Search

In the field of remote sensing change detection, accurately capturing temporal change information and efficiently integrating multilevel information is a major challenge. In order to extend the sensory domain and optimize the information fusion, the model is able to capture temporal-spatial change features more accurately and improve the accuracy of change detection. In this article, we propose a temporal-spatial multiscale graph attention network (TSMGA), specifically, TSMGA employs a pair of pretrained ResNet18 for effective multiscale feature extraction, and in order to enhance the disparity information of the bitemporal images, we also design the temporal fusion block to emphasize the changed areas. The spatial and channel features of multiscale disparity features are enhanced by multiscale spatial-channel aggregation module. To enable more robust and efficient exploration of more global contextual information, we are inspired to introduce shortest path graph attention, which allows for a more informative and complete exploration of the global context, and furthermore allows for more efficient gathering information from far-off neighbors to the central node. In order to ensure comprehensive utilization of local and global features and to significantly improve the clarity and detail retention of the output image, global context residual fusion module (GCRFM) is designed, GCRFM efficiently utilizes the complementary information of the feature maps for fusing and recovering spatial details and variation information. We validate the effectiveness and advancement of TSMGA on three classical datasets (LEVIR-CD, WHU-CD, GZ-CD), and the experimental results show that TSMGA achieves the state-of-the-art performance level.

Abstract Background Pleuronectiformes, also known as flatfish, are important model and economic animals. However, a comprehensive genome survey of their important organelles, mitochondria, has been limited. Therefore, we aim to analyze the genomic structure, codon preference, nucleotide diversity, selective pressure and repeat sequences, as well as reconstruct the phylogenetic relationship using the mitochondrial genomes of 111 flatfish species. Results Our analysis revealed a conserved gene content of protein-coding genes and rRNA genes, but varying numbers of tRNA genes and control regions across species. Various gene rearrangements were found in flatfish species, especially for the rearrangement of nad5-nad6-cytb block in Samaridae family, the swapping rearrangement of nad6 and cytb gene in Bothidae family, as well as the control region translocation and tRNA-Gln gene inversion in the subfamily Cynoglossinae, suggesting their unique evolutionary history and/or functional benefit. Codon usage showed obvious biases, with adenine being the most frequent nucleotide at the third codon position. Nucleotide diversity and selective pressure analysis suggested that different protein-coding genes underwent varying degrees of evolutionary pressure, with cytb and cox genes being the most conserved ones. Phylogenetic analysis using both whole mitogenome information and concatenated independently aligned protein-coding genes largely mirrored the taxonomic classification of the species, but showed different phylogeny. The identification of simple sequence repeats and various long repetitive sequences provided additional complexity of genome organization and offered markers for evolutionary studies and breeding practices. Conclusions This study represents a significant step forward in our comprehension of the flatfish mitochondrial genomes, providing valuable insights into the structure, conservation and variation within flatfish mitogenomes, with implications for understanding their evolutionary history, functional genomics and fisheries management. Future research can delve deeper into conservation biology, evolutionary biology and functional usages of variations.

Benefiting from continuous innovations in deep learning algorithms, the accuracy of building change detection (BCD) in remote sensing (RS) has significantly improved. Numerous networks combining CNN and transformer architectures have emerged, yet effectively balancing local detail and global context features remains a topic of ongoing discussion. Furthermore, accurately leveraging edge information within RS images to enhance the recognition of structural changes in buildings is another critical challenge. To address these issues, this article proposes a BCD network based on dynamic gate fusion and edge graph perception (DGFEG). First, a hybrid backbone, MCTrans, is employed as the encoder to extract multiscale detailed features and global positional information of buildings. Second, a dynamic gate fusion module is introduced to dynamically weight and fuse the concatenated and differential features obtained by the encoder, enhancing the semantic representation of actual building change regions. Finally, an edge graph perception module integrates edge information with the fused features, leveraging the spatial similarity of graph structures and the interaction of edge features to suppress irrelevant edge interference, thereby improving the model's sensitivity and accuracy in detecting subtle building changes. In experiments, DGFEG was tested on real-world change scenarios and multiple RSCD datasets. The results demonstrate its superior performance compared to existing state-of-the-art methods, proving its excellence and broad application potential in tackling complex BCD tasks.

Restricted by the development of contemporary sensors, we can only acquire multispectral images (MS) and high-resolution panchromatic (PAN) images separately. The purpose of pansharpening methods is to combine the rich spectral-spatial information contained in MS and PAN images to generate the high-resolution multispectral image. Most existing pansharpening methods either separately extract feature information from MS and PAN images or extract feature information after concatenating MS and PAN images, lacking the utilization of complementary information throughout the feature extraction process. Motivated by the advancements in optimization algorithm and the state space model, we introduce a convolutional dictionary learning with state space model for pansharpeningin this article. Our network comprises two parts: the encoder and the decoder. In the encoder part, we begin by building an observation model to capture the common and unique information between MS and PAN images. Subsequently, we continuously iterate and optimize the network parameters using the approximate gradient algorithm. Meanwhile, we utilize the powerful long-range dependence modeling capability of the SSM to comprehensively extract feature information from the images. In the decoder part, we propose both a detail enhancement block and an adaptive weight learning block to strengthen the model's ability to extract detailed feature information from the images. To demonstrate the superiority of our proposed method, we conduct comparative experiments with current state-of-the-art pansharpening methods on three benchmark datasets: QB, GF2, and WV3. Experimental results prove that our method exhibits the best performance.

Single image dehazing is a fundamental but challenging task in image processing. Various deep learning-based methods have achieved great dehazing performance. However, there are still hazy residues, even color distortion and texture loss when removing haze from complex outdoor images in dense hazy scenes. A densely integrated multi-branch attentive net for image dehazing is proposed in the paper to address the above problems. The network includes a multi-scale feature extraction module and a dense-feature fusion module. The multi-scale feature extraction module adopts a multi-branch structure composed of residual channel attention blocks, which can expand the receptive field and filter the extracted features of diverse scales by weighting for fusion. It raises network learning accuracy. The dense-feature fusion module contains a multi-level feature fusion module for front and back layers, a color information renovation module, and a feature enhancement module. It achieves dynamically adjusting the channel weights of features at diverse scales, learning rich context information and suppressing redundant information, and compensating for the lack of color and texture information. The dense-feature fusion module bolsters the generalization capability of the network. The proposed method achieves superior objective and subjective evaluation results via quantitative and qualitative experiments on synthetic hazy images and natural hazy images, with better generalization ability and dehazing effect than the current SOTA dehazing algorithms, and effectively ameliorates the color distortion and incomplete dehazing.

