Search

We introduce a novel technique to mitigate the adverse effects of atmospheric turbulence on astronomical imaging. Utilizing a video-to-image neural network trained on simulated data, our method processes a sliding sequence of short-exposure (∼0.2 s) stellar field images to reconstruct an image devoid of both turbulence and noise. We demonstrate the method with simulated and observed stellar fields, and show that the brief exposure sequence allows the network to accurately associate speckles to their originating stars and effectively disentangle light from adjacent sources across a range of seeing conditions, all while preserving flux to a lower signal-to-noise ratio than an average stack. This approach results in a marked improvement in angular resolution without compromising the astrometric stability of the final image. [ABSTRACT FROM AUTHOR]

Multiplicative noise removal is a challenging image processing problem. In this paper, we study a fractional-order nonlinear cross-diffusion system to denoise images corrupted by multiplicative Gamma noise. The system is coupled by two nonlinear, partial differential equations and gray level information, fractional derivative operator is considered in diffusion process to remove high level noise effectively while preserve structure details for texture images and SAR images. We prove the existence of weak solutions and other theoretical properties of the fractional-order cross-diffusion system under some hypotheses. In the numerical aspect, the model is implemented by virtue of the discrete fractional Fourier transform in the frequency domain. Experimental results show that the new system has a good compromise between multiplicative noise removal and structure preservation when compared to other well-known denoising methods. [ABSTRACT FROM AUTHOR]

The classification of vehicles presents notable challenges within the domain of image processing. Traditional models suffer from inefficiency, prolonged training times for datasets, intricate feature extraction, and variable assignment complexities for classification. Conventional methods applied to categorize vehicles from extensive datasets often lead to errors, misclassifications, and unproductive outcomes. Consequently, leveraging machine learning techniques emerges as a promising solution to tackle these challenges. This study adopts a machine learning approach to alleviate image misclassifications and manage large quantities of vehicle images effectively. Specifically, a contrast enhancement technique is employed in the pre-processing stage to highlight pixel values in vehicle images. In the feature segmentation stage, Mask-R-CNN is utilized to categorize pixels into predefined classes. VGG16 is then employed to extract features from vehicle images, while an autoencoder aids in selecting features by learning non-linear input features and compressing representation features. Finally, the CatBoost (CB) algorithm is implemented for vehicle classification (VC) in diverse critical environments, such as inclement weather, twilight, and instances of vehicle blockage. Extensive experiments are conducted using different large-scale datasets with various machine learning platforms. The findings indicate that CB (presumably a specific method or algorithm) attains the highest level of performance on the large-scale dataset named UFPR-ALPR, with an accuracy rate of 98.89%. [ABSTRACT FROM AUTHOR]

Concerns regarding microplastic (MP) contamination in aquatic ecosystems and its impact on seafood require a better understanding of human dietary MP exposure including extensive monitoring. While conventional techniques for MP analysis like infrared or Raman microspectroscopy provide detailed particle information, they are limited by low sample throughput, particularly when dealing with high particle numbers in seafood due to matrix-related residues. Consequently, more rapid techniques need to be developed to meet the requirements of large-scale monitoring. This study focused on semi-automated fluorescence imaging analysis after Nile red staining for rapid MP screening in seafood. By implementing RGB-based fluorescence threshold values, the need for high operator expertise to prevent misclassification was addressed. Food-relevant MP was identified with over 95% probability and differentiated from natural polymers with a 1% error rate. Comparison with laser direct infrared imaging (LDIR), a state-of-the-art method for rapid MP analysis, showed similar particle counts, indicating plausible results. However, highly variable recovery rates attributed to inhomogeneous particle spiking experiments highlight the need for future development of certified reference material including sample preparation. The proposed method demonstrated suitability of high throughput analysis for seafood samples, requiring 0.02–0.06 h/cm2 filter surface compared to 4.5–14.7 h/cm with LDIR analysis. Overall, the method holds promise as a screening tool for more accurate yet resource-intensive MP analysis methods such as spectroscopic or thermoanalytical techniques. [ABSTRACT FROM AUTHOR]

The proliferation of smart conurbations entails an efficient system design for managing all the crowds in public places. Multitude controlling procedures are carried out for controlling compact areas where more number of peoples is present at several groups. Therefore for controlling purpose the proposed method aims to design a pictorial representation using Internet of Things (IoT). The process is carried out by taking images and then organizing it using switching techniques in the presence of square boxes where entire populace is identified on real time experimentations. For processing and controlling the occurrence a separate architecture is designed with analytical equivalences where all data set is stored in cloud platform. Further the incorporation of system model is carried out using Switching Based Algorithm (SBA) which adds more number of columns even for high population cases. In order to verify the effectiveness of proposed model five scenarios are considered with performance evaluation metrics for SBA and all the test results provides best optimal results. Moreover the projected model is improved with an average percentage of 83 as compared to existing models. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for recognizing, extracting, and processing Phase-Resolved Partial Discharge (PRPD) patterns from two-dimensional plots to identify specific defect types affecting electrical equipment without human intervention while retaining the principals that make PRPD analysis an effective diagnostic technique. The proposed method does not rely on training complex deep learning algorithms which demand substantial computational resources and extensive datasets that can pose significant hurdles for the application of on-line partial discharge monitoring. Instead, the developed Cosine Cluster Net (CCNet) model, which is an image processing pipeline, can extract and process patterns from any two-dimensional PRPD plot before employing the cosine similarity function to measure the likeness of the patterns to predefined templates of known defect types. The PRPD pattern recognition capabilities of the model were tested using several manually classified PRPD images available in the existing literature. The model consistently produced similarity scores that identified the same defect type as the one from the manual classification. The successful defect type reporting from the initial trials of the CCNet model together with the speed of the identification, which typically does not exceed four seconds, indicates potential for real-time applications. [ABSTRACT FROM AUTHOR]

