Pixel Features Research Articles

Optimization of matched filters for VHR image segmentation

ABSTRACT The availability of very high resolution remotely sensed images has made the use of spectral information alone insufficient for class recognition, so the integration of spatial information into the segmentation task becomes necessary. Spatial information takes into account the surrounding of a pixel, rather than dealing with a pixel as an isolated item. In this paper, inspired by matched filtering theory, we propose a new technique for spatial feature extraction. The technique consists of using 2D kernels convolved with the spectral bands. The convolution operation bears valuable spatial information about the pixel under consideration. The concatenation of the extracted spatial features and spectral features of pixels feeds a support vector machine (SVM) to segment the image of interest. To cope with the complexity of images having objects of varying sizes (i.e. urban areas), we adopted a hierarchical strategy. That is, kernels with increasing size are applied to extract different spatial features corresponding to different objects. Thus, we have extended the use of matched filters from single object enhancement to multi-object enhancement. A challenging step in designing the matched filters is the two-dimensional kernels coefficients selection, which we formulated as an optimization problem within a particle swarm optimization framework. The optimization process was driven by two different fitness functions, the cross-validation SVM accuracy and the Bhattacharyya distance, which were both evaluated on training samples. We assessed the proposed procedure on two very high-resolution images having different spatial resolutions. The obtained results showed significant improvement in terms of the overall classification accuracy (over 10% for both images). Moreover, visual inspection of the segmented images, in addition to pepper and salt elimination, revealed significant improvement in many objects not detected by the spectral method. Our method of extracting spatial features seems to be very efficient.

Quantify pixel-level detection of dam surface crack using deep learning

An increasing number of detection methods based on computer vision are applied to detect cracks in water conservancy infrastructure. However, most studies directly use existing feature extraction networks to extract crack information, which are proposed for open-source datasets. As the crack distribution and pixel features are different from these data, the extracted crack information is incomplete. In this paper, a deep learning-based network for dam surface crack detection is proposed, which mainly addresses the semantic segmentation of cracks on the dam surface. Particularly, we design a shallow encoding network to extract features of crack images based on the statistical analysis of cracks. Further, to enhance the relevance of contextual information, we introduce an attention module into the decoding network. During the training, we use the sum of cross-entropy and Dice loss as the loss function to overcome data imbalance. The quantitative crack information is extracted by the imaging principle after using morphological algorithms to extract the morphological features of the predicted result. We built a manual annotation dataset containing 1577 images to verify the effectiveness of the proposed method. This method achieves state-of-the-art performance on our dataset. Specifically, the precision, recall, Intersection of Union (IoU), F1_measure, and accuracy are 90.81%, 81.54%, 75.23%, 85.93%, 99.76%, respectively, and the quantification error of cracks is less than 4%.

Light wave filtration by colored cellophane to optimize microscopic contrast ratio in pulmonary tuberculosis sputum observation

Introduction: Indonesia has the second highest number of Tuberculosis (TB) in the world and tuberculosis still pose as a global health priority problem. For the diagnostics, microscopy is still one of important modalities in TB diagnosis especially in peripheral areas for screening, case-finding, and treatment evaluation. The use of microscopy is limited to operator visual burden and specimen load. This study aims to modify the use of the microscope by using everyday item to increase microscope operator workload. Method: This is an analytic study of the use of colored cellophane in microscopic examination of sputum smear from 24 pulmonary TB patients from Jakarta and Surabaya. The sputum samples were confirmed positive by standardized ZN-AFB microscopy and/or Xpert MTB/RIF. Each sputum were made into two slides, for each slide, 10 oil immersion fields were captured using Optilab microscope camera mounted on microscope. A total of 480 data pairs were analysed by comparing color characteristic of acid-fast bacilli pixels and its adjacent background pixels and by counting Acid fast Bacilli for each observation field. IUATLD scale were also observed by 3 operators. Results: Contrast ratio for each AFB and its adjacent pixels were significantly higher in groups using cellophane filter than without using filter (p = 0.001). AFB identification per image acquired using filter were not significantly higher (p=0.815). Conclusion: Colored cellophane increases contrast ratio and eases microscopic examination, thus increases sputum smear microscopic observation capability. Also it might increase identification capability with digital image processing.