Abstract Purpose The pathways underpinning suicide ideation (SI) and certain physical and psychological factors in patients with advanced breast cancer remain unclear. This study develops and validates a mediation model that delineates the associations between several multidimensional variables and SI in Chinese patients with advanced breast cancer. Methods Patients with advanced breast cancer (n = 509) were recruited as study participants from 10 regional cancer centers across China from August 2019 to December 2020. Participants were required to complete five questionnaires using an electronic patient-reported outcomes (ePRO) system: 9 item- Patient Health Questionnaire (PHQ-9), Hospital Anxiety and Depression Scale (HADS), Insomnia Severity Index (ISI), 5-level EQ-5D (EQ-5D-5L), and MD Anderson Symptom Inventory (MDASI). Risk factors for SI were identified using multivariable logistic regression, and inputted into serial multiple mediation models to elucidate the pathways linking the risk factors to SI. Results SI prevalence was 22.8% (116/509). After adjusting for covariates, depression (odds ratio [OR] = 1.384), emotional distress (OR = 1.107), upset (OR = 0.842), and forgetfulness (OR = 1.236) were identified as significant independent risk factors (all p

Abstract Background Little is understood about the association between psychosomatic symptoms and advanced cancer among older Chinese patients. Methods This secondary analysis was part of a multicenter cross-sectional study based on an electronic patient-reported outcome platform. Patients with advanced cancer were included between August 2019 and December 2020 in China. Participants (over 60 years) completed the MD Anderson Symptom Inventory (MDASI) and Hospital Anxiety and Depression Scale (HADS) to measure symptom burden. Network analysis was also conducted to investigate the network structure, centrality indices (strength, closeness, and betweenness) and network stability. Results A total of 1022 patients with a mean age of 66 (60–88) years were included; 727 (71.1%) were males, and 295 (28.9%) were females. A total of 64.9% of older patients with advanced cancer had one or more symptoms, and up to 80% had anxiety and depression. The generated network indicated that the physical symptoms, anxiety and depression symptom communities were well connected with each other. Based on an evaluation of the centrality indices, ‘distress/feeling upset’ (MDASI 5) appears to be a structurally important node in all three networks, and ‘I lost interest in my own appearance’ (HADS-D4) had the lowest centrality indices. The network stability was relatively high (> 0.7). Conclusion The symptom burden remains high in older patients with advanced cancer in China. Psychosomatic symptoms are highly interactive and often present as comorbidities. This network can be used to provide targeted interventions to optimize symptom management in older patients with advanced cancer in China. Trial registration Chinese Clinical Trial Registry (ChiCTR1900024957), registered on 06/12/2020.

Abstract Objectives Patients with advanced colorectal cancer (CRC) have multiple concurrent physical and psychological symptoms. This study aimed to explore the relationship between anxiety, depression, and symptom burden in advanced CRC. Methods A multicenter cross‐sectional study was conducted in 10 cancer centers from geographically and economically diverse sites in China. A total of 454 patients with advanced CRC completed the Hospital Anxiety and Depression Scale and the MD Anderson Symptom Inventory. Multiple regression analysis was applied to explore the relationship between anxiety, depression and symptom burden. Results About one‐third of the patients showed symptoms of anxiety or depression. Patients with anxiety or depression reported significantly higher symptom burden than those without (p

Abstract Background Patients diagnosed with advanced stage cancer face an elevated risk of suicide. We aimed to develop a suicidal ideation (SI) risk prediction model in patients with advanced cancer for early warning of their SI and facilitate suicide prevention in this population. Patients and Methods We consecutively enrolled patients with multiple types of advanced cancers from 10 cancer institutes in China from August 2019 to December 2020. Demographic characteristics, clinicopathological data, and clinical treatment history were extracted from medical records. Symptom burden, psychological status, and SI were assessed using the MD Anderson Symptom Inventory (MDASI), Hospital Anxiety and Depression Scale (HADS), and Patient Health Questionnaire‐9 (PHQ‐9), respectively. A multivariable logistic regression model was employed to establish the model structure. Results In total, 2814 participants were included in the final analysis. Nine predictors including age, sex, number of household members, history of previous chemotherapy, history of previous surgery, MDASI score, HADS‐A score, HADS‐D score, and life satisfaction were retained in the final SI prediction model. The model achieved an area under the curve (AUC) of 0.85 (95% confidential interval: 0.82–0.87), with AUCs ranging from 0.75 to 0.95 across 10 hospitals and higher than 0.83 for all cancer types. Conclusion This study built an easy‐to‐use, good‐performance predictive model for SI. Implementation of this model could facilitate the incorporation of psychosocial support for suicide prevention into the standard care of patients with advanced cancer.

Remote sensing image change detection (CD) has witnessed remarkable performance improvements with the guidance of deep learning models, particularly convolutional neural networks and transformers. Current CD methods heavily rely on multilayered backbone structures, such as ResNet and Unet, for feature extraction. However, these approaches exhibit limitations in coordinating the utilization of local and global features across different scales. In this article, we introduce a novel cross-scale coordinated siamese (CSC) network to effectively integrate multiscale information. We introduce a cross-scale coordination module (CSCM) within the CSC network to coordinate internal features of the local branch with cross-scale information from adjacent branches, while simultaneously attending to both the local and global regions. Furthermore, to comprehensively capture contextual information, we propose a transformer aggregation module as a decoder to harmonize the output features of CSCM. We extensively evaluate our proposed CSC network on three datasets, namely, LEVIR-CD, WHU-CD, and GZ-CD. The results demonstrate that our CSC network outperforms other leading methods significantly in terms of F1-score and intersection over union evaluation metrics.

Due to the limitations of satellite sensors, we can only obtain MS images and PAN images separately. The focus of our attention is to utilize the pan-sharpening method to generate the high-resolution multispectral (HRMS) images. In this article, we proposed the dual-branch multiscale fusion network, which based on the spatial-spectral transformer to comprehensively capture the information contained in MS images and PAN images at different scales. The architecture of our network consists of three parts: during the feature extraction and image fusion stage, we first independently apply upscaling and downscaling operations to the MS and PAN images. Subsequently, we concatenate the images from the two distinct branches and input them into the shallow feature extraction module individually. And then we input them into our adaptive feature extraction block to further extract the crucial details of the images using the attention mechanism. The images a various scales in different branches are then passed through three spectral transformer and three spatial transformer modules to perform a comprehensive extraction of both spatial and spectral characteristics. Finally, the residual local feature module is utilized during the image reconstruction part to deeply extract intricate information from the images and obtain the final HRMS fused image. We have conducted both simulated and real experiments on the benchmark datasets QB and WV2. The final qualitative and quantitative comparative results demonstrate that our innovative method outperforms the current SOTA methods.

Remote sensing change detection (CD) networks have been increasingly powerful with the application of convolutional neural networks (CNNs) and transformers. The CNN-based CD method with a CNN backbone has been widely used and plays an significant role. In complex spatial relationships within remote sensing images, CNNs may face limitations due to the restricted receptive field, making it challenging to handle intricate pixel relationships effectively. Therefore, to address this limitation of CNNs, we introduce vision graph neural network (ViG) to tackle the constrained receptive field issue. In addition, we propose a backbone network named Congraph, which integrates convolution and graph interaction. Congraph simultaneously leverages local information from CNNs and global information from GNNs, enabling more comprehensive feature extraction for more accurate change detection. Furthermore, we introduce a multiscale mixed attention (MMA) module to make the model focus on different scale feature information. MMA replaces small-scale features in the multilayer encoder with self-attention to capture global feature information within small-scale features. Finally, we feed bitemporal features into a transformer module to obtain feature difference information and generate the ultimate feature difference map. Through extensive experiments on the LEVIR-CD, WHU-CD, and GZ-CD datasets, our method demonstrates more significant performance advantages compared to the current state-of-the-art change detection methods.