With the development of deep learning, the Super-Resolution (SR) reconstruction of microscopic images has improved significantly. However, the scarcity of microscopic images for training, the underutilization of hierarchical features in original Low-Resolution (LR) images, and the high-frequency noise unrelated with the image structure generated during the reconstruction process are still challenges in the Single Image Super-Resolution (SISR) field. Faced with these issues, we first collected sufficient microscopic images through Motic, a company engaged in the design and production of optical and digital microscopes, to establish a dataset. Secondly, we proposed a Residual Dense Attention Generative Adversarial Network (RDAGAN). The network comprises a generator, an image discriminator, and a feature discriminator. The generator includes a Residual Dense Block (RDB) and a Convolutional Block Attention Module (CBAM), focusing on extracting the hierarchical features of the original LR image. Simultaneously, the added feature discriminator enables the network to generate high-frequency features pertinent to the image's structure. Finally, we conducted experimental analysis and compared our model with six classic models. Compared with the best model, our model improved PSNR and SSIM by about 1.5 dB and 0.2, respectively. [ABSTRACT FROM AUTHOR]

In this study, an innovative laser 3D-scanning technology is proposed to scan pipe inner walls in order to solve the problems of the exorbitant expenses and operational complexities of the current equipment for the 3D data acquisition of the pipe inner wall, and the difficulty of both the efficiency and accuracy of traditional light stripe-center extraction methods. The core of this technology is the monocular-structured light 3D scanner, the image processing strategy based on tracking speckles, and the improved gray barycenter method. The experimental results demonstrate a 52% reduction in the average standard error of the improved gray barycenter method when compared to the traditional gray barycenter method, along with an 83% decrease in the operation time when compared to the Steger method. In addition, the size data of the inner wall of the pipe obtained using this technology is accurate, and the average deviation of the inner diameter and length of the pipe is less than 0.13 mm and 0.41 mm, respectively. In general, it not only reduces the cost, but also ensures high efficiency and high precision, providing a new and efficient method for the 3D data acquisition of the inner wall of the pipe. [ABSTRACT FROM AUTHOR]

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. [ABSTRACT FROM AUTHOR]

To reduce the occurrence of information loss and distortion in image style transfer, a method is proposed for researching and designing image style transfer technology based on multi‐scale convolutional neural networks (CNNs) feature fusion. Initially, the VGG19 model is designed for coarse and fine‐scale networks to achieve multi‐scale CNN feature extraction of target image information. Subsequently, while setting the corresponding feature loss function, an additional least‐squares penalty parameter is introduced to balance the optimal total loss function. Finally, leveraging the characteristics of stochastic gradient descent iteration, image features are fused and reconstructed to obtain better style transfer images. Experimental evaluations utilize peak signal‐to‐noise ratio (PSNR), structural similarity index (SSIM), information entropy (IE), and mean squared error (MSE) as metrics for assessing the transferred images, comparing them with three typical image style transfer methods. Results demonstrate that the proposed method achieves optimal performance across all metrics, realizing superior image style transfer effects. [ABSTRACT FROM AUTHOR]

Segmentation is crucial in diagnosing retinal diseases by accurately identifiying retinal vessels. This paper addresses the complexity of segmenting retinal vessels, highlighting the need for precise analysis of blood vessel structures. Despite the progress made by convolutional neural networsks (CNNs) in image segmentation, their limitations in capturing the global structure of retinal vsessels and maintaining segmentation continuity present challenges. To tackle these issues, our proposed network integrates graph convolutional networks (GCNs) and attention mechansims. This allows the model to consider pixel relationships and learn vessel graphical structures, significantly improving segmentation accuracy. Additionally, the attentional feature fusion module, including pixel‐wise and channel‐wise attention mechansims within the U‐Net architecture, refines the model's focus on relevant features. This paper emphasizes the importance of continuty preservation, ensuring an accurate representation of pixel‐level information and structural details during sefmentation. Therefore, our method performs as an effective solution to overcome challenges in retinal vessel segmentation. The proposed method outperformed the state‐of‐the‐art approaches on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (Structed Analysis of the Retina) datasets with accuracies of 0.12% and 0.14%, respecttively. Importantly, our proposed approach excelled in delineating slender and diminutive blood vessels, crucial for diagnosing vascular‐related diseases. Implementation is accessible on https://github.com/CVLab‐SHUT/VGA‐Net. [ABSTRACT FROM AUTHOR]

In recent years, low‐light image enhancement has become increasingly active. However, in underground mine environments, acquiring high‐quality images is still challenging due to low light, low contrast, and occlusion. To address this problem, this study proposes a low‐light image enhancement method for underground mine based on generative adversarial networks (UM‐GAN), which aims to take full advantage of the ability of GAN to achieve the restoration of details, the reduction of noise, and the improvement of overall image quality. The model proposed in this paper is divided into three main parts. Initially, a generator network adopting an encoder–decoder structure is developed. Subsequently, a novel strategy is introduced to merge information by utilizing inverted greyscale images and low‐light images as inputs. Further image quality enhancement is achieved by incorporating a noise reduction module employing the diffusion model. To ascertain the efficacy of the UM‐GAN method, evaluations are conducted on diverse real‐world and synthetic datasets, juxtaposing the approach against superior methods. Through qualitative and quantitative comparative experiments, the method showcases noteworthy advancements through qualitative and quantitative comparative experiments, substantiating its effectiveness. This research provides new ideas and methods for overcoming image quality problems in underground mine environments and contributes to the development of underground mine image processing. [ABSTRACT FROM AUTHOR]