Crowd Density Estimation Method Using Deep Learning for Passenger Flow Detection System in Exhibition Center

Aiming at the problems of crowd distribution, scale feature, and crowd feature extraction difficulties in exhibition centers, this paper proposes a crowd density estimation method using deep learning for passenger flow detection systems in exhibition centers. Firstly, based on the pixel difference symbol feature, the difference amplitude feature and gray feature of the central pixel are extracted to form the CLBP feature to obtain more crowd group description information. Secondly, use the LR activation function to add nonlinear factors to the convolution neural network (CNN) and use dense blocks derived from crowd density estimation to train the LR-CNN crowd density estimation model. Finally, experimental results show that the mean absolute error (MAE) and mean square error (MSE) of the proposed method in the UCF_CC_50 dataset are 325.6 and 369.4, respectively. Besides, MAE and MSE in part_A of the Shanghai Tech dataset are 213.5 and 247.1, respectively, and they in part_B are 85.3 and 99.7, respectively. The proposed method effectively improves the accuracy of crowd density estimation in exhibition centers.

Hierarchical Transmission Tower Detection from High-Resolution SAR Image

The small scale of transmission towers and the environmental diversity around their situations make their detection in Synthetic Aperture Radar (SAR) images a challenging task. This paper presents a new hierarchical detection algorithm for transmission towers. First, Signal-to-Clutter Ratios (SCRs) of pixels are calculated. Afterwards, a SCR threshold is set. Since transmission towers possess strong scattering characteristics, pixels with SCRs above the threshold are considered as potential transmission tower pixels. Second, spatial densities of potential transmission tower pixels are calculated. According to the aggregation characteristics of transmission tower pixels, some potential transmission tower pixels with small spatial densities are removed. The remained potential transmission tower pixels are considered as candidate transmission tower pixels. The candidate transmission tower pixels are grouped by the nearest neighbour scheme such that in each group the distance between pixels is under a given threshold. Thus, each of the groups is viewed as a quasi-transmission tower. Convex-hulls of quasi-transmission towers are built, and then Minimum Bounding Rectangle (MBR) for each convex-hull is generated. According to the rectangle aspect ratios of MBRs, the real transmission towers are extracted. C-band HH-polarization GaoFen-3 (GF-3) amplitude images are used for experiments and four of the most popular transmission tower detection algorithms are selected as comparing algorithms to validate the proposed algorithms. The detection performance of transmission towers is evaluated with detection rate and quality factor. Experimental results verify that the proposed algorithm can efficiently and accurately detect transmission towers while maintaining the transmission tower geometry to a certain extent, which indicates that the proposed algorithm is efficient and promising.

Fully connected network with multi-scale dilation convolution module in evaluating atrial septal defect based on MRI segmentation

Background and ObjectiveAtrial septal defect (ASD) is a common congenital heart disease. During embryonic development, abnormal atrial septal development leads to pores between the left and right atria. ASD accounts for the largest proportion of congenital heart disease. Therefore, the design and implementation of an ASD intelligent auxiliary segmentation system based on deep learning segmentation of the atria has very important practical significance, which we aim to achieve in this paper. MethodsThis study proposes a multi-scale dilated convolution module, which is composed of three parallel dilated convolutions with different expansion coefficients. The original FCN network usually adopts bilinear interpolation or deconvolution methods when upsampling, both of which lead to information loss to a certain extent. In order to make up for the loss of information, it is expected that the final segmentation result can be directly connected to the deep features in the cardiac MRI. This study uses a dense upsampling convolution module, and in order to obtain the shallow position information, the original FCN jump connection module is still retained. In this research, a deep convolutional neural network for multi-scale feature extraction is designed through the multi-scale expansion convolution module. At the same time, this paper also implements two traditional machine learning segmentation methods (K-means and Watershed algorithms) and a deep learning algorithm (U-net) for comparison. ResultsThe intelligent auxiliary segmentation algorithm for atrial images proposed in this framework based on multi-scale expansion convolution and adversarial learning can achieve superior results. Among them, the segmentation algorithm based on multi-scale expansion convolution can extract the associated features of pixels in multiple ranges, and can obtain deeper feature information when using a limited downsampling layer. According to the experimental results of the multi-scale expanded convolutional network on the data set, the Proportion of Greater Contour (PGC) index of the multi-scale expanded convolutional network is 98.78, the value of Average Perpendicular Distance (ADP) is 1.72mm, and the value of Overlapping Dice Metric (ODM) is 0.935, which are higher than other models. ConclusionThe experimental results show that compared with other segmentation models, the model based on multi-scale expansion convolution has significantly improved the accuracy of segmentation. Our technique will be able to assist in the segmentation of ASD, evaluation of the extent of the defect and enhance surgical planning via atrial septal occlusion.

