Synthetic aperture radar (SAR) change detection provides a powerful tool for continuous, reliable, and objective observation of the Earth, supporting wide range applications that require regular monitoring assessment changes in natural built environment. In this paper, we introduce novel SAR image method based on principal component analysis two-level clustering. First, two difference images log-ratio mean-ratio operators are computed, then fusion model is used to fuse images, new generated....

A super-resolution (SR) method based on compressive sensing (CS), structural self-similarity (SSSIM), and dictionary learning is proposed for reconstructing remote images. This aims to identify a that represents high resolution (HR) image patches in sparse manner. Extra information from similar structures which often exist images can be introduced into the dictionary, thereby enabling an HR reconstructed using CS framework. We use K-Singular Value Decomposition obtain orthogonal matching...

In the field of remote sensing, due to memory consumption and computational burden, single-image super-resolution (SISR) methods based on deep convolution neural networks (CNNs) are limited in practical application. To address this problem, we propose a lightweight feature enhancement network (FeNet) for accurate remote-sensing image (SR). Considering existence equipment with extremely poor hardware facilities, further design lighter FeNet-baseline about 158K parameters. Specifically,...

Multi-focus image fusion plays an important role in the application of computer vision. In process fusion, there may be blurring and information loss, so it is our goal to obtain high-definition information-rich images. this paper, a novel multi-focus method via local energy sparse representation shearlet domain proposed. The source images are decomposed into low- high-frequency sub-bands according transform. low-frequency fused by representation, energy. inverse transform used reconstruct...

The fusion of infrared and visible images together can fully leverage the respective advantages each, providing a more comprehensive richer set information. This is applicable in various fields such as military surveillance, night navigation, environmental monitoring, etc. In this paper, novel image method based on sparse representation guided filtering Laplacian pyramid (LP) domain introduced. source are decomposed into low- high-frequency bands by LP, respectively. Sparse has achieved...

Segmenting medical images is a necessary prerequisite for disease diagnosis and treatment planning. Among various image segmentation tasks, U-Net-based variants have been widely used in liver tumor tasks. In view of the highly variable shape size tumors, order to improve accuracy segmentation, this paper proposes hybrid structure-RDCTrans U-Net computed tomography (CT) examinations. We design backbone network dominated by ResNeXt50 supplemented dilated convolution increase depth, expand...

In this paper, we propose a novel deep unsupervised learning-based approach that jointly optimizes antenna selection and hybrid beamforming to improve the hardware spectral efficiencies of massive multiple-input-multiple-output (MIMO) downlink systems. By employing ResNet extract features from channel matrices, two neural networks, i.e., network (ASNet) (BFNet), are respectively proposed for dynamic beamformer design. Furthermore, probabilistic subsampling trick specially designed...

Poor illumination greatly affects the quality of obtained images. In this paper, a novel convolutional neural network named DEANet is proposed on basis Retinex for low-light image enhancement. combines frequency and content information images divided into three subnetworks: decomposition, enhancement, adjustment networks, which perform decomposition; denoising, contrast detail preservation; generation, respectively. The model trained public LOL dataset, experimental results show that it...

In this paper, we introduce an innovative approach to multi-focus image fusion by leveraging the concepts of fractal dimension and coupled neural P (CNP) systems in nonsubsampled contourlet transform (NSCT) domain. This method is designed overcome challenges posed limitations camera lenses depth-of-field effects, which often prevent all parts a scene from being simultaneously focus. Our proposed technique employs CNP with local topology-based model merge low-frequency components effectively....

Abstract The spectral fusion by Raman spectroscopy and Fourier infrared combined with pattern recognition algorithms is utilized to diagnose thyroid dysfunction serum, finds the segment highest sensitivity further advance diagnosis speed. Compared single or spectroscopy, proposal can improve detection accuracy, obtain more features, indicating greater differences between normal serum samples. For discriminating different samples, principal component analysis (PCA) was first used for feature...

