Search Results (70)

With the rapid development of video encoding technology in the field of computer vision, the demand for tasks such as video frame reconstruction, denoising, and super-resolution has been continuously increasing. However, traditional video encoding methods typically focus on extracting spatial or temporal domain information, often facing challenges of insufficient accuracy and information loss when reconstructing high-frequency details, edges, and textures of images. To address this issue, this paper proposes an innovative LadderConv framework, which combines discrete wavelet transform (DWT) with spatial and channel attention mechanisms. By progressively recovering wavelet subbands, it effectively enhances the video frame encoding quality. Specifically, the LadderConv framework adopts a stepwise recovery approach for wavelet subbands, first processing high-frequency detail subbands with relatively less information, then enhancing the interaction between these subbands, and ultimately synthesizing a high-quality reconstructed image through inverse wavelet transform. Moreover, the framework introduces spatial and channel attention mechanisms, which further strengthen the focus on key regions and channel features, leading to notable improvements in detail restoration and image reconstruction accuracy. To optimize the performance of the LadderConv framework, particularly in detail recovery and high-frequency information extraction tasks, this paper designs an innovative ResGroup module. By using multi-layer convolution operations along with feature map compression and recovery, the ResGroup module enhances the network’s expressive capability and effectively reduces computational complexity. The ResGroup module captures multi-level features from low level to high level and retains rich feature information through residual connections, thus improving the overall reconstruction performance of the model. In experiments, the combination of the LadderConv framework and the ResGroup module demonstrates superior performance in video frame reconstruction tasks, particularly in recovering high-frequency information, image clarity, and detail representation. Full article

In recent years, with the rapid development of the Internet and mobile devices, the high-resolution video industry has ushered in a booming golden era, making video content the primary driver of Internet traffic. This trend has spurred continuous innovation in efficient video coding technologies, such as Advanced Video Coding/H.264 (AVC), High Efficiency Video Coding/H.265 (HEVC), and Versatile Video Coding/H.266 (VVC), which significantly improves compression efficiency while maintaining high video quality. However, during the encoding process, compression artifacts and the loss of visual details remain unavoidable challenges, particularly in high-resolution video processing, where the massive amount of image data tends to introduce more artifacts and noise, ultimately affecting the user’s viewing experience. Therefore, effectively reducing artifacts, removing noise, and minimizing detail loss have become critical issues in enhancing video quality. To address these challenges, this paper proposes a post-processing method based on Convolutional Neural Network (CNN) that improves the quality of VVC-reconstructed frames through deep feature extraction and fusion. The proposed method is built upon a high-resolution dual-path residual gating system, which integrates deep features from different convolutional layers and introduces convolutional blocks equipped with gating mechanisms. By ingeniously combining gating operations with residual connections, the proposed approach ensures smooth gradient flow while enhancing feature selection capabilities. It selectively preserves critical information while effectively removing artifacts. Furthermore, the introduction of residual connections reinforces the retention of original details, achieving high-quality image restoration. Under the same bitrate conditions, the proposed method significantly improves the Peak Signal-to-Noise Ratio (PSNR) value, thereby optimizing video coding quality and providing users with a clearer and more detailed visual experience. Extensive experimental results demonstrate that the proposed method achieves outstanding performance across Random Access (RA), Low Delay B-frame (LDB), and All Intra (AI) configurations, achieving BD-Rate improvements of 6.1%, 7.36%, and 7.1% for the luma component, respectively, due to the remarkable PSNR enhancement. Full article

