Search Results (75)

Pulmonary dynamic contrast-enhanced (DCE) MRI is clinically useful for assessing pulmonary perfusion, but its signal-to-noise ratio (SNR) is limited. A self-supervised learning network-based plug-and-play (PnP) denoising model was developed to improve the image quality of pulmonary perfusion MRI. A dataset of patients with suspected pulmonary diseases was used. Asymmetric pixel-shuffle downsampling blind-spot network (AP-BSN) training inputs were two-dimensional background-subtracted perfusion images without clean ground truth. The AP-BSN is incorporated into a PnP model (PnP-BSN) for balancing noise control and image fidelity. Model performance was evaluated by SNR, sharpness, and overall image quality from two radiologists. The fractal dimension and k-means segmentation of the pulmonary perfusion images were calculated for comparing denoising performance. The model was trained on 29 patients and tested on 8 patients. The performance of PnP-BSN was compared to denoising convolutional neural network (DnCNN) and a Gaussian filter. PnP-BSN showed the highest reader scores in terms of SNR, sharpness, and overall image quality as scored by two radiologists. The expert scoring results for DnCNN, Gaussian, and PnP-BSN were 2.25 ± 0.65, 2.44 ± 0.73, and 3.56 ± 0.73 for SNR; 2.62 ± 0.52, 2.62 ± 0.52, and 3.38 ± 0.64 for sharpness; and 2.16 ± 0.33, 2.34 ± 0.42, and 3.53 ± 0.51 for overall image quality (p < 0.05 for all). PnP-BSN outperformed DnCNN and a Gaussian filter for denoising pulmonary perfusion MRI, which led to improved quantitative fractal analysis. Full article

Light Detection and Ranging (LiDAR) point clouds are an essential perception modality for artificial intelligence systems like autonomous driving and robotics, where the ubiquity of small objects in real-world scenarios substantially challenges the visual tracking of small targets amidst the vastness of point cloud data. Current methods predominantly focus on developing universal frameworks for general object categories, often sidelining the persistent difficulties associated with small objects. These challenges stem from a scarcity of foreground points and a low tolerance for disturbances. To this end, we propose a deep neural network framework that trains a Siamese network for feature extraction and innovatively incorporates two pivotal modules: the target-awareness prototype mining (TAPM) module and the regional grid subdivision (RGS) module. The TAPM module utilizes the reconstruction mechanism of the masked auto-encoder to distill prototypes within the feature space, thereby enhancing the salience of foreground points and aiding in the precise localization of small objects. To heighten the tolerance of disturbances in feature maps, the RGS module is devised to retrieve detailed features of the search area, capitalizing on Vision Transformer and pixel shuffle technologies. Furthermore, beyond standard experimental configurations, we have meticulously crafted scaling experiments to assess the robustness of various trackers when dealing with small objects. Comprehensive evaluations show our method achieves a mean Success of 64.9% and 60.4% under original and scaled settings, outperforming benchmarks by +3.6% and +5.4%, respectively. Full article

This study presents a novel two-dimensional hyperchaotic map, referred to as the 2D exponent-logarithm-sine chaotic map (2D-ELSCM), which is intricately designed through the interplay of exponential, logarithmic, and sine functions. To comprehensively evaluate the chaotic performance of the 2D-ELSCM, several critical metrics are employed, including the largest Lyapunov exponent (LLE), permutation entropy (PE), sample entropy (SE), Kolmogorov entropy (KE), and the results of the 0–1 test, which yield values of 8.3175, 0.9998, 1.9826, 2.1117, and 0.9970, respectively. Furthermore, the 2D-ELSCM successfully passes the NIST randomness tests, collectively confirming its exceptional randomness and complexity. Building upon this robust chaotic map, we develop a distinctive chaotic image encryption scheme that employs an improved Knuth-Durstenfeld shuffle (IKDS) to rearrange pixel positions, effectively disrupting the correlation between adjacent pixels. Complementing this, we introduce a dynamic diffusion mechanism that integrates DNA encoding with the Zigzag transform, thereby promoting global pixel diffusion and enhancing encryption security. The initial conditions of the chaotic map are generated from the SHA-512 hash of the plaintext image in conjunction with an external key, which not only expands the key space but also significantly improves key sensitivity. Simulation results demonstrate that the proposed encryption scheme achieves correlation coefficients approaching 0 in the encrypted test images, with an average NPCR of 99.6090% and UACI of 33.4707%. These findings indicate a strong resistance to various attacks and showcase excellent encryption quality, thereby underscoring the scheme’s potential for secure image transmission and storage. Full article