Change detection is an important task in identifying land cover change different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects performance of detection. To improve accuracy detection, a novel automatic SAR image algorithm based on saliency convolutional-wavelet neural networks proposed. The log-ratio operator adopted generate difference image, reducing anisotropic diffusion used enhance original multitemporal...

Monocular 3D human pose estimation is challenging due to depth ambiguity. Convolution-based and Graph-Convolution-based methods have been developed extract information from temporal cues in motion videos. Typically, the lifting-based methods, most recent works adopt transformer model relationship of 2D keypoint sequences. These previous usually consider all joints a skeleton as whole then calculate attention based on overall characteristics skeleton. Nevertheless, exhibits obvious part-wise...

Remote sensing image change detection is widely used in land use and natural disaster detection. In order to improve the accuracy of detection, a robust method based on nonsubsampled contourlet transform (NSCT) fusion fuzzy local information C-means clustering (FLICM) model introduced this paper. Firstly, log-ratio mean-ratio operators are generate difference (DI), respectively; then, NSCT utilized fuse two images, one new DI obtained. The fused can not only reflect real trend but also...

As a convention, satellites and drones are equipped with sensors of both the visible light spectrum infrared (IR) spectrum. However, existing remote sensing object detection methods mostly use RGB images captured by camera while ignoring IR images. Even for algorithms that take RGB-IR image pairs as input, they may fail to extract all potential features in spectrums. This letter proposes Multispectral DETR, detector based on deformable attention mechanism. To enhance multispectral feature...

To solve problems of brightness and detail information loss in infrared visible image fusion, an effective fusion method using rolling guidance filtering gradient saliency map is proposed this paper. The used to decompose the input images into approximate layers residual layers; energy attribute model fuse introduced corresponding weight matrices are constructed perform on layers. generated by reconstructing fused layer sub-image sub-images. Experimental results demonstrate superiority method.

In the realm of maritime target detection, infrared imaging technology has become predominant modality. Detecting small ships on sea surface is crucial for national defense and security. However, challenge detecting targets persists, especially in complex scenes surface. As a response to this challenge, we propose MAPC-Net, an enhanced algorithm based existing network. Unlike conventional approaches, our method focuses addressing intricacies sparse pixel occupancy ships. MAPC-Net...

Multimodal medical image fusion aims to fuse images with complementary multisource information. In this paper, we propose a novel multimodal method using pulse coupled neural network (PCNN) and weighted sum of eight-neighborhood-based modified Laplacian (WSEML) integrating guided filtering (GIF) in non-subsampled contourlet transform (NSCT) domain. Firstly, the source are decomposed by NSCT, several low- high-frequency sub-bands generated. Secondly, PCNN-based rule is used process...

In recent years, with the increasingly serious problems of resource shortage and environmental pollution, exploration development underwater clean energy were particularly important. At same time, abundant resources species have attracted a large number scientists to carry out research on underwater-related tasks. Due diversity complexity environments, it is difficult perform related vision tasks, such as target detection capture. The digital image technology has been relatively mature,...

The automatic monitoring and detection of maritime targets hold paramount significance in safeguarding national sovereignty, ensuring rights, advancing development. Among the principal means surveillance, infrared (IR) small ship technology stands out. However, due to their minimal pixel occupancy lack discernible color texture information, IR ships have persistently posed a formidable challenge realm target detection. Additionally, intricate backgrounds often exacerbate issue by inducing...

Multi-focus image fusion is an important method for obtaining fully focused information. In this paper, a novel multi-focus based on fractal dimension (FD) and parameter adaptive unit-linking dual-channel pulse-coupled neural network (PAUDPCNN) in the curvelet transform (CVT) domain proposed. The source images are decomposed into low-frequency high-frequency sub-bands by CVT, respectively. FD PAUDPCNN models, along with consistency verification, employed to fuse sub-bands, average used...