A computation-efficient CNN system for high-quality brain tumor segmentation

In this paper, a reliable computation-efficient system of Convolutional Neural Network (CNN) is proposed for brain tumor segmentation. It consists of a segmentation-CNN, a pre-CNN block for data reduction and a refinement block. The unique CNN is custom-designed, following the proposed paradigm of ASCNN (Application Specific CNN), to perform mono-modality and cross-modality feature extractions, tumor localization and pixel classification. It features modality-wise normalization to improve the input data quality, depthwise convolution, combined with instance normalization, for the mono-modality feature extraction, bilinear upsampling for dimension expansion without introducing randomness, and weighted data addition for signal modulation. The proposed activation function Full-ReLU helps to halve the number of kernels in convolution layers of high-pass filtering without degrading processing quality. In this specific design context, the CNN is structured to have 7 convolution layers, requiring only 108 kernels and 20,308 trainable parameters in total. The number of kernels in each layer is made just-sufficient for its task, instead of exponentially growing over the layers, with a view to a higher information density in data channels and lower randomness in network training. Extensive experiments with BRATS2018 dataset have been conducted to confirm the high-level processing quality and reproducibility of the system. The mean-dice-scores for enhancing-tumor, whole-tumor and tumor-core are 77.2%, 89.2% and 76.3%, respectively. Testing each patient case requires only 29.07G Flops, a tiny fraction of what found in literature. The simple structure and reliable high processing quality of the proposed system will facilitate its implementation and medical applications.

Using fault detection and classification techniques for machine breakdown reduction of the HGA process caused by the slider loss defect

Fault Detection and Classification (FDC) based on Machine Learning (ML) approach was used to detect and classify mount head fault in the slider attachment process which causes the machine alarm 71 to occur which leads to 2% of machine downtime. This paper has focused on the use of classified pixel surface of mount head with fault difference conditions including Healthy, Fault I, Fault II, and Fault III to detect and diagnose mount head before a vacuum leak. The Artificial Neural Network (ANN) algorithm was a proposed classification model and has to be evaluated before using in the real processes. Three features of mount head surface pixel, i.e., inner, outer, and overall areas were investigated and used as model training data set. The experiment result indicates that the classification using the ANN model with three features performed with an accuracy of 94.3%. According to the result, it was found that the reliability of the production processes of FDC technique has increased as a result of the reduction of machine downtime by 1.886%.

Bidirectional Multiscale Refinement Network for Crisp Edge Detection

With the development of deep convolution neural networks (CNNs), contour detection has made great progress. Some contour detectors based on CNNs have better performance than human beings on standard benchmarks. However, it is easier for CNNs to learn the similar features of adjacent pixels, and the number of background pixels and edge pixels in the input training sample is highly imbalanced. Therefore, the prediction edge by the edge detector based on CNNs is thick and requires post-processing to obtain crisp edges. Accordingly, we introduce a novel parallel attention model and a novel loss function that combines cross-entropy and dice loss through the use of adaptive coefficients, and propose a novel bidirectional multiscale refinement network (BMRN) that stacks multiple refinement modules in order to achieve richer feature representation. The experimental results show that our method has better performance than the state-of-the-art on BSDS500 (ODS F-score of 0.828), NYUDv2 depth datasets (ODS F-score of 0.778) and Multi-Cue dataset (ODS F-score 0.905(0.002)).