This work presents an optical encryption process for various types of information related to 3D worlds (scenes) or 2D images, utilizing Computer-Generated Holograms (CGHs). It also introduces a modification to the Dual Random Phase Encoding (DRPE) encryption algorithm by incorporating pixel shuffling. This proposal enables the use of either a single key for both pixel shuffling and phase mask definition or two independent keys. The latter option is particularly advantageous in applications that require the involvement of two independent agents to retrieve the original plaintext. The dimension of the CGHs determines the size of the keys based on the random generation of values by cryptographically secure algorithms, so the use of arithmetic encryption is proposed for data compression. However, this proposal allows the use of other algorithms described in the literature to generate the shuffle and phase matrices. The complete workflow is described starting from the synthesis of a 3D scene, defined by a mesh of triangles with shape and appearance modeling, or 2D images of any level of geometric or visual complexity using computer graphics; its storage in a CGH, the encryption and decryption process, and finally, the results obtained in the laboratory and by simulation are shown. The similarity between different encryption levels is measured by the Pearson Coefficient to evaluate the results obtained. Full article

Image security faces increasing challenges with the widespread application of computer science and artificial intelligence. Although chaotic systems are employed to encrypt images and prevent unauthorized access or tampering, the degradation that occurs during the binarization process in chaotic systems reduces security. The chaos- and DNA-based image encryption schemes increases its complexity, while the integration of deep learning with image encryption is still in its infancy and has several shortcomings. An image encryption scheme with high security and efficiency is required for the protection of the image. To address these problems, we propose a novel image encryption scheme based on the lightweight VGG (LVGG), referred to as LVGG-IE. In this work, we design an LVGG network with fewer layers while maintaining a high capacity for feature capture. This network is used to generate a key seed, which is then employed to transform the plaintext image into part of the initial value of a chaotic system, ensuring that the chaos-based key generator correlates with the plaintext image. A dynamic substitution box (S-box) is also designed and used to scramble the randomly shuffled plaintext image. Additionally, a single-connected (SC) layer is combined with a convolution layer from VGG to encrypt the image, where the SC layer is dynamically constructed by the secret key and the convolution kernel is set to $1\times 2$. The encryption efficiency is simulated, and the security is analyzed. The results show that the correlation coefficient between adjacent pixels in the proposed scheme achieves ${10}^{-4}$. The NPCR exceeds 0.9958, and the UACI falls within the theoretical value with a significance level of 0.05. The encryption quality, the security of the dynamic S-box and the SC layer, and the efficiency are tested. The result shows that the proposed image encryption scheme demonstrates high security, efficiency, and robustness, making it effective for image security in various applications. Full article

In this paper, a progressive image transmission and recovery algorithm based on hybrid attention mechanism and feature fusion is proposed, aiming to solve the challenge of monitoring the signal-less region of transmission lines. The method combines wavelet transform, Swin Transformer, and hybrid attention module with the Pixel Shuffle upsampling mechanism to achieve a balance between quality and efficiency of image transmission in a low bandwidth environment. Initial preview is achieved by prioritizing the transmission of low-frequency subbands through wavelet transform, followed by dynamic optimization of the weight allocation of key features using a hybrid attention and local window multi-scale self-attention mechanism, and further enhancement of the resolution of the decoded image through Pixel Shuffle upsampling. Experimental results show that the algorithm significantly outperforms existing methods in terms of image quality (PSNR, SSIM), transmission efficiency, and bandwidth utilization, proving its superior adaptability and effectiveness in surveillance scenarios in signal-free regions. Full article

Transformer-based methods have demonstrated impressive performance in image super-resolution tasks. However, when applied to large-scale Earth observation images, the existing transformers encounter two significant challenges: (1) insufficient consideration of spatial correlation between adjacent ground objects; and (2) performance bottlenecks due to the underutilization of the upsample module. To address these issues, we propose a novel distance-enhanced strip attention transformer (DESAT). The DESAT integrates distance priors, easily obtainable from remote sensing images, into the strip window self-attention mechanism to capture spatial correlations more effectively. To further enhance the transfer of deep features into high-resolution outputs, we designed an attention-enhanced upsample block, which combines the pixel shuffle layer with an attention-based upsample branch implemented through the overlapping window self-attention mechanism. Additionally, to better simulate real-world scenarios, we constructed a new cross-sensor super-resolution dataset using Gaofen-6 satellite imagery. Extensive experiments on both simulated and real-world remote sensing datasets demonstrate that the DESAT outperforms state-of-the-art models by up to 1.17 dB along with superior qualitative results. Furthermore, the DESAT achieves more competitive performance in real-world tasks, effectively balancing spatial detail reconstruction and spectral transform, making it highly suitable for practical remote sensing super-resolution applications. Full article

