

Secrecy Energy-Efficient UAV Communication via Trajectory Design and Power Control

This paper investigates the problem of maximizing the secrecy energy efficiency (SEE) for unmanned aerial vehicle- (UAV-) to-ground wireless communication system, in which a fixed-wing UAV tries to transmit covert information to a terrestrial legitimate destination receiver with multiple terrestrial eavesdroppers. In particular, we intend to maximize the worst-case SEE of UAV by jointly optimizing UAV’s flight trajectory and transmit power over a finite flight period. However, the formulated problem is challenging to solve because of its large-scale nonconvexity. For efficiently solving this problem, we first decouple the above optimization problem into two subproblems and then propose an alternating iterative algorithm by adopting block coordinate descent method and Dinkelbach’s algorithm as well as successive convex approximation technique to seek a suboptimal solution. For the sake of performance comparison, two benchmark schemes, the secrecy rate maximization (SRM) scheme and constrained energy minimization (CEM) scheme are considered to obtain more useful insights. Finally, simulation results are executed to verify that our proposed SEE maximization (SEEM) algorithm is superior to two benchmark schemes for the UAV-ground communication system.

Hyperspectral target detection based on transform domain adaptive constrained energy minimization

Traditional hyperspectral target detection methods use spectral domain information for target recognition. Although it can effectively retain intrinsic characteristics of substances, targets in homogeneous regions still cannot be effectively recognized. By projecting the spectral domain features on the transform domain to increase the separability of background and target, fractional domain-based revised constrained energy minimization detector is proposed. Firstly, the fractional Fourier transform is adopted to project the original spectral information into the fractional domain for improving the separability of background and target. Then, a newly revised constrained energy minimization detector is performed, where sliding double window strategy is used to make the best of the local spatial statistical characteristics of testing pixel. In order to make the best of inner window information, the mean value of Pearson correlation coefficient is measured between prior target pixel and testing pixel associated with its four neighborhood pixels. Extensive experiments for four real hyperspectral scenes indicate that the performance of the proposed algorithm is excellent when compared with other related detectors.

Imaging Mars analog minerals' reflectance spectra and testing mineral detection algorithms

Mineral mapping of a planetary surface is of prime importance to better understanding its composition and constraining its geologic evolution. Visible-to-Near-Infrared (VNIR) hyperspectral remote sensing is the primary tool to detect the composition of the martian surface at high spatial resolution. However, it is not straightforward to validate the mapping results since mineralogical groundtruth is typically unavailable. Furthermore, determining whether common approaches used to decode terrestrial VNIR data are applicable to Mars requires rigorous evaluation. In this work, we collected a suite of laboratory hyperspectral images with groundtruth, consisting of binary mixtures of Mars Global Simulant (MGS-1) and various hydrous minerals. The spectral effects of mixing MGS-1 with hydrous minerals were analyzed through conventional spectral parameters. It is observed that MGS-1 substantially reduces the spectral contrast of hydrous minerals. We then conducted a systematic comparison of seven benchmark target detection algorithms on the laboratory datasets, including Constrained Energy Minimization, Adaptive Coherence Estimator, Matched filter, Hierarchical Constrained Energy Minimization, Sparse Representation for Target Detection, Joint Sparse Representation and Multi-task Learning method, and Multi-task Joint Sparse and low-rank Representation (MTJSLR) method. Extensive experiments demonstrate that MTJSLR outperforms other competitors in successfully detecting low modal abundance hydrous minerals. The detection limits for nontronite, montmorillonite, kaolinite, gypsum, and calcite are 2.5%, 2.5%, 1%, 5%, and 5%, respectively. Carbonates are more challenging to detect than phyllosilicates even at the same abundance, which could partially contribute to the relative paucity of observed carbonates on Mars relative to phyllosilicates.

A new hybrid method for epithermal gold exploration using multi-sensor satellite data in Sistan and Baluchestan Province (Iran)

Remote sensing data provide a useful piece of information for initial identification of alteration zones, lithological units and structures in relation to mineralization, saving time and cost. In this research, silicic, argillic and propylitic alteration zones with gold mineralization in Taftan area in Sistan and Baluchestan province (Iran) were identified by thermal infrared (TIR), shortwave infrared (SWIR) and visible-near infrared (VNIR) bands of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Landsat-8 data. Detecting altered and mineralized zones of epithermal gold were conducted using a conventional hybrid method of band ratio in false coloured composite (BR-FCC), and a new hybrid method including, constrained energy minimization in false coloured composite (CEM-FCC). The hybrid methods of the BR-FCC (BRs in RGB) identified the silicic area and places, containing clay and secondary iron minerals. Furthermore, the advanced argillic, argillic and propylitic alteration zones detected and derived in altered areas specifically to the northwest of Taftan, in Kharestan and Bidester deposits using the hybrid methods of the CEM-FCC (CEMs in RGB). Results of image processing showed two new prospective altered places to the northeast of Kharestan deposit and to the northwest of Taftan volcano.