In the current remote sensing segmentation tasks, we identify issues of insufficient accuracy in segmenting objects and types with similar colors, along with a lack of adequate smoothness and coherence in edge segmentation. To address these challenges, we propose a network framework called the multielement-feature-based hierarchical context integration network (MHCINet). This framework achieves deep integration of global information, local information, multiscale information, and edge information. First, we introduce an Edge and Levels Grouped Aggregator to fuse shallow features, deep features, and edge information, enhancing foreground saliency. Finally, to better identify instances with similar colors during the feature reconstruction stage, we design a constant multivariate feature integrator to fully exploit multiscale information and global context, thereby improving the segmentation model's performance. Comprehensive experimental results on the Vaihingen and Potsdam datasets demonstrate that MHCINet outperforms existing state-of-the-art methods, achieving mean intersection over union of 84.8% and 87.6% on the Vaihingen and Potsdam datasets, respectively.

In recent years, change detection (CD) methods have faced challenges in being applied to various types of remote sensing datasets and related research fields, particularly in the domain of CD in remote sensing images. While convolutional neural networks (CNNs) have significantly advanced CD in remote sensing images, they struggle with modeling long-distance dependencies between image pairs, leading to poor recognition of semantically similar objects with different features. Meanwhile, transformer technology has gained widespread popularity for global applications, but it lacks in extracting local features effectively. Current approaches typically rely on single or dual-branch network structures for mining change-related features in remote sensing images, yet they still lack in extracting both local and global features comprehensively. To address these issues, this article proposes a triple-branch network combining transformer and CNN, comprising CNN, transformer, and channel feature-guided branch. These branches extract and fuse three types of change features from both global and local perspectives. Importantly, the channel feature-guided branch is introduced to capture continuous and detailed change relationship features, thus enhancing the model's change discrimination ability. Experimental results on three datasets (LEVIR-CD, WHU-CD, and GZ-CD) demonstrate the superior performance of the model over state-of-the-art methods.

In current remote sensing segmentation tasks, the difficulty of segmenting spectrally similar objects is a significant issue. Solving this problem is crucial for improving segmentation accuracy. Traditional image-domain segmentation methods rely on color and texture features, but spectrally similar objects have negligible color differences, leading to suboptimal segmentation results. To address this, we propose a network framework called Correlated Mapping Attention Cooperative Network (CMACNet) by extending the problem from the image domain to the feature domain. Image-domain methods depend on color and texture features, whereas feature-domain methods process higher-level abstract features, avoiding issues caused by color similarity. Specifically, CMACNet first employs an autoencoder structure. The autoencoder compresses the input data and attempts to reconstruct the original data, ensuring that the latent space representations capture essential and representative features of the input data, thereby extracting highly generalized and versatile features. Next, we introduce the correlated mapping attention mechanism, which adaptively adjusts the attention to different features based on their correlations, effectively addressing the challenge of segmenting spectrally similar objects. Furthermore, to efficiently establish global relationships among features, we design a cross global interaction layer for global feature remapping. Comprehensive experiments on the Vaihingen and Potsdam datasets demonstrate that CMACNet outperforms existing state-of-the-art methods, achieving mean intersection over union scores of 84.77% and 87.69%, respectively.

The goal of pansharpening is to fuse a high spatial resolution panchromatic (PAN) image with a lower spatial resolution multispectral (MS) image to produce a high-resolution multispectral image. Most deep learning-based methods consider only local or global features, and focusing solely on one type of feature may limit the network's representational capacity. In addition, the fusion process often overlooks the heterogeneous and complementary information unique to PAN and MS images. Therefore, we propose a prompt-driven dynamic adaptive fusion network. To better combine the advantages of local and global features, we introduce a local and global adaptive modulation module. We also innovatively propose a prompt-driven dynamic fusion module that effectively integrates unique heterogeneous information while reconstructing corresponding complementary information. Finally, an expert mixing mechanism is employed to enhance the fused features, achieving superior fusion results. Our proposed method outperforms recent pansharpening methods, as demonstrated by reduced-resolution experiments and full-resolution validation.

In recent years, the field of remote sensing change detection (RSCD) has experienced transformative advancements through the application of convolutional neural networks (CNNs). However, inconsistencies in image quality, noise, and pseudochanges caused by variations in illumination, climate, and surface conditions due to different acquisition times pose significant challenges. Addressing these issues, this study increases traditional RSCD methodologies by introducing a novel temporal interaction and multiscale fusion network (TIMF-Net). TIMF-Net incorporates a temporal interaction and difference enhancement module (TIDEM) that effectively extracts and augments change information within images. This module deeply integrates temporal information through a weighted fusion strategy, not only capturing the juxtaposition and superposition relationships between images but also unraveling complex feature representations to ensure accurate alignment and coupling of features across different periods. Additionally, we propose a multiscale global-aware (MSGA) module, which attends to both local details and global contextual information, integrating pixel-level features and demonstrating heightened sensitivity to multiscale changes such as path alterations, water fluctuations, and agricultural variations. TIMF-Net outperforms mainstream and state-of-the-art methods on three datasets, achieving an F1 score of 91.96% and intersection over union (IoU) of 85.12% on the LEVIR-CD dataset, an F1 of 93.37% and IoU of 87.56% on the WHU-CD dataset, and an F1 of 87.12% and IoU of 77.19% on the GZ-CD dataset, with 27.64 M Params and 42.8 G FLOPs.

Remote sensing change detection has achieved amazing results in recent years, especially the application of convolutional neural networks (CNN) and Transformer networks, which have revolutionized the field. However, the complex ground cover changes and the differences in lighting conditions caused by different times still pose challenges to the detection accuracy. In order to further extract spatial feature information and suppress irrelevant influences, we innovatively propose an edge-enhanced and time-synchronized remote sensing change detection network, called CNN and transformer-based spatio-temporally synchronized network (CTST). CTST designs a unique feature-integrated coding model with CNN and Transformer architectures, which enhances the model's understanding of the global dependencies and the extraction effect of the local features through the dynamic weight allocation method. We designed the edge salient feature enhancement module, which uses a dual operator fusion structure to combine the edge semantic information with the depth feature information, greatly enhancing the model's ability to recognize the edges of important terrain and features in remote sensing images. In addition, the spatio-temporally synchronized module is used to fuse the difference and superposition relationships between bitemporal features, and an innovative correlation mapping weighting algorithm is proposed to evaluate the similarity and difference of the fused features. Finally, the feature decoding complementary module is proposed to combine and complement features at different scales to further refine the already fused bichronological remote sensing features. The network results are optimized by the deep supervision (DS) strategy, which ensures the model's high efficiency and accuracy. CTST outperforms mainstream and state-of-the-art methods on all three datasets, with an F1 of 92.08% and an IoU of 85.33 on the LEVIR-CD dataset, an F1 of 93.25% and an IoU of 87.36% on the WHU-CD dataset, and an F1 of 93.25% and an IoU of 87.36% on the GZ-CD dataset. CD dataset the F1 is 85.95% and IoU is 75.37%, Param is 31.87 M, and FLOPS is 29.58 G.