In recent years, the rapid advancement of drone technology has led to an increasing use of drones equipped with hyperspectral sensors for ground imaging. Hyperspectral data captured via drones offer significantly higher spatial resolution, but this also introduces more complex background details and larger target scales in high-resolution hyperspectral imagery (HRHSI), posing substantial challenges for hyperspectral anomaly detection (HAD). Mainstream reconstruction-based deep learning methods predominantly emphasize spatial local information in hyperspectral images (HSIs), relying on small spatial neighborhoods for reconstruction. As a result, large anomalous targets and background details are often well reconstructed, leading to poor anomaly detection performance, as these targets are not sufficiently distinguished from the background. To address these limitations, we propose a novel HAD network for HRHSI based on large-kernel central block masked convolution and channel attention, termed LKCMCA. Specifically, we first employ the pixel-shuffle technique to reduce the size of anomalous targets without losing image information. Next, we design a large-kernel central block masked convolution to make the network pay more attention to the surrounding background information, enabling better fusion of the information between adjacent bands. This, coupled with an efficient channel attention mechanism, allows the network to capture deeper spectral features, enhancing the reconstruction of the background while suppressing anomalous targets. Furthermore, we introduce an adaptive loss function by down-weighting anomalous pixels based on the mean absolute error. This loss function is specifically designed to suppress the reconstruction of potentially anomalous pixels during network training, allowing our model to be considered an excellent background reconstruction network. By leveraging reconstruction error, the model effectively highlights anomalous targets. Meanwhile, we produced four benchmark datasets specifically for HAD tasks using existing HRHSI data, addressing the current shortage of HRHSI datasets in the HAD field. Extensive experiments demonstrate that our LKCMCA method achieves superior detection performance, outperforming ten state-of-the-art HAD methods on all datasets. Full article

The computer network has fundamentally transformed modern interactions, enabling the effortless transmission of multimedia data. However, the openness of these networks necessitates heightened attention to the security and confidentiality of multimedia content. Digital images, being a crucial component of multimedia communications, require robust protection measures, as their security has become a global concern. Traditional color image encryption/decryption algorithms, such as DES, IDEA, and AES, are unsuitable for image encryption due to the diverse storage formats of images, highlighting the urgent need for innovative encryption techniques. Chaos-based cryptosystems have emerged as a prominent research focus due to their properties of randomness, high sensitivity to initial conditions, and unpredictability. These algorithms typically operate in two phases: shuffling and replacement. During the shuffling phase, the positions of the pixels are altered using chaotic sequences or matrix transformations, which are simple to implement and enhance encryption. However, since only the pixel positions are modified and not the pixel values, the encrypted image’s histogram remains identical to the original, making it vulnerable to statistical attacks. In the replacement phase, chaotic sequences alter the pixel values. This research introduces a novel encryption technique for color images (RGB type) based on DNA subsequence operations to secure these images, which often contain critical information, from potential cyber-attacks. The suggested method includes two main components: a high-speed permutation process and adaptive diffusion. When implemented in the MATLAB software environment, the approach yielded promising results, such as NPCR values exceeding 98.9% and UACI values at around 32.9%, demonstrating its effectiveness in key cryptographic parameters. Security analyses, including histograms and Chi-square tests, were initially conducted, with passing Chi-square test outcomes for all channels; the correlation coefficient between adjacent pixels was also calculated. Additionally, entropy values were computed, achieving a minimum entropy of 7.0, indicating a high level of randomness. The method was tested on specific images, such as all-black and all-white images, and evaluated for resistance to noise and occlusion attacks. Finally, a comparison of the proposed algorithm’s NPCR and UAC values with those of existing methods demonstrated its superior performance and suitability. Full article