Quantitative Measurement of Breast Tumors Using Intravoxel Incoherent Motion (IVIM) MR Images.

Breast magnetic resonance imaging (MRI) is currently a widely used clinical examination tool. Recently, MR diffusion-related technologies, such as intravoxel incoherent motion diffusion weighted imaging (IVIM-DWI), have been extensively studied by breast cancer researchers and gradually adopted in clinical practice. In this study, we explored automatic tumor detection by IVIM-DWI. We considered the acquired IVIM-DWI data as a hyperspectral image cube and used a well-known hyperspectral subpixel target detection technique: constrained energy minimization (CEM). Two extended CEM methods—kernel CEM (K-CEM) and iterative CEM (I-CEM)—were employed to detect breast tumors. The K-means and fuzzy C-means clustering algorithms were also evaluated. The quantitative measurement results were compared to dynamic contrast-enhanced T1-MR imaging as ground truth. All four methods were successful in detecting tumors for all the patients studied. The clustering methods were found to be faster, but the CEM methods demonstrated better performance according to both the Dice and Jaccard metrics. These unsupervised tumor detection methods have the advantage of potentially eliminating operator variability. The quantitative results can be measured by using ADC, signal attenuation slope, D*, D, and PF parameters to classify tumors of mass, non-mass, cyst, and fibroadenoma types.

Multisource Data Analysis for Gold Potentiality Mapping of Atalla Area and Its Environs, Central Eastern Desert, Egypt

In this research, airborne geophysical and remote sensing datasets were integrated for gold potentiality mapping (GPM) over the Atalla area in Central Eastern Desert, Egypt. Utilizing aeromagnetic data, detailed structural complexity maps were constructed using the center for exploration targeting (CET) procedure. Then, spectrometric gamma-ray data primarily located hydrothermally altered tracts with discriminating various rock units. The latter are precisely outlined by implementing various techniques (false-color composite (FCC), band ratio (BR), relative absorption band depth (RBD), directed principal component analysis (DPCA), and constrained energy minimization (CEM)) to ASTER, Sentinel 2 and ALOS PRISM datasets, with reference to the geological maps. The study exhibits that gold mineralization is structurally controlled by NW-SE direction. The findings of structural complexity and hydrothermal alteration (argillic, advanced argillic, phyllic, and propylitic) were used as weighted inputs for contouring gold potentiality. The resultant GPM accentuated five gold-promising zones; two are confirmed via locations of ancient gold mines, while the remaining three zones are strongly recommended for their gold potentiality.

EXTRACTING FEATURE OF WATER FROM REMOTELY SENSED IMAGE

In the present work, different remote sensing techniques have been used to analyze remote sensing data spectrally using ENVI software. The majority of algorithms used in the Spectral Processing can be organized as target detection and classification. In this paper method of target detection has been studied constrained energy minimization on the Therthar Lakeand surrounding area has been done. Also the results that obtained from applying constrained energy minimization were more accurate than other method comparing with the real situation.

A Discrete‐Domain Approach to Three‐Phase Hysteresis in Porous Media

AbstractWe present a discrete‐domain approach to three‐phase displacements and hysteresis in porous media. In this method, constrained energy minimization leads to evolution equations for local saturations that describe a wide range of three‐phase displacements, including pressure‐ and saturation‐controlled displacement with or without preservation of one of the defending phases. Under action of global saturation constraints, irreversible displacements lead to significant fluid redistribution, as well as abrupt fluctuations of both the three‐phase saturation paths and the corresponding capillary pressures. These features are a consequence of Haines jumps with cooperative behavior that occur at pore scale in three‐phase systems. The method is a fast and convenient way to investigate hysteresis behavior of three‐phase displacement in porous media. As free energy is an extensive property, the framework links pore and core scales and provide a means to achieve upscaled three‐phase displacements for higher‐order hysteresis loops, which rarely is obtained in time‐consuming three‐phase measurements or pore‐scale simulations.