Full Coverage Estimation of the PM Concentration Across China Based on an Adaptive Spatiotemporal Approach

Particulate pollution threatens the ecological environment, air quality, and public health. Therefore, it has become an increasing concern for the public and governments in recent decades. In this study, a full coverage PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> (aerodynamic diameter of less than 2.5 microns) estimation strategy is proposed based on spatiotemporal machine learning approaches including the Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) and Random Forest (RF). The RF estimates PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> by considering the features of a single pixel, while the introduction of the CNN-LSTM (size of 7 × 7 × 4) assists in exploiting the spatiotemporal correlation of surrounding pixel features. Compared with linear models and empirical spatiotemporal weight methods, our CNN-LSTM+RF avoids the uncertainty and complexity owing to actual measurements of the surrounding sites. In addition, full coverage is achieved using both satellite data and reanalysis data. Results showed that, the Root Mean Squared Error (RMSE) and coefficient of determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) of the CNN-LSTM+RF were 12.790 μg/m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> and 0.910, respectively, in sample-based Cross-Validation (CV). From the perspective of the season, the best performance of the CNN-LSTM+RF was found in autumn (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.915) and the lowest was in summer (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.848). In the meantime, for the different regions of China, the CNN-LSTM+RF also showed stable performance. The proposed method can generate high-precision continuous PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> distribution maps that provide beneficial support for improving environmental and public health, and provide a reference for using deeper networks.

An Adaptive PolSAR Trilateral Filter Based on the Mechanism of Scattering Consistency

Polarimetric Synthetic Aperture Radar (PolSAR) can record the backscattering information of ground objects by capturing the phase difference of echo signal in different polarization combinations. Due to the characteristics of coherent imaging, there is a lot of coherent speckle noise in PolSAR images. However, most of the current PolSAR image despeckling algorithms are difficult to balance the ability in aspects of speckle suppression, polarization information retention and edge structure preservation. This paper proposes an adaptive PolSAR trilateral filter (PTF) based on the mechanism of scattering consistency, which consists of following three steps. (1) The marker map of ground object scattering category is firstly obtained based on the dominant scattering mechanism determined by Freeman decomposition of the polarization covariance matrix. (2) Next, the neighborhood pixels with the same scattering mechanism as the center pixel are screened out within an adaptive filtering window. (3) A PolSAR trilateral filter is established through integration of the spatial proximity, polarization similarity and local structural characteristics of the center pixel and the screened pixels to effectively suppress the speckle noises. Experimental results upon the data of Radarsat-2 and AIRSAR demonstrate that PTF can not only suppress coherent speckle noise effectively without sacrificing the edge structure information, but also retain the unique polarization information of PolSAR image. In particular, compared with the traditional six widely used PolSAR despeckling algorithms, PTF have been significantly improved in terms of Equivalent Number of Looks (ENL) and Degree of difference (Dod) indexes by 2.49 times and 6 orders of magnitude, respectively.

Progressive Feature Learning for Facade Parsing With Occlusions.

Existing deep models for facade parsing often fail in classifying pixels in heavily occluded regions of facade images due to the difficulty in feature representation of these pixels. In this paper, we solve facade parsing with occlusions by progressive feature learning. To this end, we locate the regions contaminated by occlusions via Bayesian uncertainty evaluation on categorizing each pixel in these regions. Then, guided by the uncertainty, we propose an occlusion-immune facade parsing architecture in which we progressively re-express the features of pixels in each contaminated region from easy to hard. Specifically, the outside pixels, which have reliable context from visible areas, are re-expressed at early stages; the inner pixels are processed at late stages when their surroundings have been decontaminated at the earlier stages. In addition, at each stage, instead of using regular square convolution kernels, we design a context enhancement module (CEM) with directional strip kernels, which can aggregate structural context to re-express facade pixels. Extensive experiments on popular facade datasets demonstrate that the proposed method achieves state-of-the-art performance.

Polarimetric SAR Image Classification Based on Feature Enhanced Superpixel Hypergraph Neural Network

Synthetic aperture radar (SAR) images can capture abundant spatial and polarimetric information of land cover objects, and thus polarimetric SAR (PolSAR) image classification has been developed for various applications. Combining the advantages of spatial and polarimetric information simultaneously is of great importance for PolSAR image classification. In this paper, a feature enhanced superpixel hypergraph neural network (FESHNN) is proposed for PolSAR image classification, which aims to take full advantage of spatial features and polarimetric features from PolSAR images. In the proposed model, superpixel hypergraph neural network is constructed for feature representation of superpixels, which aims to obtain spatial correlation and polarimetric correlation in a hypergraph. Then, a feature enhancement module is employed to refine the local features of pixels and the spatial features of superpixels, which aims to enhance the discrimination of feature representation. Experimental results on three PolSAR datasets demonstrate that the proposed method yields superior classification performance compared with other related approaches.