As a core component of mechanical transmission systems, gear damage status significantly impacts the safety and efficiency of an overall mechanical system. However, existing fault diagnosis methods often struggle to extract features effectively in complex application scenarios characterized by conditions such as high temperature, high humidity, and high-level vibrations. Consequently, they exhibit poor adaptability and limited anti-noise capabilities. To address these limitations and enhance the adaptability and precision of gear fault diagnosis (GFD), a novel compressive sensing lightweight attention multi-scale residual network (CS-LAMRNet) method is proposed. Initially, compressive sensing technology was employed to remove noise and redundant information from the vibration signal, and the reconstructed 1D gear vibration signal was then converted into a 2D image. Subsequently, a multi-scale feature extraction (MSFE) module was designed based on multi-scale learning, with the aim of improving the feature extraction ability of the signal in noisy environments. Finally, an improved depth residual attention (IDRA) module was established and connected to the MSFE module, further enhancing the exactitude and generalization ability of the diagnosis method. The performance of the proposed CS-LAMRNet was evaluated using the NEU dataset and the SEU dataset, and it was compared with seven other fault diagnosis methods. The experimental results demonstrate that the accuracies of the CS-LAMRNet reached 99.80% and 100%, respectively, thus proving that the proposed method has a higher fault identification capability for gears under noisy environments. Full article

In recent years, the internet has developed rapidly. With the popularity of social media, uploading and backing up digital images has become the norm. A huge number of digital images are circulating on the internet daily, and issues related to information security follow. To protect intellectual property rights, digital watermarking is an indispensable technology. However, the common lossy compression technology in the network transmission process is a big problem for watermarking. This paper describes an innovative semi-blind watermarking method with the use of deep convolutional generative adversarial networks (DCGANs) for hiding and extracting watermarks from JPEG-compressed images. The proposed method achieves an average peak signal-to-noise ratio (PSNR) of 49.99 dB, a structural similarity index (SSIM) of 0.95, and a bit error rate (BER) of 0.008 across varying JPEG quality factors. The process is based on an embedder, decoder, generator, and discriminator. It allows watermarking, decoding, or reconstruction to be symmetric such that there is less distortion and durability is improved. It constructs a specific generator for each image and watermark that is supposed to be protected. Experimental results show that, with the variety of JPEG quality factors, the restored watermark achieves a remarkably low corrupted rate, outstripping recent deep learning-based watermarking methods. Full article

To reduce bandwidth usage in communications, absolute moment block truncation coding is employed to compress cover images. Confidential data are embedded into compressed images using reversible data-hiding technology for purposes such as image management, annotation, or authentication. As data size increases, enhancing embedding capacity becomes essential to accommodate larger volumes of secret data without compromising image quality or reversibility. Instead of using conventional absolute moment block truncation coding to encode each image block, this work proposes an effective reversible data-hiding scheme that enhances the embedding results by utilizing the traditional set of values: a bitmap, a high value, and a low value. In addition to the traditional set of values, a value is calculated using arithmetical differential coding and may be used for embedding. A process involving joint neighborhood coding and logical differential coding is applied to conceal the secret data in two of the three value tables, depending on the embedding capacity evaluation. An indicator is recorded to specify which two values are involved in the embedding process. The embedded secret data can be correctly extracted using a corresponding two-stage extraction process based on the indicator. To defeat the state-of-the-art scheme, bitmaps are also used as carriers in our scheme yet are compacted even more with Huffman coding. To reconstruct the original image, the low and high values of each block are reconstructed after data extraction. Experimental results show that our proposed scheme typically achieves an embedding rate exceeding 30%, surpassing the latest research by more than 2%. Our scheme reaches outstanding embedding rates while allowing the image to be perfectly restored to its original absolute moment block truncation coding form. Full article