Sparse Channel Estimation via Hierarchical Hybrid Message Passing for Massive MIMO-OFDM Systems

In this paper, we investigate a sparse channel estimation problem for broadband massive multiple-input-multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. We propose a hidden Markov model to capture the structured sparsity and temporal dependency characteristic of massive MIMO-OFDM channels in the angle-delay domain, and this probability model exhibits extensive adaptability to different realistic propagation scenarios. Then we solve the channel estimation problem based on a novel optimization framework named constrained Bethe free energy (BFE) minimization, which is valid for a generic statistical model. Under this systematic theoretical framework, a hierarchical hybrid message passing (HHMP) algorithm is proposed to track dynamic channel parameters recursively. The proposed method can adaptively learn the sparse structure and temporal correlation of multiuser channels without requiring the knowledge of hidden Markov channel parameters. Numerical simulations demonstrate that the proposed HHMP algorithm can accurately estimate angle-delay domain channels with reduced iteration times and pilot overhead.

Multispatial Filtering Module Cascaded System for Hyperspectral Image Classification

This article presents a multispatial filtering module cascaded system (MSFMCS) for hyperspectral image classification (HSIC), which can serve as a paradigm to improve spectral–spatial classification. It includes multiple spatial filtering modules (SFMs) that are cascaded to particularly capture spatial information from the classification maps generated from the preceding modules. As a result, any spectral classifier (SC) can be used as an input to an initial/input module (IM). Through MSFMCS, its classification performance keeps improving as more SFMs are processed. To terminate MSFMCS, an automatic stopping rule is particularly designed by support vector machine (SVM) which is used not only as a classifier but also as a decision-maker. So, once an SC cannot be further improved, MSFMCS is terminated. One major benefit resulting from MSFMCS is its framework which can implement any arbitrary SC as its initial classifier in IM. Another is its ability in capturing additional spatial classification information module by module as the process progresses. A third one is no weights connected between modules so that no training phase is required like a feedforward neural network. Finally, the number of modules used in MSFMCS can be automatically determined by its stopping rule not predetermined empirically. To illustrate full advantages of MSFMCS in HSIC, three types of heterogeneous classifiers, pure-pixel-based SVM, mixed-pixel-based constrained energy minimization (CEM), and feature-extraction-based classifier—orthogonal total variation component analysis (OTVCA)—are used for experiments to demonstrate how MSFMCS can improve their classification performance.

Identify Informative Bands for Hyperspectral Target Detection Using the Third-Order Statistic

Constrained energy minimization (CEM) has been proposed and widely researched in the field of hyperspectral target detection. Generally, it selects one of the target spectra as the representative and then keeps its output constant while minimizing the average filter output energy of the data. However, it has been proven that as the number of bands (L) increases, CEM will gradually lower the average filter output energy when keeping the representative’s output constant. Unavoidably, due to the inherent spatial and temporal variation of the spectra, this will lead to an unreasonable phenomenon, i.e., if L is particularly large, when adding more bands, CEM will suppress more and more pixels, even including the target pixels. This means that the optimal solution of CEM may not correspond to the target detection result that we desire. To deal with this, in this paper, we introduce the third-order statistic (skewness) of the CEM model, served as an auxiliary index to determine whether a band is beneficial to target detection or not. Theoretically, we prove that the skewness index can always exclude the noisy bands with Gaussian distribution. In addition, experiments on several widely used remote sensing data indicate that the index can also efficiently identify informative bands for a better target detection performance.

Constraint energy minimization generalized multiscale finite element method in mixed formulation for parabolic equations

In this paper, we develop the constraint energy minimization generalized multiscale finite element method (CEM-GMsFEM) in mixed formulation applied to parabolic equations with heterogeneous diffusion coefficients. The construction of the method is based on two multiscale spaces: pressure multiscale space and velocity multiscale space. The pressure space is constructed via a set of well-designed local spectral problems, which can be solved independently. Based on the computed pressure multiscale space, we will construct the velocity multiscale space by applying constrained energy minimization. The convergence of the proposed method is proved. In particular, we prove that the convergence of the method depends only on the coarse grid size, and is independent of the heterogeneities and contrast of the diffusion coefficient. Four typical types of permeability fields are exploited in the numerical simulations, and the results indicate that our proposed method works well and gives efficient and accurate numerical solutions.