Search

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.

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.

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.

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.

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.

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.

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.

In this paper, we propose an Iterative Residual Network. By designing the calculation unit, we put the hazy image into the calculation unit to perform an iterative operation that can stitch the hazy image in stages with the unit output and substitute it into the calculation. After multiple iterations, a clean image can be generated. We introduce Long Short-Term Memory network and Residual ideas in the design process of the computing unit to further optimize the model. The Long Short-Term Memory network can be used to connect computing units at different stages. The use of residual block connection in the deep processing of the computing unit can preserve the original features of the image and prevent the model from overfitting. This model directly generates hazy-free images in an end-to-end manner and does not rely on the estimations of the transmission map and atmospheric light. Experiments show that Iterative Residual Network can effectively remove the haze in the image. In the test of the synthetic dataset and the real dataset, Iterative Residual Network is superior to the existing methods in terms of PSNR, SSIM, FADE and subjective visual effects.

For patients with color vision defects, owing to the destruction of cone cells and loss of function, some color information is lost, hence changing the originally transmitted information by the image. The purpose of the traditional method of correction is to help patients distinguish between colors, but it does not take into account the problem of the saliency of the image. In this paper, we propose a saliency consistency-based image re-colorization for color blindness. We use image retrieval methods to select a large number of images and use co-saliency methods to detect salient areas of standard color images and color-blind simulated images. According to the detection results, an image with the same detection result was selected as the reference image. We grayscale the significantly changed image, recolor the grayscale image using the reference image, and the color scheme of the recolored image is similar to the reference image. The color matching scheme of the reference image makes the significance of the image basically unchanged in standard vision and color vision defects, thereby making the color blindness patient's perception of the image close to standard vision. We invite green blind patients to evaluate CVD simulation images with different recoloring methods subjectively. In addition, we use different evaluation criteria to evaluate the experimental results objectively. In the subjective evaluation and objective evaluation, the method proposed in this paper has achieved good results, which validates the effectiveness of our method.

Truncated singular value decomposition (TSVD) is a simple and efficient technique for patch-based image denoising, in which a hard thresholding operator is utilized to set some small singular values to zero. Before performing the hard thresholding, the noise variance should be accurately estimated in order to determine the rank of the patch matrices. However, when the noise level is high, the denoisied results from the TSVD still contain some residual noise. To solve this problem, we present a hybrid thresheldoing strategy that combines a hard thresholding operator and a soft one. The former is directly reused the thresholding derived from TSVD, the latter is derived by minimum variance estimator. Simulation experiments are conducted to verify the effectiveness of the proposed method. Experimental results show that the method can effectively denoise the images with high level noise.

Remote sensing satellites can provide a large number of multispectral images. However, due to the limitations of optical sensors embedded in satellites, the spatial resolution of multispectral images is relatively low. Pansharpening aims to combine high-resolution panchromatic and multi-spectral images to generate high-resolution multi-spectral images. In this paper, we propose a pansharpening method based on a component substitution framework. We use fractional-order differential operators and guided filter to balance the spectral distortion and spatial information loss that occur when remote sensing image fusion. Fractional-order differentiation can better define the detailed map, and the guided filter can enhance the spectral information of the detailed map. Experiments show that the proposed method in this paper can better combine the spectral information and spatial information, as well as obtain satisfactory results in both subjective visual perception and objective object evaluation.

In this paper, we propose a simple and efficient approach to generate a high-quality trimap from the input image. Most of the state-of-the-art matting algorithms require human intervention in the form of trimap or scribbles to generate the alpha matte from the input image. An attentively created trimap is required to acquire an accurate alpha matte. This is a very tedious task and may even become impractical for some applications. The accuracy of trimap-based approach reduces drastically as the trimap becomes thicker and coarser. We use the co-fusion-based method to generate a high-quality trimap in less time, which assists in obtaining accurate and fast results. The experimental results demonstrate that our method produces good quality trimap, which results in an accurate matte estimation. We validate our results by replacing our generated trimap by manually created trimap while using the same image matting algorithm.

There is a series of image degradation in the image acquired in haze and other weather. The single image dehazing is a challenging and ill-posed problem. Using deep neural network methods, it solves the drawbacks of manually designing haze-related features. This paper proposes a dehazing algorithm using residual-based deep CNN. The network model is divided into two phases: in the first stage, a haze image is input, and the transmission map is estimated by network; in the second stage, the ratio of foggy image and transmission map is used as input, and the residual network is used to remove haze. It avoids the estimation of atmospheric light and improves the efficiency of dehazing. To train the proposed network, we use the NYU2 depth dataset as the training set. In the full-reference metric peak signal to noise ratio, structural similarity, and feature similarity and no-reference metric Spatial-Spectral Entropy-based Quality, Blind/Referenceless Image Spatial Quality Evaluator, and Natural Image Quality Evaluator aspect, the experimental results confirm the efficiency and robustness of the proposed method.

Chinese roses have both ornamental and medicinal value. However, Chinese roses are susceptible to various diseases during their growing process. It is a challenge for growers to promptly detect and control diseases, especially in extensive planting scenarios. A novel disease identification approach for Chinese roses is proposed to help growers accurately determine the severity of Chinese rose diseases so that they can take control of the diseases at the appropriate time. In the proposed approach, which is called MixNet-CA for short, coordinate attention and residual connections are introduced. First, the squeeze-and-excitation attention in MixNet-s is replaced by coordinate attention to enhance the information representation capability of the network and more precisely obtain disease features. Second, residual connections are constructed based on the characteristics of the MixNet-s model to enhance the network representation and prevent overfitting. Finally, reducing the network depth ensures that all network layers are fully trained. The experimental results show that the Chinese rose disease identification accuracy of MixNet-CA is 98.82%, which is 3.4% higher than that of the original MixNet-s model. The MixNet-CA model yields classification precision, recall, and F1 score metrics exceeding 97% for each category. It is also evident from the results that MixNet-CA demonstrates excellent performance compared to other networks, achieving a balance in terms of accuracy, size, the number of parameters, and the number of FLOPs. MixNet-CA also demonstrates good generalization ability on different datasets.

In mobile wireless multimedia sensor networks' image compression task collaborations, the existing methods do not consider the dynamic changes in the processing ability and the locations of the cooperative nodes. when processing the image compression tasks, these methods will cause frequent interruptions and result in data re-transmission for those tasks. in this paper, an image compression task collaboration algorithm based on dynamic alliance is proposed to solve this problem in mobile wireless multimedia sensor networks. first, a dynamic task alliance is established by the camera node based on the location, computing capability and resource usage of ordinary nodes. then, the location and average moving velocity of the camera nodes and ordinary nodes are considered to calculate the task stable execution time. the image compression task is divided into an image transfer sub task and an image compression sub task based on the task stable execution time. finally, an image compression task collaboration allocation optimization model is established according to the transmission time, the execution time, the execution cost, and the network energy consumption. the gradient method is used to realize the cooperative allocation of image compression tasks. simulation results show that the proposed algorithm can realize task load balancing, reduce the execution time, and network energy consumption.