Coral reefs are vital to marine biodiversity but are increasingly threatened by global climate change and human activities, leading to significant declines in live coral cover (LCC). Monitoring LCC is crucial for assessing the health of coral reef ecosystems and understanding their degradation and recovery. Traditional methods for estimating LCC, such as the manual interpretation of underwater survey videos, are labor-intensive and time-consuming, limiting their scalability for large-scale ecological monitoring. To overcome these challenges, this study introduces an innovative deep learning-based approach that utilizes semantic segmentation to automatically interpret LCC from underwater videos. That is, we enhanced PSPNet for live coral segmentation by incorporating channel and spatial attention mechanisms, along with pixel shuffle modules. Experimental results demonstrated that the proposed model achieved a mean Intersection over Union (mIoU) of 89.51% and a mean Pixel Accuracy (mPA) of 94.47%, showcasing superior accuracy in estimating LCC compared to traditional methods. Moreover, comparisons indicated that the proposed model aligns more closely with manual interpretations than other models, with an mean absolute error of 4.17%, compared to 5.89% for the original PSPNet, 6.03% for Deeplab v3+, 7.12% for U-Net, and 6.45% for HRNet, suggesting higher precision in LCC estimation. By automating the estimation of LCC, this deep learning-based approach can greatly enhance efficiency, thereby contributing significantly to global conservation efforts by enabling more scalable and efficient monitoring and management of coral reef ecosystems. Full article

Restricted by a metal-enclosed structure, the internal defects of large transformers are difficult to visually detect. In this paper, a micro-robot is used to visually inspect the interior of a transformer. For the micro-robot to successfully detect the discharge level and insulation degradation trend in the transformer, it is essential to segment the carbon trace accurately and rapidly from the complex background. However, the complex edge features and significant size differences of carbon traces pose a serious challenge for accurate segmentation. To this end, we propose the Hadamard production-Spatial coordinate attention-PixelShuffle UNet (HSP-UNet), an innovative architecture specifically designed for carbon trace segmentation. To address the pixel over-concentration and weak contrast of carbon trace image, the Adaptive Histogram Equalization (AHE) algorithm is used for image enhancement. To realize the effective fusion of carbon trace features with different scales and reduce model complexity, the novel grouped Hadamard Product Attention (HPA) module is designed to replace the original convolution module of the UNet. Meanwhile, to improve the activation intensity and segmentation completeness of carbon traces, the Spatial Coordinate Attention (SCA) mechanism is designed to replace the original jump connection. Furthermore, the PixelShuffle up-sampling module is used to improve the parsing ability of complex boundaries. Compared with UNet, UNet++, UNeXt, MALUNet, and EGE-UNet, HSP-UNet outperformed all the state-of-the-art methods on both carbon trace datasets. For dendritic carbon traces, HSP-UNet improved the Mean Intersection over Union (MIoU), Pixel Accuracy (PA), and Class Pixel Accuracy (CPA) of the benchmark UNet by 2.13, 1.24, and 4.68 percentage points, respectively. For clustered carbon traces, HSP-UNet improved MIoU, PA, and CPA by 0.98, 0.65, and 0.83 percentage points, respectively. At the same time, the validation results showed that the HSP-UNet has a good model lightweighting advantage, with the number of parameters and GFLOPs of 0.061 M and 0.066, respectively. This study could contribute to the accurate segmentation of discharge carbon traces and the assessment of the insulation condition of the oil-immersed transformer. Full article

Visually Impaired Persons (VIPs) have difficulty in recognizing vehicles used for navigation. Additionally, they may not be able to identify the bus to their desired destination. However, the bus bay in which the designated bus stops has not been analyzed in the existing literature. Thus, a guidance system for VIPs that identifies the correct bus for transportation is presented in this paper. Initially, speech data indicating the VIP’s destination are pre-processed and converted to text. Next, utilizing the Arctan Gradient-activated Recurrent Neural Network (ArcGRNN) model, the number of bays at the location is detected with the help of a Global Positioning System (GPS), input text, and bay location details. Then, the optimal bay is chosen from the detected bays by utilizing the Experienced Perturbed Bacteria Foraging Triangular Optimization Algorithm (EPBFTOA), and an image of the selected bay is captured and pre-processed. Next, the bus is identified utilizing a You Only Look Once (YOLO) series model. Utilizing the Sub-pixel Shuffling Convoluted Encoder–ArcGRNN Decoder (SSCEAD) framework, the text is detected and segmented for the buses identified in the image. From the segmented output, the text is extracted, based on the destination and route of the bus. Finally, regarding the similarity value with respect to the VIP’s destination, a decision is made utilizing the Multi-characteristic Non-linear S-Curve-Fuzzy Rule (MNC-FR). This decision informs the bus conductor about the VIP, such that the bus can be stopped appropriately to pick them up. During testing, the proposed system selected the optimal bay in 247,891 ms, which led to deciding the bus stop for the VIP with a fuzzification time of 34,197 ms. Thus, the proposed model exhibits superior performance over those utilized in prevailing works. Full article