The surface quality of steel strip is a critical indicator of the quality of hot‐rolled strip, so accurate inspection of its surface is essential. However, the complex texture of steel strip surface defects makes the detection challenging. Here, a multi‐scale feature fusion and attention based YOLOv5 (MFFA‐YOLOv5) model is proposed. Specifically, the bottom layer features are up‐sampled and fused not only with the middle layer features, but also with the top layer features, so that the model better captures the surface texture information of the steel strip. Secondly, an improved attention mechanism module is introduced to deal with the global and local information of the steel strip surface by introducing down‐sampling and up‐sampling paths based on Convolutional Block Attention Module (CBAM). Meanwhile, a self‐attention mechanism path is added to improve the capability of feature representation. Experimental results on the NEU‐DET dataset show that the MFFA‐YOLOv5 model significantly outperforms other state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Slug flow processes draw much attention in chemical and pharmaceutical manufacturing thanks to their ability to eliminate downtime costs and batch‐to‐batch variation. Using in‐line video can monitor the current process status and improve the stability of the slug flow. However, there are no effective image processing methods aiming at such videos from chemical experiments due to limited training sample size and the variety of experimental settings. The paper proposes a training‐free method to automatically detect and measure the slugs from in‐line videos. Multiple image features are fused to identify the slug shapes under various lighting conditions, a six‐point model is fitted to achieve better volume estimation, and a consistency score is estimated to quantify the detection uncertainty. The proposed algorithm achieves similar results to manual labeling for various types of slug flow processes, improving the accuracy of slug column estimation by a large margin compared to the existing automatic methods. Finally, using it to monitor the slug flow process's stability and the change of the slug volume in an injection point are demonstrated. The method not only shows that handcrafted image features have the capability for detection and segmentation from chemical experiment images but also paves the road for a training‐based algorithm for the task. [ABSTRACT FROM AUTHOR]

The demand for less complex and more accurate architectures has always been a priority since the broad usage of computer vision in everyday life, like auto‐drive cars, portable applications, augmented reality systems, medical image analysis etc. There are a lot of methods that have been developed to improve the accuracy and complexity of object detection, like the generations of R‐CNNs and YOLOs. However, these methods are not the most efficient architectures, and there is always room to improve. In this study, the 5th version of YOLO is employed and the improved architecture, Inception‐YOLO, is presented. The model significantly outperforms the SOTA YOLO family. Specifically, the improvements can be summarised as follows: impressive improvement of floating point operations (FLOPs) and number of parameters, as well as improvement in accuracy compared to the models with fewer FLOPs. All our presented approaches, like the optimized inception module, proposed structures for CSP and SPPF, and the improved loss function used in this research, work together to incrementally improve detection results, accuracy, demanded memory, and FLOPs simultaneously. For a glimpse of performance, the Inception‐YOLO‐S model hits 38.7% AP with 5.9M parameters and 11.5 BFLOPs and outperforms YOLOv5‐S with 37.4% AP, 7.2M parameters, and 16.5 BFLOPs. [ABSTRACT FROM AUTHOR]

Low‐light image enhancement is a longstanding challenge in low‐level vision, as images captured in low‐light conditions often suffer from significant aesthetic quality flaws. Recent methods based on deep neural networks have made impressive progress in this area. In contrast to mainstream convolutional neural network (CNN)‐based methods, an effective solution inspired by the transformer, which has shown impressive performance in various tasks, is proposed. This solution is centred around two key components. The first is an image synthesis pipeline, and the second is a powerful transformer‐based pre‐trained model, known as the low‐light image enhancement transformer (LIET). The image synthesis pipeline includes illumination simulation and realistic noise simulation, enabling the generation of more life‐like low‐light images to overcome the issue of data scarcity. LIET combines streamlined CNN‐based encoder‐decoders with a transformer body, efficiently extracting global and local contextual features at a relatively low computational cost. The extensive experiments show that this approach is highly competitive with current state‐of‐the‐art methods. The codes have been released and are available at LIET. [ABSTRACT FROM AUTHOR]

In the realm of video salient object detection (VSOD), the majority of research has traditionally been centered on third‐person perspective videos. However, this focus overlooks the unique requirements of certain first‐person tasks, such as autonomous driving or robot vision. To bridge this gap, a novel dataset and a camera‐based VSOD model, CaMSD, specifically designed for egocentric videos, is introduced. First, the SalEgo dataset, comprising 17,400 fully annotated frames for video salient object detection, is presented. Second, a computational model that incorporates a camera movement module is proposed, designed to emulate the patterns observed when humans view videos. Additionally, to achieve precise segmentation of a single salient object during switches between salient objects, as opposed to simultaneously segmenting two objects, a saliency enhancement module based on the Squeeze and Excitation Block is incorporated. Experimental results show that the approach outperforms other state‐of‐the‐art methods in egocentric video salient object detection tasks. Dataset and codes can be found at https://github.com/hzhang1999/SalEgo. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Computer Vision, discussing the topic of advanced image restoration and enhancement. The editorial highlights the challenges faced in this field, such as the complexity of degradation models for real-world low-quality images and the difficulty of acquiring paired data. It also introduces a special issue of the journal that includes five accepted papers, which focus on video reconstruction and image super-resolution. The editorial concludes by providing brief summaries of each accepted paper. The guest editors of the special issue are also mentioned, along with their research interests and affiliations. [Extracted from the article]

Perception systems in autonomous vehicles need to accurately detect and classify objects within their surrounding environments. Numerous types of sensors are deployed on these vehicles, and the combination of such multimodal data streams can significantly boost performance. The authors introduce a novel sensor fusion framework using deep convolutional neural networks. The framework employs both camera and LiDAR sensors in a multimodal, multiview configuration. The authors leverage both data types by introducing two new innovative fusion mechanisms: element‐wise multiplication and multimodal factorised bilinear pooling. The methods improve the bird's eye view moderate average precision score by +4.97% and +8.35% on the KITTI dataset when compared to traditional fusion operators like element‐wise addition and feature map concatenation. An in‐depth analysis of key design choices impacting performance, such as data augmentation, multi‐task learning, and convolutional architecture design is offered. The study aims to pave the way for the development of more robust multimodal machine vision systems. The authors conclude the paper with qualitative results, discussing both successful and problematic cases, along with potential ways to mitigate the latter. [ABSTRACT FROM AUTHOR]