Hyperspectral compressed imaging is a novel imaging detection technology based on compressed sensing theory that can quickly acquire spectral information of terrestrial objects in a single exposure. It combines reconstruction algorithms to recover hyperspectral data from low-dimensional measurement images. However, hyperspectral images from different scenes often exhibit high-frequency data sparsity and existing deep reconstruction algorithms struggle to establish accurate mapping models, leading to issues with detail loss in the reconstruction results. To address this issue, we propose a hyperspectral reconstruction method based on global gradient information and local low-rank priors. First, to improve the prior model’s efficiency in utilizing information of different frequencies, we design a gradient sampling strategy and training framework based on decision trees, leveraging changes in the loss function gradient information to enhance the model’s predictive capability for data of varying frequencies. Second, utilizing the local low-rank prior characteristics of the representative coefficient matrix, we develop a sparse sensing denoising module to effectively improve the local smoothness of point predictions. Finally, by establishing a regularization term for the reconstruction process based on the semantic similarity between the denoised results and prior spectral data, we ensure spatial consistency and spectral fidelity in the reconstruction results. Experimental results indicate that the proposed method achieves better detail recovery across different scenes, demonstrates improved generalization performance for reconstructing information of various frequencies, and yields higher reconstruction quality. Full article

With the popularity of High Dynamic Range (HDR) display technology, consumer demand for HDR images is increasing. Since HDR cameras are expensive, reconstructing High Dynamic Range (HDR) images from traditional Low Dynamic Range (LDR) images is crucial. However, existing HDR image reconstruction algorithms often fail to recover fine details and do not adequately address the fundamental principles of the LDR imaging pipeline. To overcome these limitations, the Reversing Lossy UNet (RLUNet) has been proposed, aiming to effectively balance dynamic range expansion and recover overexposed areas through a deeper understanding of LDR image pipeline principles. The RLUNet model comprises the Reverse Lossy Network, which is designed according to the LDR–HDR framework and focuses on reconstructing HDR images by recovering overexposed regions, dequantizing, linearizing the mapping, and suppressing compression artifacts. This framework, grounded in the principles of the LDR imaging pipeline, is designed to reverse the operations involved in lossy image operations. Furthermore, the integration of the Texture Filling Module (TFM) block with the Recovery of Overexposed Regions (ROR) module in the RLUNet model enhances the visual performance and detail texture of the overexposed areas in the reconstructed HDR image. The experiments demonstrate that the proposed RLUNet model outperforms various state-of-the-art methods on different testsets. Full article

Compressed sensing (CS) is an innovative signal acquisition and reconstruction technology that has broken through the limit of the Nyquist sampling theory. It is widely employed to optimize the measurement processes in various applications. One of the core challenges of CS is the construction of a measurement matrix. However, traditional random measurement matrices are often impractical. Additionally, many existing deterministic binary measurement matrices fail to provide the required flexibility for practical applications. In this study, inspired by the observation that pseudo-random sequences share similar properties with random sequences, we constructed a deterministic sparse measurement matrix with a flexible measurement number based on an pseudo-random sequence—the Legendre sequence. Empirical analysis of the phase transition and an assessment of the practical features of the proposed measurement matrix were conducted. We validated the effectiveness of the proposed measurement matrix on randomly synthesized signals and images. The results of our simulations reveal that our proposed measurement matrix performs better than several other measurement matrices, particularly in terms of accuracy and efficiency. Full article

In recent years, super-resolution technology has gained widespread attention in the field of remote sensing. Despite advancements, current methods often employ uniform reconstruction techniques across entire remote sensing images, neglecting the inherent variability in spatial frequency distributions, particularly the distinction between high-frequency texture regions and smoother areas, leading to computational inefficiency, which introduces redundant computations and fails to optimize the reconstruction process for regions of higher complexity. To address these issues, we propose the Perception-guided Classification Feature Intensification (PCFI) network. PCFI integrates two key components: a compressed sensing classifier that optimizes speed and performance, and a deep texture interaction fusion module that enhances content interaction and detail extraction. This network mitigates the tendency of Transformers to favor global information over local details, achieving improved image information integration through residual connections across windows. Furthermore, a classifier is employed to segment sub-image blocks prior to super-resolution, enabling efficient large-scale processing. The experimental results on the AID dataset indicate that PCFI achieves state-of-the-art performance, with a PSNR of 30.87 dB and an SSIM of 0.8131, while also delivering a 4.33% improvement in processing speed compared to the second-best method. Full article