In remote sensing image segmentation tasks, various challenges arise, including difficulties in recognizing objects due to differences in perspective, difficulty in distinguishing objects with similar colors, and challenges in segmentation caused by occlusions. To address these issues, we propose a method called the grouped multiview aggregation network (GVANet), which leverages multiview information for image analysis. This approach enables global multiview expansion and fine-grained cross-layer information interaction within the network. Within this network framework, to better utilize a wider range of multiview information to tackle challenges in remote sensing segmentation, we introduce the multiview feature aggregation block for extracting multiview information. Furthermore, to overcome the limitations of same-level shortcuts when dealing with multiview problems, we propose the channel group fusion block for cross-layer feature information interaction through a grouped fusion approach. Finally, to enhance the utilization of global features during the feature reconstruction phase, we introduce the aggregation-inhibition-activation block for feature selection and focus, which captures the key features for segmentation. Comprehensive experimental results on the Vaihingen and Potsdam datasets demonstrate that GVANet outperforms current state-of-the-art methods, achieving mIoU scores of 84.5% and 87.6%, respectively.

With the remarkable success of change detection (CD) in remote sensing images in the context of deep learning, many convolutional neural network (CNN) based methods have been proposed. In the current research, to obtain a better context modeling method for remote sensing images and to capture more spatiotemporal characteristics, several attention-based methods and transformer (TR)-based methods have been proposed. Recent research has also continued to innovate on TR-based methods, and many new methods have been proposed. Most of them require a huge number of calculation to achieve good results. Therefore, using the TR-based mehtod while maintaining the overhead low is a problem to be solved. Here, we propose a GNN-based multi-scale transformer siamese network for remote sensing image change detection (GMTS) that maintains a low network overhead while effectively modeling context in the spatiotemporal domain. We also design a novel hybrid backbone to extract features. Compared with the current CNN backbone, our backbone network has a lower overhead and achieves better results. Further, we use high/low frequency (HiLo) attention to extract more detailed local features and the multi-scale pooling pyramid transformer (MPPT) module to focus on more global features respectively. Finally, we leverage the context modeling capabilities of TR in the spatiotemporal domain to optimize the extracted features. We have a relatively low number of parameters compared to that required by current TR-based methods and achieve a good effect improvement, which provides a good balance between efficiency and performance.

Background: Edge accuracy and positional accuracy are the two goals pursued by medical image segmentation. In clinical medicine diagnosis and research, these two goals enable medical image segmentation techniques to help in the effective determination of lesions and lesion analysis. At present, U-Net has become the most important network in the field of image segmentation, and the technologies used in various achievements are derived from its architecture, which also proves from practice that the network structure proposed by U-Net is effective. Objective: We have found in a large number of experiments that classical networks indeed show good performance in the field of medical segmentation, but there are still some deficiencies in edge determination and network robustness, especially in the face of blurred edges, the processing results often fail to achieve the expected results. In order to be able to locate segmentation targets and achieve effective determination of blurred edges, a Multiscale Spatial Attention Network (MSA-Net) is proposed as in Fig. 1. Method: In MSA-Net, the Multiscale Pyramid Attention Block (MPAB) is created to enhance the capture of high-level semantic information. In addition, the network uses ASPP, which not only expands the network’s field of view, but also captures richer feature information. In the decoding phase, the Feature Fusion Block (FFB) is created to enable better focus on different dimensional information features and to enhance the feature fusion process. Result: To demonstrate the effectiveness of the network, we validate the performance of MSA-Net on four datasets (ISIC2016, DSB2018, JSRT, GlaS) in three different categories. Compared with mainstream networks, MSA-Net shows better results in detail features, target localization, and edge processing. Finally, we also demonstrate the effectiveness of the MSA-Net architecture through ablation experiments.

Abstract When the lighting conditions are poor and the environmental light is weak, the image captured by the imaging device often has lower brightness and is accompanied by a lot of noise. The paper designs a progressive self‐calibration network model (PSCNet) for recovering high‐quality low‐light‐enhanced images. First, shallow features in low‐light images can be better focused and extracted with the help of attention mechanism. Next, the feature mapping is passed to the encoder and decoder modules, where the transformer and encoder‐decoder jump connection structures can be better combined with the semantic information of the context to learn rich deep feature information. Finally, the self‐calibration module can adaptively cascade the features decoded by the decoder and input them into the residual attention module quickly and accurately. Meanwhile, the LBP features of the image are also fused into the feature information of the residual attention module to enhance the detailed texture information of the image. Qualitative analysis and quantitative comparison of a large number of experimental results show that this method outperforms existing methods.

Change detection based on remote sensing data is an important method to detect the earth surface changes. With the development of deep learning, convolutional neural networks have excelled in the field of change detection. However, the existing neural network models are susceptible to external factors in the change detection process, leading to pseudo change and missed detection in the detection results. In order to better achieve the change detection effect and improve the ability to discriminate pseudo change, this article proposes a new method, namely, transformer-based context information aggregation network for remote sensing image change detection. First, we use a filter-based visual tokenizer to segment each temporal feature map into multiple visual semantic tokens. Second, the addition of the progressive sampling vision transformer not only effectively excludes the interference of irrelevant changes, but also uses the transformer encoder to obtain compact spatiotemporal context information in the token set. Then, the tokens containing rich semantic information are fed into the pixel space, and the transformer decoder is used to acquire pixel-level features. In addition, we use the feature fusion module to fuse low-level semantic feature information to complete the extraction of coarse contour information of the changed region. Then, the semantic relationships between object regions and contours are captured by the contour-graph reasoning module to obtain feature maps with complete edge information. Finally, the prediction model is used to discriminate the change of feature information and generate the final change map. Numerous experimental results show that our method has more obvious advantages in visual effect and quantitative evaluation than other methods.

The self-attention mechanism can break the limitation of the receptive field, model in a global scope, and extract global information efficiently. In this work, we propose a lightweight remote sensing building change detection model (ESACD). In the encoder, we use the enhanced self-attention layer, CoT layer, instead of the normal convolution operation. The CoT layer fuses the dynamic context with the static context. Compared with the ordinary convolutional layer, this strategy can fully mine the local features between the input keys to dynamically enhance the feature representation. Subsequently, we use dual attention to further mine the low-frequency information and high-frequency information of the images and the semantic features of interest to the model. Dual attention consists of the HiLo attention mechanism and the Tokenizer attention mechanism. HiLo extracts high-frequency information and low-frequency information through two branches. In the high-frequency branch, nonoverlapping windows are applied to the features for self-attention. In the low-frequency branch, average pooling is first performed on features before self-attention. After Tokenizer attention extracts the feature tokens that the model is interested in, it encodes its information and, then, converts the tokens into pixel-level features. Tokenizer attention realizes the efficient extraction of features and enhances the representation ability of the model. Finally, we fuse feature information to enhance the fluidity of information and improve accuracy. Through our experiments on two change detection datasets, ESACD has better performance than other state-of-the-art methods while maintaining fewer parameters.