Recent advances in deep convolutional neural networks have shown improved performance in face super‐resolution through joint training with other tasks such as face analysis and landmark prediction. However, these methods have certain limitations. One major limitation is the requirement for manual marking information on the dataset for multi‐task joint learning. This additional marking process increases the computational cost of the network model. Additionally, since prior information is often estimated from low‐quality faces, the obtained guidance information tends to be inaccurate. To address these challenges, a novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding. Specifically, the proposed GLFEU is composed of an attention branch and a Transformer branch, to simultaneously restore global facial structure and local texture details. Additionally, a Multi‐Stage Feature Fusion Module is incorporated to fuse features from different network stages, further improving the quality of the restored face images. Compared with previous methods, DCTNet improves Peak Signal‐to‐Noise Ratio by 0.23 and 0.19 dB on the CelebA and Helen datasets, respectively. Experimental results demonstrate that the designed DCTNet offers a simple yet powerful solution to recover detailed facial structures from low‐quality images. [ABSTRACT FROM AUTHOR]

In recent years, many methods for image super‐resolution (SR) have relied on pairs of low‐resolution (LR) and high‐resolution (HR) images for training, where the degradation process is predefined by bicubic downsampling. While such approaches perform well in standard benchmark tests, they often fail to accurately replicate the complexity of real‐world image degradation. To address this challenge, researchers have proposed the use of unpaired image training to implicitly model the degradation process. However, there is a significant domain gap between the real‐world LR and the synthetic LR images from HR, which severely degrades the SR performance. A novel unsupervised image‐blind super‐resolution method that exploits degradation feature‐based learning for real‐image super‐resolution reconstruction (RDFL) is proposed. Their approach learns the degradation process from HR to LR using a generative adversarial network (GAN) and constrains the data distribution of the synthetic LR with real degraded images. The authors then encode the degraded features into a Transformer‐based SR network for image super‐resolution reconstruction through degradation representation learning. Extensive experiments on both synthetic and real datasets demonstrate the effectiveness and superiority of the RDFL method, which achieves visually pleasing reconstruction results. [ABSTRACT FROM AUTHOR]

Mobile devices and handheld systems, such as the smartphones and tablets universally extended, are becoming increasingly powerful. Their basic hardware configuration is usually state-of-the-art heterogeneous architectures consisting of multi-core processors and some kind of accelerator such as GPUs or DSPs. Specific code adapted to the architecture is mandatory if high-performance computation is required and low-level libraries and parallelism are needed, which constitutes an important barrier for the usual developer in such devices. In this context, we propose the FancyJCL framework. It provides a high-level abstraction layer that hides implementation details and allows to develop parallel programs for mobile devices. The target platform for FancyJCL is mainly Android and Java developers due to their high market penetration. A very simple, seemingly sequential encoding results in parallel efficient OpenCL code. FancyJCL is itself based on the Fancier framework, which enables optimal memory management across memory spaces on unified memory systems. Benchmarks of FancyJCL code developed for a wide range of image processing algorithms show good performance with low development effort. [ABSTRACT FROM AUTHOR]

Conventional image processing and machine learning based on handcrafted features struggle to meet the real time and high-accuracy requirements for industrial defect detection in complex, sensitive, and dynamic environments. To address this issue, this paper proposes AENet, a novel real-time defect detection network based on an encoder-decoder model, which achieves high detection accuracy and efficiency while demonstrating excellent convergence and generalization. Firstly, a spatial channel attention module in the encoding network is designed to exploit both spatial attention and channel attention using a multi-head 3D self-attention mechanism. This improves parallelism and detection efficiency. Secondly, the decoding network of AENet incorporates the cross-level attention fusion module, which fuses input features from different layers. Combined with multi-level upsampling design, the decoder enhances the representation of defect details. Furthermore, we insert a simplified aggregator into the encoder-decoder network to extract feature information at different scales with low computational cost. This aggregation process aids in training and inference on industrial defect datasets by incorporating contextual information. Extensive experimental results demonstrate that AENet outperforms other segmentation models in accomplishing defect recognition and segmentation in challenging optical environments. It exhibits a faster convergence than other networks and a balance between accuracy and speed. It achieves a recognition accuracy of over 96% for almost all types of defects in the actual industrial environment on the NVIDIA Tesla V100 GPU. [ABSTRACT FROM AUTHOR]

While the fabric of soil can significantly influence its behaviour, the effect of varying fabric parameters on the subgrade shear response is still not well understood. This study creates soil specimens with different fabrics which are then captured through X-ray microscopic-computed tomography scanning and quantified by image processing techniques. A comprehensive laboratory investigation is conducted to understand how the soil fabric affects its monotonic and cyclic shear behaviour. The results indicate that the consolidation method creates a more homogeneous fabric with mainly small-to-medium interconnected pores, whereas the compaction technique creates significantly large and mostly inter-aggregate pores with lower connectivity. In this regard, the consolidated specimens exhibit an elastic-perfectly plastic behaviour, while the compacted specimens show strain-hardening transformation during isotropic monotonic shearing. Under anisotropic conditions, the compacted specimens exhibit a greater strain softening response and excess pore pressure than the consolidated specimens because they have a weaker fabric. Furthermore, the compacted specimens show a smaller threshold strain at a lower critical number of cycles due to the collapse of large pores. These current findings prove the decisive role that soil fabric plays in determining the shear response and failure of subgrade soils. [ABSTRACT FROM AUTHOR]

Rock strength parameters such as uniaxial compressive strength and modulus of elasticity are crucial parameters in designing rock engineering structures. Owing to the importance of the aforementioned parameters, in this paper, image processing technique is coupled with artificial neural network (ANN) method for assessing the uniaxial compressive strength and modulus of elasticity of sandstones. For this reason, 102 core sandstone samples were prepared. Subsequently petrographic analyses and imaging operation for 102 images were performed. Principal component analysis was then conducted for feature reduction purposes. At last, an ANN model, which received its input data from image processing technique, was constructed for assessing the UCS and E of sandstone samples. Overall, the best performance of the network was obtained when 10 hidden nodes were used. The correlation coefficient (R) values of 0.9722 and 0.97062 for UCS and E, respectively, suggest the feasibility of the proposed model. [ABSTRACT FROM AUTHOR]