Medical professionals primarily utilize medical images to detect anomalies within the interior structures and essential organs concealed by the skeletal and dermal layers. The primary purpose of medical imaging is to extract image features for the diagnosis of medical conditions. The processing of these images is indispensable for evaluating a patient’s health. However, when monitoring patients over extended periods using specific medical imaging technologies, a substantial volume of data accumulates daily. Consequently, there arises a necessity to compress these data in order to remove duplicates and speed up the process of acquiring data, making it appropriate for effective analysis and transmission. Compressed Sensing (CS) has recently gained widespread acceptance for rapidly compressing images with a reduced number of samples. Ensuring high-quality image reconstruction using conventional CS and block-based CS (BCS) poses a significant challenge since they rely on randomly selected samples. This challenge can be surmounted by adopting a variable BCS approach that selectively samples from diverse regions within an image. In this context, this paper introduces a novel CS method that uses an energy matrix, namely coefficient shuffling variable BCS (CSEM-VBCS), tailored for compressing a variety of medical images with balanced sparsity, thereby achieving a substantial compression ratio and good reconstruction quality. The results of experimental evaluations underscore a remarkable enhancement in the performance metrics of the proposed method when compared to contemporary state-of-the-art techniques. Unlike other approaches, CSEM-VBCS uses coefficient shuffling to prioritize regions of interest, allowing for more effective compression without compromising image quality. This strategy is especially useful in telemedicine, where bandwidth constraints often limit the transmission of high-resolution medical images. By ensuring faster data acquisition and reduced redundancy, CSEM-VBCS significantly enhances the efficiency of remote patient monitoring and diagnosis. Full article

For missile-borne platforms, traditional SAR technology consistently encounters two significant shortcomings: geometric distortion of 2D images and the inability to achieve forward-looking imaging. To address these issues, this paper explores the feasibility of using a maneuvering trajectory to enable forward-looking and three-dimensional imaging by analyzing the maneuvering characteristics of an actual missile-borne platform. Additionally, it derives the corresponding resolution characterization model, which lays a theoretical foundation for future applications. Building on this, the paper proposes a three-dimensional super-resolution imaging algorithm that combines axis rotation with compressed sensing. The axis rotation not only realizes the dimensionality reduction of data, but also can expand the observation scenario in the cross-track dimension. The proposed algorithm first focuses on the track-vertical plane to extract 2D position parameters. Then, a compressed sensing-based process is applied to extract reflection coefficients and super-resolution cross-track position parameters, thereby achieving precise 3D imaging reconstruction. Finally, numerical simulation results confirm the effectiveness and accuracy of the proposed algorithm. Full article

The proliferation of battery-operated end-user electronic devices due to technological advancements, especially in medical image processing applications, demands low power consumption, high-speed operation, and efficient coding. The design of these devices is centered on the Application-Specific Integrated Circuits (ASIC), General Purpose Processors (GPP), and Field Programmable Gate Array (FPGA) frameworks. The need for low-power functional blocks arises from the growing demand for high-performance computational units that are part of high-speed processors operating at high clock frequencies. The operational speed of the processor is determined by the computational unit, which is the workhorse of high-speed processors. A novel approach to integrating Very Large-Scale Integration (VLSI) ASIC design and the concepts of low-power VLSI compatible with medical image compression was embraced in this research. The focus of this study was the design, development, and implementation of a Power Delay Product (PDP) optimized computational unit targeted for medical image compression using ASIC design flow. This stimulates the research community’s quest to develop an ideal architecture, emphasizing on minimizing power consumption and enhancing device performance for medical image processing applications. The study uses area, delay, power, PDP, and Peak Signal-to-Noise Ratio (PSNR) as performance metrics. The research work takes inspiration from this and aims to enhance the efficiency of the computational unit through minor design modifications that significantly impact performance. This research proposes to explore the trade-off of high-performance adder and multiplier designs to design an ASIC-based computational unit using low-power techniques to enhance the efficiency in power and delay. The computational unit utilized for the digital image compression process was synthesized and implemented using gpdk 45 nm standard libraries with the Genus tool of Cadence. A reduced PDP of 46.87% was observed when the image compression was performed on a medical image, along with an improved PSNR of 5.89% for the reconstructed image. Full article