Remote sensing change detection is an important research direction in the field of remote sensing. It is mainly used to focus on the changing information on the ground over a period of time, and to identify the interested change targets from it. The rapid changes in ground information due to social development undoubtedly increase the importance of change detection. Currently, change detection methods still have some shortcomings in dealing with complex targets, environmental noise, and other aspects. Therefore, we propose a differential feature extraction network based on adaptive frequency transformer for remote sensing change detection (DAFT). Adaptive frequency transformer (AFFormer) is capable of separating change targets and environments from a frequency perspective and capturing long-range dependencies between feature information through self-attention. Therefore, in DAFT, we use AFFormer as the backbone network to extract feature information from bitemporal images, enhancing our focus on change targets while obtaining richer and more detailed information. To our knowledge, this is the first time that AFFormer has been applied in the field of CD. To address the issues of missing location information of change targets and insufficient local feature correlation, DAFT proposes a differential features enhancement module in the feature reconstruction stage of change targets. In addition, DAFT uses DO-Conv to enhance pixel correlation calculation in convolutional operations, allowing the network to focus on richer information. By outputting results at different scales during the feature reconstruction stage, DAFT computes multiple losses that are summed up to guide the training process for better performance. The experimental results prove that DAFT achieves high versus mainstream networks. On LEVIR-CD the F1 is 91.814 and the IoU is 84.866; on WHU-CD the F1 is 92.085 and the IoU is 85.330; on GZ-CD the F1 is 86.065 and the IoU is 74.512.

Detecting changes in two remote sensing images of the same region but at different times is of great significance in applications, such as land management and urban planning, which also prompts the continuous development and progress of change detection (CD) technology. The current deep learning-based methods make full use of the excellent feature learning ability of deep convolution to show excellent detection performance. However, advances in remote sensing technology also mean that detected objects have higher resolution and more complex content, which is more challenging for CD techniques. Strengthening the model's ability to learn the context of the detected remote sensing image can effectively improve the model's ability to distinguish between changing features and nonchanging features, thereby achieving higher-precision detection results. In order to explore and utilize the contextual information of different levels of features as much as possible, we design a dual-attention cross fusion module in our method to realize the cross-learning of contextual information of different scales during the decoding process. It will be able to complementarily fuse feature content of different granularities. We also propose an Atrous Pyramid Difference Module (APDM) to efficiently capture the difference information of two refined features by exploiting receptive fields of different sizes. In addition, in order to further improve the context modeling ability of the model, we introduce a context transformer block (Cot). Different from other transformer-based self-attention methods, Cot dynamically guides the learning of the attention matrix by the contextual information of the input keys. Our method achieves F1-scores of 91.08%/91.93%/79.80% on the LEVIR-CD/WHU-CD/DSIFN-CD datasets, respectively. Extensive qualitative and quantitative experiments on these datasets validate the effectiveness of our method.

Rice (Oryza sativa L.) is a staple food that feeds over half of the world's population, and the contents of metallic elements in rice grain play important roles in human nutrition. In this study, the contents of important metallic elements were determined by ICP-OES, and included cadmium (Cd), zinc (Zn), manganese (Mn), copper (Cu), iron (Fe), nickel (Ni), calcium (Ca), and magnesium (Mg) in brown rice, in the first node from the top (Node 1), in the second node from the top (Node 2), and in roots of 55 hybrids and their parental lines. The heritability of metallic element contents (MECs), the general combining ability (GCA) for MEC, and the correlation between MECs in different organs/tissues of hybrids were also analyzed. The results indicated that: (1) there was a positive correlation between the contents of Cd and Zn in nodes and roots, but a negative correlation between the contents of Cd and Zn in brown rice of the hybrids(2) the GCA for MECs can be used to evaluate the ability of the parental lines to improve the metal contents in brown rice of the hybrids(3) the contents of Cd, Zn, Ca, and Mg in brown rice were mainly affected by additive genetic effects(4) the restorer lines R2292 and R2265 can be used to cultivate hybrids with high Zn and low Cd contents in the brown rice.

ObjectiveTo deal with the external time-variance disturbances and possible failure of actuators during the dynamic positioning operation of an unmanned underwater vehicle (UUV), this paper proposes a nonlinear observer-based adaptive allocation strategy to achieve thruster fault tolerance. MethodThe control scheme is first established by means of the power sliding mode control technique to obtain the dynamic position. Meanwhile, a nonlinear disturbance observer is designed to estimate external disturbances. Then, based on the estimated external disturbance and state deviation sequence under the failure mode, a quadratic programming problem is constructed and solved to obtain the efficiency factor of each thruster, and the thrust distribution matrix is modified to achieve adaptive control allocation under thruster fault tolerance. ResultsThe simulation results show that the UUV control system can effectively estimate external environmental disturbances and the efficiency factor of each thruster. Even if the actuator fails, the UUV can still accomplish its dynamic positioning mission. ConclusionThe results of this study show that the proposed adaptive thruster allocation and sliding mode control algorithm is reasonable and can be effectively applied to UUVs under external environmental disturbances and actuator failure.

Abstract In realistic low‐light environments, images captured by imaging devices often have problems such as low brightness and low contrast, serious loss of detail information, and a large amount of noise, posing major challenges to computer vision tasks. Low‐light image enhancement can effectively improve the overall quality of the image, which has important significance and application value. In this study, an attention‐based multi‐channel feature fusion enhancement network (M‐FFENet) is proposed to process low‐light images. In this network, a feature extraction model is first used to obtain the deep features of the downsampled low‐light images and fit them to an affine bilateral grid. Second, the addition of attention‐based residual dense blocks (ARDB) allows the network to focus on more details and spatial information. Meanwhile, all color channels are considered. The channel features and bilateral meshes are then linearly interpolated using the feature reconfiguration model (FRM) to obtain high‐quality features containing rich color and texture information. Next, the feature fusion module (FFM) is used to fuse features that contain different information. Enhancement model is used to further recover texture and detail in the image. Finally, the enhanced image is output. Numerous experimental results have shown that the method achieves better results in both quantitative and qualitative aspects compared to other methods.

Abstract Free space detection is a very important task in road scene understanding. With the continued development of convolutional neural networks, free‐space detection can be seen as a class‐specific semantic segmentation problem. In this paper, a new encoding–decoding network structure‐HRUnet is designed, which always maintains the input of high‐resolution images in both the encoding and decoding phases. It extracts multi‐scale information from RGB images and continuously fuses them, and finally achieves accurate spatial detection. In addition, in order to improve the accuracy of detection, the attention mechanism module‐spin attention is proposed to achieve the interaction between channel and spatial dimensions when calculating channel attention, establish the come relationship between channel and space, reduce the loss of feature information, and further improve the accuracy of spatial detection. Experimental results show that the proposed neural network structure outperforms current popular models in terms of balanced the computational complexity and accuracy.