Region-Based Polarimetric Covariance Difference Matrix for PolSAR Ship Detection

To more effectively detect small ships, in this article, a novel region-based polarimetric covariance difference matrix [RP] is put forward, which mainly consists of two stages. Briefly speaking, in the first stage, a new pixel representation way is proposed to depict the spatial characteristics of pixel, through which the difference information related to pixel’s local region is calculated as well. In the second stage, the global region difference information of pixel is computed. Finally, we construct [RP] via fusing these two different kinds of information together with a balance factor <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$c$ </tex-math></inline-formula> . Meanwhile, considering that the backscattering energy of ships is useful for ship detection, a new intensity-driven polarimetric notch filter (ID-PNF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RP</sub> ) is also derived from [RP]. Three different datasets are adopted to evaluate the effectiveness of [RP] and ID-PNF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RP</sub> . Experimental results show that: 1) compared with the polarimetric 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">$C$ </tex-math></inline-formula> ] and the polarimetric covariance difference matrix [ <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> ], [RP] is more suitable for ship detection and 2) compared with the original geometrical perturbation-polarimetric notch filter (GP-PNF) and the total power detector SPAN, the proposed method ID-PNF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RP</sub> can better detect small ships with greater figure of merit (FoM) and target-to-clutter ratio (TCR) values.

Cluster Alignment With Target Knowledge Mining for Unsupervised Domain Adaptation Semantic Segmentation

Unsupervised domain adaptation (UDA) carries out knowledge transfer from the labeled source domain to the unlabeled target domain. Existing feature alignment methods in UDA semantic segmentation achieve this goal by aligning the feature distribution between domains. However, these feature alignment methods ignore the domain-specific knowledge of the target domain. In consequence, 1) the correlation among pixels of the target domain is not explored; and 2) the classifier is not explicitly designed for the target domain distribution. To conquer these obstacles, we propose a novel cluster alignment framework, which mines the domain-specific knowledge when performing the alignment. Specifically, we design a multi-prototype clustering strategy to make the pixel features within the same class tightly distributed for the target domain. Subsequently, a contrastive strategy is developed to align the distributions between domains, with the clustered structure maintained. After that, a novel affinity-based normalized cut loss is devised to learn task-specific decision boundaries. Our method enhances the model's adaptability in the target domain, and can be used as a pre-adaptation for self-training to boost its performance. Sufficient experiments prove the effectiveness of our method against existing state-of-the-art methods on representative UDA benchmarks.

MSIF: Multisize Inference Fusion-Based False Alarm Elimination for Ship Detection in Large-Scale SAR Images

Ship detection in large-scale synthetic aperture radar (SAR) images has essential value in both military and civilian applications. However, due to the complexity of the background and the simplicity of the texture, ship detection in large-scale SAR images is prone to false alarms, such as similar-shaped reefs, islands, sea clutter, and inland buildings. This article proposes a multisize inference fusion framework to eliminate false alarms and improve the overall performance of ship detection in large-scale SAR images. In this framework, a multisize slicer is proposed to expand the scale range of image expression. Then, a detection model library is built to keep various types of models for different task scenarios and requirements. Finally, two subapproaches are proposed for false alarm elimination, namely, pixel feature filtering (FAE-pff) and multisource fusion (FAE-msf), to reduce false detection results in the output of the detection model. FAE-pff calculates how obvious each target is relative to the background and eliminates less obvious results. FAE-msf obtains bounding boxes and corresponding confidences from multiple inference sources and fuses them through weighting and updating them to achieve complementation and enhancement of information. Various experiments were conducted to evaluate the performance of each module qualitatively and quantitatively. It proves the effectiveness of the proposed framework, which can achieve more correct detections while greatly reducing erroneous detections.

Dense Pixel-Level Interpretation of Dynamic Scenes With Video Panoptic Segmentation.