Compressive sensing (CS) is recognized for its adeptness at compressing signals, making it a pivotal technology in the context of sensor data acquisition. With the proliferation of image data in Internet of Things (IoT) systems, CS is expected to reduce the transmission cost of signals captured by various sensor devices. However, the quality of CS-reconstructed signals inevitably degrades as the sampling rate decreases, which poses a challenge in terms of the inference accuracy in downstream computer vision (CV) tasks. This limitation imposes an obstacle to the real-world application of existing CS techniques, especially for reducing transmission costs in sensor-rich environments. In response to this challenge, this paper contributes a CV-oriented adaptive CS framework based on saliency detection to the field of sensing technology that enables sensor systems to intelligently prioritize and transmit the most relevant data. Unlike existing CS techniques, the proposal prioritizes the accuracy of reconstructed images for CV purposes, not only for visual quality. The primary objective of this proposal is to enhance the preservation of information critical for CV tasks while optimizing the utilization of sensor data. This work conducts experiments on various realistic scenario datasets collected by real sensor devices. Experimental results demonstrate superior performance compared to existing CS sampling techniques across the STL10, Intel, and Imagenette datasets for classification and KITTI for object detection. Compared with the baseline uniform sampling technique, the average classification accuracy shows a maximum improvement of 26.23%, 11.69%, and 18.25%, respectively, at specific sampling rates. In addition, even at very low sampling rates, the proposal is demonstrated to be robust in terms of classification and detection as compared to state-of-the-art CS techniques. This ensures essential information for CV tasks is retained, improving the efficacy of sensor-based data acquisition systems. Full article

Stress wave technology is very suitable for detecting internal defects of standing trees, logs, and wood and has gradually become the mainstream technology in this research field. Usually, 12 sensors are positioned equidistantly around the cross-section of tree trunks in order to obtain enough stress wave signals. However, the arrangement of sensors is time-consuming and laborious, and maintaining the accuracy of stress wave imaging under sparse signals is a challenging problem. In this paper, a novel stress wave hybrid imaging method based on compressive sensing and elliptic interpolation is proposed. The spatial structure of the defective area is reconstructed by using the advantages of compressive sensing in sparse signal representation and solution of stress waves, and the healthy area is reconstructed by using the elliptic space interpolation method. Then, feature points are selected and mixed for imaging. The comparative experimental results show that the overall imaging accuracy of the proposed method reaches 89.7%, and the high-quality imaging effect can be guaranteed when the number of sensors is reduced to 10, 8, or even 6. Full article

Due to a unique imaging mechanism, Synthetic Aperture Radar (SAR) images typically exhibit degradation phenomena. To enhance image quality and support real-time on-board processing capabilities, we propose a lightweight deep generative network framework, namely, the Lightweight Super-Resolution Generative Adversarial Network (LSRGAN). This method introduces Depthwise Separable Convolution (DSConv) in residual blocks to compress the original Generative Adversarial Network (GAN) and uses the SeLU activation function to construct a lightweight residual module (LRM) suitable for SAR image characteristics. Furthermore, we combine the LRM with an optimized Coordinated Attention (CA) module, enhancing the lightweight network’s capability to learn feature representations. Experimental results on spaceborne SAR images demonstrate that compared to other deep generative networks focused on SAR image super-resolution reconstruction, LSRGAN achieves compression ratios of $74.68\%$ in model storage requirements and $55.93\%$ in computational resource demands. In this work, we significantly reduce the model complexity, improve the quality of spaceborne SAR images, and validate the effectiveness of the SAR image super-resolution algorithm as well as the feasibility of real-time on-board processing technology. Full article