This paper presents a fault diagnosis method for a vacuum contactor using the generalized Stockwell transform (GST) of vibration signals. The objective is to solve the problem of low diagnostic performance efficiency caused by the inadequate feature extraction capability and the redundant pixels in the graph background. The proposed method is based on the time-frequency graph optimization technique and ShuffleNetV2 network. Firstly, vibration signals in different states are collected and converted into GST time-frequency graphs. Secondly, multi-resolution GST time-frequency graphs are generated to cover signal characteristics in all frequency bands by adjusting the GST Gaussian window width factor λ. The OTSU algorithm is then combined to crop the energy concentration area, and the size of these time-frequency graphs is optimized by 68.86%. Finally, considering the advantages of the channel split and channel shuffle methods, the ShuffleNetV2 network is adopted to improve the feature learning ability and identify fault categories. In this paper, the CKJ5-400/1140 vacuum contactor is taken as the test object. The fault recognition accuracy reaches 99.74%, and the single iteration time of model training is reduced by 19.42%. Full article

Computed tomography (CT) imaging is vital for diagnosing and monitoring diseases in both humans and animals, yet radiation exposure remains a significant concern, especially in animal imaging. Low-dose CT (LDCT) minimizes radiation exposure but often compromises image quality due to a reduced signal-to-noise ratio (SNR). Recent advancements in deep learning, particularly with CycleGAN, offer promising solutions for denoising LDCT images, though challenges in preserving anatomical detail and image sharpness persist. This study introduces a novel framework tailored for animal LDCT imaging, integrating deep learning techniques within the CycleGAN architecture. Key components include BlurPool for mitigating high-resolution image distortion, PixelShuffle for enhancing expressiveness, hierarchical feature synthesis (HFS) networks for feature retention, and spatial channel squeeze excitation (scSE) blocks for contrast reproduction. Additionally, a multi-scale discriminator enhances detail assessment, supporting effective adversarial learning. Rigorous experimentation on veterinary CT images demonstrates our framework’s superiority over traditional denoising methods, achieving significant improvements in noise reduction, contrast enhancement, and anatomical structure preservation. Extensive evaluations show that our method achieves a precision of 0.93 and a recall of 0.94. This validates our approach’s efficacy, highlighting its potential to enhance diagnostic accuracy in veterinary imaging. We confirm the scSE method’s critical role in optimizing performance, and robustness to input variations underscores its practical utility. Full article

Affected by the complex underwater environment and the limitations of low-resolution sonar image data and small sample sizes, traditional image recognition algorithms have difficulties achieving accurate sonar image recognition. The research builds on YOLOv7 and devises an innovative fast recognition model designed explicitly for sonar images, namely the Dual Attention Mechanism YOLOv7 model (DA-YOLOv7), to tackle such challenges. New modules such as the Omni-Directional Convolution Channel Prior Convolutional Attention Efficient Layer Aggregation Network (OA-ELAN), Spatial Pyramid Pooling Channel Shuffling and Pixel-level Convolution Bilat-eral-branch Transformer (SPPCSPCBiFormer), and Ghost-Shuffle Convolution Enhanced Layer Aggregation Network-High performance (G-ELAN-H) are central to its design, which reduce the computational burden and enhance the accuracy in detecting small targets and capturing local features and crucial information. The study adopts transfer learning to deal with the lack of sonar image samples. By pre-training the large-scale Underwater Acoustic Target Detection Dataset (UATD dataset), DA-YOLOV7 obtains initial weights, fine-tuned on the smaller Smaller Common Sonar Target Detection Dataset (SCTD dataset), thereby reducing the risk of overfitting which is commonly encountered in small datasets. The experimental results on the UATD, the Underwater Optical Target Detection Intelligent Algorithm Competition 2021 Dataset (URPC), and SCTD datasets show that DA-YOLOV7 exhibits outstanding performance, with mAP@0.5 scores reaching 89.4%, 89.9%, and 99.15%, respectively. In addition, the model maintains real-time speed while having superior accuracy and recall rates compared to existing mainstream target recognition models. These findings establish the superiority of DA-YOLOV7 in sonar image analysis tasks. Full article