Apple-picking robot can promote the development of smart agriculture, and accurate object recognition in complex natural environments using deep learning algorithms is critical. However, research has shown that changes in illumination and object occlusion remain significant challenges for recognition. In order to improve the accuracy of apple apple-picking robot’s identification and positioning of apples in natural environment, a method using YOLOv5 (You Only Look Once, YOLO) combined with fast-guided filter is proposed. By introducing a fast-guided filtering module, the ability to extract image features is improved, and the problem of inaccurate occlusion targets and edge detection is solved; K-means clustering algorithm is introduced in improving YOLOv5, which can realize automatic adjustment of image size and step size; BiFPN structure is introduced in Neck network to add weighted feature fusion to highlight the detailed features. The results show that the algorithm proposed in this paper can well remove noise information such as occlusion edge blurring in apple images in a natural light environment. In the real orchard environment, the apple recognition accuracy rate reached 97.8%, the recall rate was 97.3% and the recognition rate was about 26.84fps. The results show that this research based on YOLOv5 and fast-guided filtering can realize fast and accurate identification of apple fruits in natural environment, and meet the practical application requirements of real-time target detection. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for 3D data cube denoising, where the 3D data cube is corrupted by noise with spatially varying noise levels. We perform 3D dual tree complex wavelet transform (DTCWT) to the 3D data cube, and then conduct wavelet-based thresholding based on three scales of dependency in wavelet coefficients. Instead of using the global noise level, we estimate the noise levels locally, which improve the denoising results substantially. We conduct inverse DTCWT to obtain the noise reduced data cubes. Experiments demonstrate that our proposed method outperforms block matching and 3D filtering, video block matching and 3D filtering, 2D bivariate shrinkage, and 3D bivariate shrinkage significantly for noise reduction of 3D data cubes. [ABSTRACT FROM AUTHOR]

Decomposing an image into meaningful components is an effective way for image processing. Making full use of cartoon features and texture features with deep neural networks may further achieve the stable noise cancellation performance for low-dose computed tomography (LDCT) denoising. However, the performance of conventional deep neural networks is limited by their black-box nature. To overcome this drawback, we proposed an algorithm unrolling approach for LDCT denoising, namely, the cartoon-texture features guided network (CTFG-Net). The CTFG-Net integrates a cartoon sub-network, a texture sub-network, and a fusion sub-network into an end-to-end convolutional neural network model. A cartoon decomposition algorithm and a texture decomposition algorithm were unrolled to the cartoon sub-network and the texture sub-network, respectively. These two sub-networks were employed to decompose a LDCT image into its cartoon components and texture components. During the process of image decomposition, these two sub-networks exploited cartoon features and texture features to greatly suppress noise and remove artifacts in the corresponding components. At last, the final denoised results were yielded through a data fusion of the denoised cartoon components and the denoised texture components. The proposed model was tested with three datasets, Mayo dataset, Piglet dataset, and AbdomenCT-1K dataset. Qualitative results show that the CTFG-Net achieved better denoising effects for LDCT images than the competing algorithms. Compared to the competing algorithms, the proposed CTFG-Net also improved the peak signal-to-noise ratio, structural similarity index measure, and visual information fidelity by (0.3994 dB and 0.7692 dB), (0.0115 and 0.0056), and (0.0751 and 0.0433) with Mayo dataset and Piglet dataset. [ABSTRACT FROM AUTHOR]

Approximate multipliers are widely used in image processing and multimedia signal processing applications for the reduction in area, computation time, and power consumption. 4:2 compressors play a key role in multipliers for efficient addition of partial product bits. In this paper, an inexact 4:2 compressor is proposed, where a major portion of the logic associated with the generation of Carry and Sum are shared to reduce the logic/circuit complexity. During the design time overestimates are balanced with the underestimates so as to reduce the total error distance. The proposed compressor is used for the addition of partial products of the Baugh-Wooley multiplier. A novel algorithm is proposed for the placement of inexact 4:2 compressors in the partial product bit array, based on the minimum peak signal-to-noise ratio requirement of the application. The approximate multipliers thus obtained are used for edge detection using Sobel operator. It is observed from the Pareto analysis that the proposed design offers significant saving in area, computation time, and power consumption over the design with nearly the same error performance. Besides, the proposed design is more error tolerant compared with the design with nearly the same area-delay trade-off and power-delay trade-off. Moreover, the proposed inexact 4:2 compressor-based Baugh-Wooley multiplier is found to offer better accuracy-area trade-off compared to the state-of-the-art 4:2 compressors in convolutional neural network-based classification. [ABSTRACT FROM AUTHOR]

Many algorithms for image processing do not require particularly high precision, but they rely on complicated arithmetic operations for every pixel in an image. The Bernsen algorithm is a typical local thresholding algorithm for solving the problem of uneven lighting. However, this algorithm requires a significant computing overhead and is extremely sensitive to noise. In this work, two stochastic computing architectures are proposed for implementing the Bernsen algorithm by using, respectively, uncorrelated and correlated input bitstreams. Experimental results show that both designs, especially the one using correlated bitstreams, present high fault tolerance of soft errors and low hardware cost in comparison with its conventional binary implementation. However, SC logic with uncorrelated inputs is not always superior to its corresponding binary circuit in energy consumption, especially the circuit that needs long input bitstreams. That means that a reasonable use of correlation can further optimize the SC circuit design. [ABSTRACT FROM AUTHOR]

• Phisically-based thermal infrared images rendering chain for artificial satellite targets. • Assessment and comparison of most relevant pixel-level VIS-TIR image fusion techniques. • Fused noisy image processing within the context of uncooperative space-craft relative navigation. State-of-the-art techniques for vision-based relative navigation rely on images acquired in the visible spectral band. Consequently, the accuracy and robustness of the navigation is strongly influenced by the illumination conditions. The exploitation of thermal-infrared images for navigation purposes is studied in the present paper, as a possible solution to improve navigation in close proximity with a target spacecraft. Thermal-infrared images depend on the thermal radiation emitted by the target, hence, they are independent from light conditions; however, they suffer from a poorer texture and a lower contrast with respect to visible ones. This paper proposes pixel-level image fusion to overcome the limitations of the two types of images. The two source images are merged into a more informative one, retaining the strengths of the distinguished sensing modalities. The contribution of this work is twofold: firstly, a realistic thermal infrared images rendering tool for artificial targets is implemented; secondly, different pixel-level visible-thermal infrared images fusion techniques are assessed through qualitative and quantitative performance metrics to ease and improve the subsequent image processing step. The work presents a comprehensive evaluation of the best fusion techniques for on-board implementation, paving the way to the development of a multispectral end-to-end navigation chain. [ABSTRACT FROM AUTHOR]