The convolutional neural network, as the backbone network for medical image segmentation, has shown good performance in the past years. However, its drawbacks cannot be ignored, namely, convolutional neural networks focus on local regions and are difficult to model global contextual information. For this reason, transformer, which is used for text processing, was introduced into the field of medical segmentation, and thanks to its expertise in modelling global relationships, the accuracy of medical segmentation was further improved. However, the transformer-based network structure requires a certain training set size to achieve satisfactory segmentation results, and most medical segmentation datasets are small in size. Therefore, in this paper we introduce a gated position-sensitive axial attention mechanism in the self-attention module, so that the transformer-based network structure can also be adapted to the case of small datasets. The common operation of the visual transformer introduced to visual processing when dealing with segmentation tasks is to divide the input image into equal patches of the same size and then perform visual processing on each patch, but this simple division may lead to the destruction of the structure of the original image, and there may be large unimportant regions in the divided grid, causing attention to stay on the uninteresting regions, affecting the segmentation performance. Therefore, in this paper, we add iterative sampling to update the sampling positions, so that the attention stays on the region to be segmented, reducing the interference of irrelevant regions and further improving the segmentation performance. In addition, we introduce the strip convolution module (SCM) and pyramid pooling module (PPM) to capture the global contextual information. The proposed network is evaluated on several datasets and shows some improvement in segmentation accuracy compared to networks of recent years.

How to efficiently and accurately identify and extract the focused regions in the source image is a difficult problem in the field of multi-focus image fusion. The existing fusion methods suffer from color distortion, loss of detail information, and high time cost, which limit the subsequent processing and real-time application of fused images. Based on this, this paper proposes a multi-focus image fusion method based on Transformer and feedback mechanism. The method uses a combination of Transformer and convolutional neural network, and integrates the local information extracted by CNN and the global information obtained by transformer, which improves the accuracy of focus region identification. In addition, this paper uses a feedback mechanism to provide more contextual information so that the features can be fully utilized, which improves the performance of the network in feature fusion. This paper conducts comparison tests with seven advanced fusion methods on the Lytro and Grayscale datasets, and the results show that the algorithm in this paper is superior in both subjective and objective evaluations.

Abstract Hazy images often have color distortion, blur and other visible visual quality degradation, affecting the performance of some advanced visual tasks. Therefore, single image dehazing has always been a challenging and significant problem. Convolutional neural network has been widely used in image dehazing task, but the limitations of convolutional operation limit the development of dehazing task. Nowadays, Transformer offers a holistic approach to CV development and does not grow in location as the network deepens. For this reason, a hierarchical Transformer is introduced for use in the dehazing network. Specifically, the codec is improved and Transformer and CNN are combined to achieve basic feature extraction in the first stage. The encoder only models the global relationship at each layer, reducing the resolution of the feature map continuously and expanding the field of perception. In addition, an inter‐block supervision mechanism is added between encoder unit and decoder unit to refine features and supervise and select them, thus improving the efficiency of feature transmission. In the second stage, the original resolution block is used to extract the local features, and then feature fusion and interaction are carried out. In addition, to ensure the authenticity of the transmission of characteristic signals in the first stage and improve the transmission efficiency of the network, fusion attention mechanism is added between stages. It adds the residual image of the early input features to the image acquired in the first stage, then passes to the next stage. Ablation experiments show that the two‐stage network has significant benefits for image quality and visual effects. The experimental results on RESIDE, O‐Haze, and I‐Haze datasets show that the method is superior to advanced methods in dehazing effectiveness.

Let $ \mathcal{P}_r $ denote an almost–prime with at most $ r $ prime factors, counted according to multiplicity. In this paper, it is proved that for every sufficiently large even integer $ N $, the following equation $ \begin{equation*} N = p_1^2+p_2^2+x^3+p_3^3+p_4^3+p_5^3 \end{equation*} $ is solvable with $ x $ being an almost–prime $ \mathcal{P}_7 $ and the other variables primes. This result constitutes a deepening upon that of previous results.

Abstract At night or in other low‐illumination environments, optical imaging devices cannot capture details and color information in images accurately because of the reduced number of photons captured and the low signal‐to‐noise ratio. Consequently, the image is very noisy with low contrast and inaccurate color information, which affects human visual perception and creates significant challenges in computer vision tasks. Low‐light image enhancement has great research value because it aims to reduce image noise and improve image quality. In this study, we propose an LBP‐based progressive feature aggregation network (P‐FANet) for low‐light image enhancement. The LBP feature has insensitivity to illumination, and it contains rich texture information. In the network, we input the LBP feature into each iteration of the network in an accompanying manner, which helps to restore some detailed information of the low‐light image. First, we input the low‐light image into the dual attention mechanism model to extract global features. Second, the extracted different features enter the feature aggregation module (FAM) for feature fusion. Third, we use the recurrent layer to share the features extracted at different stages, and use the residual layer to further extract deeper features. Finally, the enhanced image is output. The rationality of the method in this study has been verified through ablation experiments. Many experimental results show that the method in this study has greater advantages in subjective and objective evaluations compared with many other advanced methods.

Automatic extraction of water bodies from various satellite images containing complex targets is a very important and challenging task in remote sensing and image interpretation. In recent years, convolutional neural networks (CNNs) have become an important choice in the field of semantic segmentation of remote sensing images. However, generic CNN models present many problems when performing water body segmentation, such as: 1) blurred water body boundaries; 2) difficulty in accommodating different scales of rivers, often losing information about many small-scale rivers; and 3) a large number of trainable parameters. This article proposes an end-to-end CNN structure based on multiscale residuals and squeeze-and-excitation (SE)-attention for water segmentation, called MRSE-Net. MRSE-Net consists of an encoder–decoder and a skip connection, which captures contextual information at different scales using the encoder, and then passes the encoder feature mapping through the improved skip connection, while localization is achieved by the decoder is implemented. With the multiscale residual module, the number of parameters in our model can be significantly reduced and water pixels can be extracted accurately. The SE-attention module is used to enhance the prediction results, mitigate the blurring effect, and make the segmented water boundaries more continuous. Landsat-8 images are used to train our model and validate our proposed method’s performance and effectiveness. In addition, we evaluate our method on Landsat-7 and Sentinel-2 images and obtain the best water segmentation results. Preliminary results on Sentinel-2 images show that the cross-sensor generalization capability of our model is beyond the range of the Landsat sensor family.

In order to solve the single imaging problem of remote sensing satellites, pan-sharpening technology is proposed. By fusing multispectral (MS) images and panchromatic (PAN) images, high-resolution multispectral resulting images are obtained. There is an urgent need to solve the problem of how to achieve higher spatial and spectral resolution in fused images. We propose an dual attention based dual regression network (DADR) architecture. The DADR network is mainly divided into three stages: feature extraction and feature fusion, image reconstruction, and dual regression network. Residual channel attention module (RCAM) and effective channel attention module (ECA) are added to the backbone network, so that the network can learn important spectral and spatial information and improve the ability of the network to retain information. The dual regression network solves the problem of adaptive and poor performance generated by the image reconstruction model. Because the dual regression network learns directly from feature fusion images, our model can better adapt to the data in real scenes and has stronger generalization ability. A series of experiments were conducted on GF-2, QB, and WV2 datasets, respectively. The validity of the DADR method was verified by quantitative comparison and qualitative analysis. Meanwhile, extensive experiments demonstrate that the DADR method is superior to other existing advanced pan-sharpening methods.

