Search

This article focuses on the first aspect of the album of deep learning: the deep convolutional method. The traditional matching point extraction algorithm typically uses manually designed feature descriptors and the shortest distance between them to match as the matching criterion. The matching result can easily fall into a local extreme value, which causes missing of the partial matching point. Targeting this problem, we introduce a two-channel deep convolutional neural network based on spatial scale convolution, which performs matching pattern learning between images to realize satellite image matching based on a deep convolutional neural network. The experimental results show that the method can extract the richer matching points in the case of heterogeneous, multi-temporal and multi-resolution satellite images, compared with the traditional matching method. In addition, the accuracy of the final matching results can be maintained at above 90%.

Numerous deep learning-based object detection methods have achieved excellent performance. However, the performance on small-size object detection and positive and negative sample imbalance problems is not satisfactory. We propose a multi-scale feature selective matching network (MFSMNet) to improve the performance of small-size object detection and alleviate the positive and negative sample imbalance problems. First, we construct a multi-scale semantic enhancement module (MSEM) to compensate for the information loss of small-sized targets during down-sampling by obtaining richer semantic information from features at multiple scales. Then, we design the anchor selective matching (ASM) strategy to alleviate the training dominated by negative samples caused by the imbalance of positive and negative samples, which converts the offset values of the localization branch output in the detection head into localization scores and reduces negative samples by discarding low-quality anchors. Finally, a series of quantitative and qualitative experiments on the Microsoft COCO 2017 and PASCAL VOC 2007 + 2012 datasets show that our method is competitive compared to nine other representative methods. MFSMNet runs on a GeForce RTX 3090. [ABSTRACT FROM AUTHOR]

The metasedimentary rocks of the South Liaohe Group are widely distributed along the Jiao‐Liao‐Ji Belt (JLJB) in eastern Liaoning Province. It is important to understanding tectonic setting and evolution of the JLJB by determining its sediment sources and properties of the provenances, sedimentary facies, metamorphic ages, and facies. After the detailed field geological surveys and comprehensive laboratory observation, many high‐grade metapelitic rocks are identified in the South Liaohe Group. The main rock type is sillimanite‐garnet‐cordierite‐biotite plagiogneiss. The zircon U–Pb geochronology of three samples shows that these high‐grade meta‐pelitic rocks are mainly derived from the Liaoji Granites and the Archean basement. The protolith formation ages are between 2.00 and 1.93 Ga. Subsequently, these protolithes underwent high‐pressure metamorphism resulted from collisional orogeny, with peak metamorphism at ca. 1.88 Ga. Then, at 1.88–1.84 Ga, these rocks experienced the retrograde metamorphism and exhumed to the surface during crustal uplift. Geochemical data show that the protoliths are alumina‐rich claystones and graywackes with low maturity, implying near‐source sedimentation. The chemical index of alteration (CIA) values of these samples range from 60 to 80, indicating that the protoliths underwent moderate weathering. The sediment source was mainly felsic components of the upper crust, possibly with the addition of ancient sediments. Various tectonic environment discrimination diagrams combined with previous results on metamorphism and isotope chronology of these metasedimentary rocks in the JLJB indicate that the rocks in the study area originated from an active continental margin with an evolving island arc. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing is an essential research topic for spectral data analysis due to the existence of mixed pixels. Recently, many methods based on sparse nonnegative matrix factorization (NMF) have been widely used for unmixing by incorporating similarity preserving. However, most of them conduct the similarity learning and unmixing by using two separate steps, which may lead to the case that the learned similarity matrix is not the optimal one for unmixing. Thus, the performance of unmixing would be influenced and become undesirable. To alleviate this problem, we propose an adaptive relationship preserving-based sparse NMF (ARP-NMF) for hyperspectral unmixing. Typically, we regard similarity learning and unmixing as an alternative optimization process. During this process, the learned similarity weights and unmixing results can be mutually improved. Thus, our proposed method can learn the optimal similarity weights for unmixing and obtain better generalization ability for different hyperspectral images than traditional methods. Moreover, by using the spectral and spatial local structure, our ARP-NMF method effectively preserves structure consistency between pixels and abundances. Experimental results both on the synthetic data and the real data reveal that our proposed method outperforms several representative sparse NMF-based methods. [ABSTRACT FROM AUTHOR]

The Palaeoproterozoic tectonic evolution of the Jiao–Liao–Ji Belt (JLJB) in the North China Craton remains controversial, particularly in the absence of adequate evidence for oceanic plate subduction. Here, we report SHRIMP U–Pb zircon ages, whole‐rock geochemistry, and Sm–Nd isotope data on felsic tuffs from the Anshan–Helan–Lianshanguang area in the Liaodong Peninsula which provides important insights into the early tectonic evolution of the JLJB. The zircon SHRIMP U–Pb ages suggest formation of the tuffs crystallized at ca. 2.17 Ga, which coincide with the crystallization of the voluminous Liaoji granitoids in this belt. The felsic tuffs show calc‐alkaline features and are characterized by a wide range of SiO2 (61.89–72.55 wt.%), MgO (1.35–5.80 wt.%), Cr (36.0–67.8 ppm) and Ni (5.88–28.8 ppm) contents, and low TiO2 (0.42–0.64 wt.%) and total Fe2O3 (2.14–5.64 wt.%) concentrations. They also display enrichment in LREE and depletion in Nb, Ta, and Ti similar to the features of continental arc andesites. Their wide variation in whole‐rock εNd(t) (−2.6 to +3.4) combined with the synchronous magmatic activity in this region suggests that they were derived from mixing of mafic (e.g., those in the Liaohe suite) and felsic (e.g., the Liaoji granitoids) magmas, followed by fractional crystallization. In view of the widespread distribution of magmatism, including the Helan felsic tuffs and Liaoji granitoids, and the synchronous sedimentary rocks in the Liaodong Peninsula, we propose that the evolution of the JLJB involved an initial back‐arc extension stage, followed by arc‐continent collision. [ABSTRACT FROM AUTHOR]

Statistical modeling of wavelet subbands has frequently been used for image recognition and retrieval. However, traditional wavelets are unsuitable for use with images containing distributed discontinuities, such as edges. Shearlets are a newly developed extension of wavelets that are better suited to image characterization. Here, we propose novel texture classification and retrieval methods that model adjacent shearlet subband dependences using linear regression. For texture classification, we use two energy features to represent each shearlet subband in order to overcome the limitation that subband coefficients are complex numbers. Linear regression is used to model the features of adjacent subbands; the regression residuals are then used to define the distance from a test texture to a texture class. Texture retrieval consists of two processes: the first is based on statistics in contourlet domains, while the second is performed using a pseudo-feedback mechanism based on linear regression modeling of shearlet subband dependences. Comprehensive validation experiments performed on five large texture datasets reveal that the proposed classification and retrieval methods outperform the current state-of-the-art. [ABSTRACT FROM PUBLISHER]

As a newly developed 2-D extension of the wavelet transform using multiscale and directional filter banks, the contourlet transform can effectively capture the intrinsic geometric structures and smooth contours of a texture image that are the dominant features for texture classification. In this paper, we propose a novel Bayesian texture classifier based on the adaptive model-selection learning of Poisson mixtures on the contourlet features of texture images. The adaptive model-selection learning of Poisson mixtures is carried out by the recently established adaptive gradient Bayesian Ying-Yang harmony learning algorithm for Poisson mixtures. It is demonstrated by the experiments that our proposed Bayesian classifier significantly improves the texture classification accuracy in comparison with several current state-of-the-art texture classification approaches. [ABSTRACT FROM AUTHOR]