Spiking neural membrane systems (SN P systems) are a class of bio-inspired models inspired by the activities and connectivity of neurons. Extensive studies have been made on SN P systems with synchronization-based communication, while further efforts are needed for the systems with rhythm-based communication. In this work, we design an asynchronous SN P system with resonant connections where all the enabled neurons in the same group connected by resonant connections should instantly produce spikes with the same rhythm. In the designed system, each of the three modules implements one type of the three operations associated with the edge detection of digital images, and they collaborate each other through the resonant connections. An algorithm called EDSNP for edge detection is proposed to simulate the working of the designed asynchronous SN P system. A quantitative analysis of EDSNP and the related methods for edge detection had been conducted to evaluate the performance of EDSNP. The performance of the EDSNP in processing the testing images is superior to the compared methods, based on the quantitative metrics of accuracy, error rate, mean square error, peak signal-to-noise ratio and true positive rate. The results indicate the potential of the temporal firing and the proper neuronal connections in the SN P system to achieve good performance in edge detection. [ABSTRACT FROM AUTHOR]

Conventional photography can only provide a two-dimensional image of the scene, whereas emerging imaging modalities such as light field enable the representation of higher dimensional visual information by capturing light rays from different directions. Light fields provide immersive experiences, a sense of presence in the scene, and can enhance different vision tasks. Hence, research into light field processing methods has become increasingly popular. It does, however, come at the cost of higher data volume and computational complexity. With the growing deployment of machine-learning and deep architectures in image processing applications, a paradigm shift toward learning-based approaches has also been observed in the design of light field processing methods. Various learning-based approaches are developed to process the high volume of light field data efficiently for different vision tasks while improving performance. Taking into account the diversity of light field vision tasks and the deployed learning-based frameworks, it is necessary to survey the scattered learning-based works in the domain to gain insight into the current trends and challenges. This paper aims to review the existing learning-based solutions for light field imaging and to summarize the most promising frameworks. Moreover, evaluation methods and available light field datasets are highlighted. Lastly, the review concludes with a brief outlook for future research directions. [ABSTRACT FROM AUTHOR]

Background: Plants are known to be infected by a wide range of pathogenic microbes. To study plant diseases caused by microbes, it is imperative to be able to monitor disease symptoms and microbial colonization in a quantitative and objective manner. In contrast to more traditional measures that use manual assignments of disease categories, image processing provides a more accurate and objective quantification of plant disease symptoms. Besides monitoring disease symptoms, computational image processing provides additional information on the spatial localization of pathogenic microbes in different plant tissues. Results: Here we report on an image analysis tool called ScAnalyzer to monitor disease symptoms and bacterial spread in Arabidopsis thaliana leaves. Thereto, detached leaves are assembled in a grid and scanned, which enables automated separation of individual samples. A pixel color threshold is used to segment healthy (green) from chlorotic (yellow) leaf areas. The spread of luminescence-tagged bacteria is monitored via light-sensitive films, which are processed in a similar manner as the leaf scans. We show that this tool is able to capture previously identified differences in susceptibility of the model plant A. thaliana to the bacterial pathogen Xanthomonas campestris pv. campestris. Moreover, we show that the ScAnalyzer pipeline provides a more detailed assessment of bacterial spread within plant leaves than previously used methods. Finally, by combining the disease symptom values with bacterial spread values from the same leaves, we show that bacterial spread precedes visual disease symptoms. Conclusion: Taken together, we present an automated script to monitor plant disease symptoms and microbial spread in A. thaliana leaves. The freely available software (https://github.com/MolPlantPathology/ScAnalyzer) has the potential to standardize the analysis of disease assays between different groups. [ABSTRACT FROM AUTHOR]

The article explores advanced image processing techniques for pigment discrimination in rock art paintings, emphasizing color separation using RGB (red, green, blue) and LHCUv (Luminance, Hue, Chroma) imagery. It highlights the use of dimensionality reduction methods such as Principal Components Analisys PCA and Independent Component Analysis (ICA), with a focus on Gaussian Mixture Models (GMM) for probabilistic classification of image elements. This approach, applied to the Chomache archaeological site on the northernmost coast of the Atacama Desert in Chile, reveals previously undetected motifs and details, offering a nuanced perspective in rock art documentation and analysis. This proposal reinforces the value of rock art panel not only as a finished product but as a process. [ABSTRACT FROM AUTHOR]

Background: X-ray computed tomography (CT) is a powerful tool for measuring plant root growth in soil. However, a rapid scan with larger pots, which is required for throughput-prioritized crop breeding, results in high noise levels, low resolution, and blurred root segments in the CT volumes. Moreover, while plant root segmentation is essential for root quantification, detailed conditional studies on segmenting noisy root segments are scarce. The present study aimed to investigate the effects of scanning time and deep learning-based restoration of image quality on semantic segmentation of blurry rice (Oryza sativa) root segments in CT volumes. Results: VoxResNet, a convolutional neural network-based voxel-wise residual network, was used as the segmentation model. The training efficiency of the model was compared using CT volumes obtained at scan times of 33, 66, 150, 300, and 600 s. The learning efficiencies of the samples were similar, except for scan times of 33 and 66 s. In addition, The noise levels of predicted volumes differd among scanning conditions, indicating that the noise level of a scan time ≥ 150 s does not affect the model training efficiency. Conventional filtering methods, such as median filtering and edge detection, increased the training efficiency by approximately 10% under any conditions. However, the training efficiency of 33 and 66 s-scanned samples remained relatively low. We concluded that scan time must be at least 150 s to not affect segmentation. Finally, we constructed a semantic segmentation model for 150 s-scanned CT volumes, for which the Dice loss reached 0.093. This model could not predict the lateral roots, which were not included in the training data. This limitation will be addressed by preparing appropriate training data. Conclusions: A semantic segmentation model can be constructed even with rapidly scanned CT volumes with high noise levels. Given that scanning times ≥ 150 s did not affect the segmentation results, this technique holds promise for rapid and low-dose scanning. This study offers insights into images other than CT volumes with high noise levels that are challenging to determine when annotating. [ABSTRACT FROM AUTHOR]