Abstract Owing to the influence of light absorption and scattering in underwater environments, underwater images exhibit color deviation, low contrast and detail blur, and other degradations. This paper proposes an underwater image enhancement method combining a residual convolution network, local binary pattern (LBP), and self‐attention mechanism. The LBP operator processes the input underwater images. The LBP feature images and underwater images thus obtained constitute the network input. The network consists of three modules: a color correction module to remove the color deviation in underwater images, detail repair module to restore the integrity of details, and an LBP auxiliary enhancement module for global enhancement of image details. The correction and repair modules generate the correct color image and detailed supplement images, respectively. The final‐result image is obtained by superpositioning the two generated images. The experimental results confirm that our method can reproduce the bright colors and complete details of the visual effect, showing a significant improvement over other advanced methods in quantitative evaluation.

Background: In recent years, computer-assisted diagnosis of patients is an increasingly common topic. Multi-organ segmentation of clinical Computed Tomography (CT) images of the patient’s abdomen and magnetic resonance images (MRI) of the patient’s heart is a challenging task in medical image segmentation. The accurate segmentation of multiple organs is an important prerequisite for disease diagnosis and treatment planning. Methods: In this paper, we propose a new method based on multi-organ segmentation in CT images or MRI images; this method is based on the CNN-Transformer hybrid model, and on this basis, a progressive sampling module is added. Results: We performed multi-organ segmentation on CT images and MRI images provided by two public datasets, Synapse multi-organ CT dataset (Synapse) and Automated cardiac diagnosis challenge dataset (ACDC). By using Dice Similarity Coefficient (DSC) and Hausdorff_95 (HD95) as the evaluation metric for the Synapse dataset. For the Synapse dataset of CT images, the average DSC reached 79.76%, and the HD95 reached 21.55%. The DSC indicators of Kidney(R), Pancreas, and Stomach reached 80.77%, 59.84%, and 81.11%, respectively. The average DSC for the ACDC dataset of MRI images reaches 91.8%, far exceeding other state-of-the-art techniques. Conclusion: In this paper, we propose a multi-sampled vision transformer MPSHT based on the CNN-Transformer structure. The model has both the advantages of CNN convolutional network and Transformer, and at the same time, the addition of a progressive sampling module makes the model’s segmentation of organs more accurate, making up for the shortcomings of the previous CNN-Transformer hybrid model.

Let $ N $ be a sufficiently large integer. In this paper, it is proved that, with at most $ O\big(N^{4/9+\varepsilon}\big) $ exceptions, all even positive integers up to $ N $ can be represented in the form $ p_1^2+p_2^3+p_3^3+p_4^3+p_5^3+p_6^3 $, where $ p_1, p_2, p_3, p_4, p_5, p_6 $ are prime numbers.

Remote sensing change detection (CD) is to use multitemporal remote sensing data to extract change information by using a variety of image processing and pattern recognition methods, and quantitatively analyze and determine the characteristics and processes of surface changes. In recent research on CD, how to more accurately segment objects and how to extract and effectively link spatiotemporal information are important parts. To achieve this, we propose a progressive sampling (PS) transformer network for remote sensing image CD, which continuously extracts and optimizes feature information in an iterative manner, so that pixels can establish better connections in the spatial domain to model the context. Our intuition is that, through this iterative sampling method, the parts of interest in the image can be gradually extracted. This allows subsequent processing to be more focused on useful areas, which in turn reduces interference from uninteresting parts, and the information after PS will be generalize into several tokens containing rich semantic information. Using the excellent modeling ability of the transformer, the optimized tokens are mapped back to the original image features to achieve the purpose of segmenting accurate difference images. We conducted extensive experiments on three CD datasets, LEVIR-CD, DSIFN-CD, and WHU-CD, and achieved evaluation scores of 90.73/84.11, 80.10/68.93, and 91.67/85.15 on F1-score and IoU metrics, respectively. Notably, the convolutional neural network (CNN) backbone of our network uses only a simplified ResNet model, without using structurally complex frameworks, such as FPN and Unet, but our model uses PS module and transformer to achieve better performance than the recent advanced CD models.

Abstract Depth of field is one of the critical reasons to limit the richness of image information. Usually, in a scene with multiple targets, when the distance between each target and the lens is different, the clear scene image can be get within a certain distance range. This situation restricts the further image processing, such as semantic segmentation, object recognition and 3D reconstruction. Multi‐focus image fusion uses two or more images focused on different targets to fuse scene information, which can solve this problem to a great extent. In general, two or more multi‐focus images can cover almost all near/far targets. The fusion of more than two multi‐focus images can be accomplished by cascading the fusion results of the previous two images and the next image to be processed many times. Therefore, the paper focus on the fusion of two multi‐focus images. Inspired by this, new Pseudo‐Siamese neural network with several residual atrous convolution pyramids with multi‐level perception ability to perceive the multi‐level features and consistency relations of multi‐focus image pairs is proposed, and multi‐layer residual blocks are used to fuse the extracted features. In this process, the residual of the groundtruth and the generated image will be learned. Finally, a fully focused image without blur will be generated. After several ablation experiments and comparison experiments with other methods, the results show that the performance of the method proposed in this paper is state‐of‐the‐art, and overall better than other methods, which are advanced.

Abstract Due to insufficient illumination in low‐light conditions, the brightness and contrast of the captured images are low, which affect the processing of other computer vision tasks. Low‐light enhancement is a challenging task that requires simultaneous processing of colour, brightness, contrast, artefacts and noise. To solve this problem, the authors apply the deep residual network to the low‐light enhancement task, and propose a hierarchical guided low‐light enhancement network. The key of this method is recombined hierarchical guided features through the feature aggregation module to realize low‐light enhancement. The network is based on the U‐Net network, and then hierarchically guided with the input pyramid branch in the encoding and decoding network. The input pyramid structure realizes multi‐level receptive fields and generates a hierarchical representation. The encoding and decoding structure concatenates the hierarchical features of the input pyramid and generates a set of hierarchical features. Finally, the feature aggregation module is used to fuse different features to achieve low‐light enhancement tasks. The effectiveness of the components is proved through ablation experiments. In addition, the authors are also evaluating on different data sets, and the experimental results show that the method proposed is superior to other methods in subjective and objective evaluation.

IntroductionThe seriously degraded fogging image affects the further visual tasks. How to obtain a fog-free image is not only challenging, but also important in computer vision. Recently, the vision transformer (ViT) architecture has achieved very efficient performance in several vision areas.MethodsIn this paper, we propose a new transformer-based progressive residual network. Different from the existing single-stage ViT architecture, we recursively call the progressive residual network with the introduction of swin transformer. Specifically, our progressive residual network consists of three main components: the recurrent block, the transformer codecs and the supervise fusion module. First, the recursive block learns the features of the input image, while connecting the original image features of the original iteration. Then, the encoder introduces the swin transformer block to encode the feature representation of the decomposed block, and continuously reduces the feature mapping resolution to extract remote context features. The decoder recursively selects and fuses image features by combining attention mechanism and dense residual blocks. In addition, we add a channel attention mechanism between codecs to focus on the importance of different features.Results and discussionThe experimental results show that the performance of this method outperforms state-of-the-art handcrafted and learning-based methods.