A holistic understanding of dynamic scenes is of fundamental importance in real-world computer vision problems such as autonomous driving, augmented reality and spatio-temporal reasoning. In this paper, we propose a new computer vision benchmark: Video Panoptic Segmentation (VPS). To study this important problem, we present two datasets, Cityscapes-VPS and VIPER together with a new evaluation metric, video panoptic quality (VPQ). We also propose VPSNet++, an advanced video panoptic segmentation network, which simultaneously performs classification, detection, segmentation, and tracking of all identities in videos. Specifically, VPSNet++ builds upon a top-down panoptic segmentation network by adding pixel-level feature fusion head and object-level association head. The former temporally augments the pixel features while the latter performs object tracking. Furthermore, we propose panoptic boundary learning as an auxiliary task, and instance discrimination learning which learns spatio-temporally clustered pixel embedding for individual thing or stuff regions, i.e., exactly the objective of the video panoptic segmentation problem. Our VPSNet++ significantly outperforms the default VPSNet, i.e., FuseTrack baseline, and achieves state-of-the-art results on both Cityscapes-VPS and VIPER datasets. The datasets, metric, and models are publicly available at https://github.com/mcahny/vps.

Filtering and Enhancement Method of Ancient Architectural Decoration Image based on Neural Network

Due to poor ambient light or uneven lighting, the old decoration image acquisition methods are easy to cause the image blur. To solve this problem, this paper proposes a neural network-based filtering enhancement method for ancient architectural decoration images, which preserves image details by enhancing contrast, smoothing noise reduction and edge sharpening. Based on the convolutional neural network which is composed of encoder, decoder and layer hop connection, the residual network and hole convolution are introduced, and the hole U-Net neural network is constructed to fuse the pixel feature blocks of different levels. This method enhanced the image contrast according to the gray level and frequency histogram, and aiming at the gray value of the pixel to be processed in the image. And the middle value of the gray value of the neighborhood pixel is used to filter the noise of the ancient building decoration image. The paper also analyzes the joint strength of beams and columns in ancient buildings, and calculates the elastic constants of beams and columns and the stress at the joint of them, considering the image texture characteristics of the wood in ancient buildings with the mortise and tenon connection of beams and columns. Experimental results show that the proposed method has good noise suppression performance, can effectively obtain image detail features, and significantly improve the subjective visual effect of ancient architectural decoration images.

Social media image classification and retrieval method based on deep hash algorithm

In order to solve the problems of large classification error and low retrieval accuracy of traditional retrieval methods, a social media image classification retrieval method based on deep hash algorithm is proposed. With the help of CBOW model to extract semantic features and colour histogram to extract colour features of social media images, social media image classification is completed. Hash algorithm is used to deal with the unidirectional irreversibility of social media image, and the pixel feature points in the image are regarded as density function for one-to-one correspondence. The loss function is used to control the convergence of the hash algorithm to achieve social media image retrieval. Experimental results show that the error of social media image classification is only 2%, the retrieval accuracy is always higher than 90%, and the retrieval time is only 3.4 s, which has the advantage of high retrieval efficiency.

Spatial Dynamic Selection Network for Remote-Sensing Image Fusion

Nowadays, high-resolution images with rich spectral information are necessary for earth observation. Remote-sensing image fusion is an effective method to provide high-resolution multispectral images, which are obtained by fusing high-resolution panchromatic images and low-resolution multispectral images. However, existing methods mostly use the same network for image feature extraction, without considering the differences among different pixels, resulting in that the extracted features are not accurate enough. This letter proposes a spatial dynamic selection network for remote-sensing image fusion. A dynamic feature extraction module composed of multiple spatial dynamic blocks (SDBs) and cross-scale context connection blocks (CSCBs) is designed. The SDB can extract image features according to the input by different networks, and realize dynamic selection of pixel features. Since the spatial structure and spectral characteristic of each pixel are different, two complementary branches are designed in the SDB to extract different features, which improves the capability of feature extraction. Multiscale network structure is designed to obtain more abundant information and the CSCB is used to integrate the information of different scales. Experimental results on GeoEye-1 and WorldView-3 datasets demonstrate the superiority of the proposed method.