Introduction: In recent decades, numerous large survey projects have been initiated to enhance our understanding of the cosmos. Among these, the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) stands out as a flagship project of the Stage IV cosmology imaging surveys, offering an open-source framework for data management and processing adaptable to various instruments. Methods: In this paper, we introduce the 'obs_mccd' software package, designed to serve as a bridge linking raw data from generic mosaic-CCD instruments to the LSST data management framework. The package also facilitates the deployment of tailored configurations to the pipeline middleware. To validate our data processing pipeline, we processed a batch of realistic data from a commissioning wide-field telescope. Results: We established a prototype of the quality control (QC) system capable of assessing image quality parameters such as PSF size, ellipticity, and astrometric calibration. Our findings indicate that using a fifth-order polynomial for astrometric calibration effectively characterizes geometric distortion, achieving a median average geometric distortion residual of 0.011 pixel. Discussion: When comparing the performance of our pipeline to our inhouse pipeline applied to the same dataset, we observed that our new 'obs_mccd' pipeline offers improved precision, reducing the median average geometric distortion residual from 0.016 pixel to 0.011 pixel. This enhancement in performance underscores the benefits of the obs_mccd package in managing and processing data from wide-field surveys, and it opens up new avenues for scientific exploration with smaller, flexible survey systems complementing the LSST. [ABSTRACT FROM AUTHOR]

Tools for implementing a systematic quality management are necessary for the use of material extrusion as an additive manufacturing process for products with high quality requirements. Well-defined quality classes are crucial for ensuring that the requirements for a product can be communicated transparently and that the existing properties can be evaluated. Furthermore, there is a lack of capable measurement equipment for the acquisition of process data during the production process. To address these challenges, the present paper introduces an image processing system that determines quality indicators for individual layers in terms of imperfect surface percentages and the number of imperfections. The central element of the hardware is an adaptive darkfield illumination, which leads to high-contrast images. In addition, five types of layer subareas are identified in a segmentation step. Unsupervised machine learning methods are then used to detect imperfections in each layer subarea. In the segmentation, the current layer can be distinguished from irrelevant image background regions with an F-measure of 0.981. For the layer-wise measurement of the quality indicators, relative measurement errors with standard deviations of 25 to 76.1% are found. After evaluating the capabilities of the image processing system, a proposal for limits of quality classes is derived by monitoring several material extrusion processes. For this purpose, three quality classes for each of the five layer subareas are deduced from the process scatter measured by the image processing system. The results are an important contribution to the industrialization of material extrusion in safety–critical areas such as medical technology or the aerospace industry. [ABSTRACT FROM AUTHOR]

Converting a camera's RAW image to an RGB format for human perception involves utilizing an imaging pipeline, and a series of processing modules. Existing modules often result in varying degrees of original information loss, which can render the reverse imaging pipeline unable to recover the original RAW image information. To this end, this paper proposes a new, almost reversible image imaging pipeline. Thus, RGB images and RAW images can be effectively converted between each other. Considering the impact of original information loss, this paper introduces a two-stage tone mapping operation (TMO). In the first stage, the RAW image with a linear response is transformed into an RGB color image. In the second stage, color scale mapping corrects the dynamic range of the image suitable for human perception through linear stretching, and reduces the loss of sensitive information to the human eye during the integer process. effectively preserving the original image's dynamic information. The DCRAW imaging pipeline addresses the problem of high light overflow by directly highlighting cuts. The proposed imaging pipeline constructs an independent highlight processing module, and preserves the highlighted information of the image. The experimental results demonstrate that the two-stage tone mapping operation embedded in the imaging processing pipeline provided in this article ensures that the image output is suitable for human visual system (HVS) perception and retains more original image information. [ABSTRACT FROM AUTHOR]

Cancer Stem Cells presumably drive tumor growth and resistance to conventional cancer treatments. From a previous computational model, we inferred that these cells are not uniformly distributed in the bulk of a tumorsphere. To confirm this result, we cultivated tumorspheres enriched in stem cells, and performed immunofluorescent detection of the stemness marker SOX2 using confocal microscopy. In this article, we present an image processing method that reconstructs the amount and location of the Cancer Stem Cells in the spheroids. Its advantage is the use of a statistical criterion to classify the cells in Stem and Differentiated, instead of setting an arbitrary threshold. Moreover, the analysis of the experimental images presented in this work agrees with the results from our computational models, thus enforcing the notion that the distribution of Cancer Stem Cells in a tumorsphere is non-homogeneous. Additionally, the method presented here provides a useful tool for analyzing any image in which different kinds of cells are stained with different markers. [ABSTRACT FROM AUTHOR]

In the finite element analysis of asphalt concrete (AC), it is nowadays common to incorporate the information from the underlying scales to study the overall response of this material. Heterogeneity observed at the asphalt mixture scale is analyzed in this paper. Reliable finite element analysis (FEA) of asphalt concrete comprises a set of complex issues. The two main aspects of the asphalt concrete FEA discussed in this study are: (1) digital reconstruction of the asphalt pavement microstructure using processing of the high-quality images; and (2) FEA of the asphalt concrete idealized samples accounting for the viscoelastic material model. Reconstruction of the asphalt concrete microstructure is performed using a sequence of image processing operations (binarization, removing holes, filtering, segmentation and boundaries detection). Geometry of the inclusions (aggregate) are additionally simplified in a controlled mode to reduce the numerical cost of the analysis. As is demonstrated in the study, the introduced geometry simplifications are justified. Computational cost reduction exceeds of several orders of magnitude additional modeling error occurring due to the applied simplification technique. Viscoelastic finite element analysis of the AC identified microstructure is performed using the Burgers material model. The analysis algorithm is briefly described with a particular focus on the computational efficiency aspects. In order to illustrate the proposed approach, a set of 2D problems is solved. Numerical results confirm both the effectiveness of the self-developed code and the applicability of the Burgers model to the analyzed class of AC analysis problems. Further research directions are also described to highlight the potential benefits of the developed approach to numerical modeling of asphalt concrete. [ABSTRACT FROM AUTHOR]