Abstract Aiming at the problems of residual noise, low contrast, and limited detail information caused by low‐light images, this paper proposes a new Retinex variational model. According to Retinex theory, it is necessary to estimate the illumination and reflectance components decomposed from the original image. In order to better maintain the edge information, texture richness, and prevent artefacts, the exponential forms of local variation deviation and total variation are used as illumination prior and reflectance prior, respectively, and mixed norms are used to constrain them, so as to deal with the illumination information and texture details of the image more effectively, and then use the bright channel prior to improve the colour reproduction sense of the original image, thereby constructing the objective function, and finally using the alternating iterative optimization method to find the optimal solution to the proposed model. Experiments show that compared with other existing image enhancement methods, the method proposed here improves the contrast of the image, overcomes the phenomenon of halo artefacts and colour distortion, is more consistent with human vision, and produces better results in terms of quantitative performance.

Abstract In a group of images, the recurrent foreground objects are considered as the key objects in the group of images. In co‐saliency detection, these are described as common saliency objects. The aim is to be able to naturally guide the user's gaze to these common salient objects. By guiding the user's gaze, users can easily find these common saliency objects without interference from other information. Therefore, a method is proposed for reducing user visual attention based on co‐saliency detection. Through the co‐saliency detection algorithm and matting algorithm for image preprocessing, the exact position of non‐common saliency objects (called Region of Interest here, i.e. ROI) in the image group can be obtained. In the attention retargeting algorithm, the internal features of the image to adjust the saliency of the ROI areas are considered. In the HSI colour space, the three components H, S, and I are adjusted separately. First, the hue distribution is constructed by the Dirac kernel function, and then the most similar hue distribution to the surrounding environment is selected as the best hue distribution of ROI areas. The S and I components can be set as the contrast difference between ROI areas and surrounding background areas according to the user's demands. Experimental results show that this method effectively reduces the ROI areas' attraction to the user's visual attention. Moreover, comparing this method with other methods, the saliency adjustment effect achieved is much better, and the processed image is more natural.

Abstract In dynamic scene deblurring, recent neural network–based methods have been very successful. But with the improvement of deep deblurring performance, network structure and learning become more complicated. Compared with large‐scale network parameters and complex network structures, an iterative multi‐scale residual network to achieve a more effective parameter sharing scheme is proposed. In each iterative unit, fast multi‐scale residual blocks to replace superimposed convolutional layers or classic residual blocks are used. On the basis of preventing model overfitting, the receptive field of the network is increased. At the same time, the gated recurrent unit is introduced to connect modules of different stages. The model does not rely on the estimation of the blur kernel and directly generates sharp images in an end‐to‐end manner. The experimental structure on the benchmark dataset and real‐world images showed that this method has better quality than the existing methods in terms of large‐scale blur and subjective perception effects, both in quantitative and qualitative terms.

BackgroundPatients with cancer experience multiple symptoms related to cancer, cancer treatment, and the procedures involved in cancer care; however, many patients with pain, depression, and fatigue, especially those outside the hospital, receive inadequate treatment for their symptoms. Using an electronic patient-reported outcome (ePRO) platform to conduct symptom management follow-up in outpatients with advanced cancer could be a novel and potentially effective approach. However, empirical evidence describing in detail the preparation and implementation courses in a real setting is needed. ObjectiveThe purpose of this paper was to describe the implementation process and evaluation of an ePRO platform that facilitates symptom management for patients with cancer, share our experiences and the problems we encountered during the process of implementation, and share the solutions we identified for those problems. Moreover, we tested the feasibility, safety, and efficacy of the ePRO platform. MethodsThis was a real-world, ongoing, longitudinal, single-center, prospective study with a total of 7 follow-ups conducted within 4 weeks after the first visit to the symptom management clinic (on days 1, 3, 7, 10, 14, 21, and 28). Participants were encouraged to complete scales for physical symptoms (pain, fatigue, and shortness of breath), cognitive symptoms (memory problems and impaired concentration), and affective symptoms (especially depression and anxiety) during follow-up. The design and function of the ePRO-doctor client and ePRO-patient client, the patient-reported outcome (PRO) scales used in the study, and the strategies to promote symptom tracking have been described. Moreover, the training and evaluation for research assistants have been presented. The efficacy of the ePRO platform was assessed with a comparison of the baseline and 4-week outcomes on the MD Anderson Symptom Inventory. ResultsUsing the ePRO platform for symptom management follow-ups in advanced cancer patients was associated with a high completion rate (72.7%-86.4%) and a low drop-off rate (23.6%). The ePRO platform sent 293 alert notifications to both patients and doctors, which promoted patient security. The short and sharp PRO tool selection, user-friendly interface, automatic reminder notifications and alerts, and multiple dimensional training were essential components for the preparation and implementation of the ePRO system. The results showed significant improvements in the mean scores of pain, fatigue, and numbness from baseline to day 28 (P=.02, P=.02, and P

Pan-sharpening of remote sensing images is a significant method for integrating remote sensing information in the field of computer vision, where complementary and redundant information between multispectral (MS) images and panchromatic (PAN) images is used to generate high-resolution MS (HRMS) images. Inspired by the remarkable achievements of convolutional neural networks in a variety of computer-vision tasks, we incorporate domain-specific knowledge to design our attention-based triangle UNet (Tri-UNet) architecture to generate high-quality HRMS images. The attention-based Tri-UNet is mainly divided into the following three modules: 1) feature extraction; 2) feature fusion; and 3) image reconstruction. In the feature extraction step, the feature extraction module simultaneously extracts spectral and spatial information from the MS and PAN images. The feature maps are then fused in the feature fusion module, which makes the final feature image contain rich spectral and spatial information. Finally, the image reconstruction module generates a high-resolution MS image that uses the fused image as input. The attention mechanism is introduced into the image reconstruction module to make the network focus more on key information in the feature image. The experimental results demonstrate that the proposed method can generate high-quality HRMS images. A quantitative comparison and qualitative analysis of the experimental results indicate that our method is superior to the existing methods.

Abstract A new method is presented to determine parameter values (knot) for data points for curve and surface generation. With four adjacent data points, a quadratic polynomial curve can be determined uniquely if the four points form a convex polygon. When the four data points do not form a convex polygon, a cubic polynomial curve with one degree of freedom is used to interpolate the four points, so that the interpolant has better shape, approximating the polygon formed by the four data points. The degree of freedom is determined by minimizing the cubic coefficient of the cubic polynomial curve. The advantages of the new method are, firstly, the knots computed have quadratic polynomial precision, i.e., if the data points are sampled from a quadratic polynomial curve, and the knots are used to construct a quadratic polynomial, it reproduces the original quadratic curve. Secondly, the new method is affine invariant, which is significant, as most parameterization methods do not have this property. Thirdly, it computes knots using a local method. Experiments show that curves constructed using knots computed by the new method have better interpolation precision than for existing methods.