While binder jetting (BJ) additive manufacturing (AM) holds considerable promise for industrial applications, defects often compromise part quality. This study addresses these challenges by investigating binding mechanisms and analyzing common defects, proposing tailored solutions to mitigate them. Emphasizing defect identification for effective quality control in BJ-AM, this research offers strategies for in-process rectification and post-process evaluation to elevate part quality. It shows how to successfully process metallic parts with complex geometries while maintaining consistent material properties. Furthermore, the paper explores the microstructure of AISI M2 tool steel, utilizing advanced image processing techniques like digital image analysis and SEM images to evaluate carbide distribution. The results show that M2 tool steel has a high proportion of M6C carbides, with furnace-cooled samples ranging from ~2.4% to 7.1% and MC carbides from ~0.4% to 9.4%. M6C carbides ranged from ~2.6% to 3.8% in air-cooled samples, while water-cooled samples peaked at ~8.52%. Sintering conditions also affected shrinkage, with furnace-cooled samples showing the lowest rates (1.7 ± 0.4% to 5 ± 0.4%) and water-cooled samples showing the highest (2 ± 0.4% to 14.1 ± 0.4%). The study recommends real-time defect detection systems with autonomous corrective capabilities to improve the quality and performance of BJ-AM components. [ABSTRACT FROM AUTHOR]

The process of image fusion is the process of enriching an image and improving the image's quality, so as to facilitate the subsequent image processing and analysis. With the increasing importance of image fusion technology, the fusion of infrared and visible images has received extensive attention. In today's deep learning environment, deep learning is widely used in the field of image fusion. However, in some applications, it is not possible to obtain a large amount of training data. Because some special organs of snakes can receive and process infrared information and visible information, the fusion method of infrared and visible light to simulate the visual mechanism of snakes came into being. Therefore, this paper takes into account the perspective of visual bionics to achieve image fusion; such methods do not need to obtain a significant amount of training data. However, most of the fusion methods for simulating snakes face the problem of unclear details, so this paper combines this method with a pulse coupled neural network (PCNN). By studying two receptive field models of retinal nerve cells, six dual-mode cell imaging mechanisms of rattlesnakes and their mathematical models and the PCNN model, an improved fusion method of infrared and visible images was proposed. For the proposed fusion method, eleven groups of source images were used, and three non-reference image quality evaluation indexes were compared with seven other fusion methods. The experimental results show that the improved algorithm proposed in this paper is better overall than the comparison method for the three evaluation indexes. [ABSTRACT FROM AUTHOR]

Precise and timely recognition of hazardous chemical substances is of great significance for safeguarding human health, ecological environment, public security, etc., especially crucial for adopting appropriate disposition measures. Up to now, there remains a practical challenge to sensitively detect and differentiate organic amines with similar chemical structures with intuitive analysis outcomes. Here, a unique optical probe with two electrophilic recognition sites for rapid and ultra‐sensitive ratiometric fluorescence detection of ethylenediamine (EDA) is presented, while producing distinct fluorescence signals to its structural analog. The probe exhibits ppb/nmol level sensitivity to liquidous and gaseous EDA, specific recognition toward EDA without disturbance to up to 28 potential interferents, as well as rapid fluorescence response within 0.2 s. By further combining the portable sensing chip with the convolutional algorithm endowed with image processing, this work cracked the problem of precisely discriminating the target and non‐targets at extremely low concentrations. [ABSTRACT FROM AUTHOR]

Lyotropic liquid crystals represent an important class of anisotropic colloid systems. Their integration with optically active nanoparticles can provide us with responsive luminescent media that offer new fundamental and applied solutions for biomedicine. This paper analyzes the molecular-level behavior of such composites represented by tetraethylene glycol monododecyl ether and nanoscale carbon dots in microfluidic channels. Microfluidic confinement allows for simultaneously applying multiple factors, such as flow dynamics, wall effects, and temperature, for the precise control of the molecular arrangement in such composites and their resulting optical properties. The microfluidic behavior of composites was characterized by a set of analytical and modeling tools such as polarized and fluorescent microscopy, dynamic light scattering, and fluorescent spectroscopy, as well as image processing in Matlab. The composites were shown to form tunable anisotropic intermolecular structures in microchannels with several levels of molecular ordering. A predominant lamellar structure of the composites was found to undergo additional ordering with respect to the microchannel axis and walls. Such an alignment was controlled by applying shear and temperature factors to the microfluidic environment. The revealed molecular behavior of the composite may contribute to the synthesis of hybrid organized media capable of polarized luminescence for on-chip diagnostics and biomimetics. [ABSTRACT FROM AUTHOR]

The fast scenario transfer for portrait styles has been a universal concern in the area of image processing. Conventionally, it was realized mostly by manual manipulation based on expertise experience, which costs a large amount of human labor. To fit the growing business volume in the era of Internet 4.0, it is supposed to investigate reliable autonomous workflow that generates portrait-style results via intelligent algorithms. Therefore, this paper proposes a fast scenario transfer method for portrait styles through collaborative awareness of convolutional neural network (CNN) and generative learning (GAL). On the one hand, a CNN structure is designed to make feature extraction towards the initial images, which can be used for following image generation. On the other hand, the GAL is utilized to generate new images with post-transferred scenario styles, so that the expected scenario style transfer results can be output by generating new images through long-term iterations. Especially, the loss function is designed by simultaneously considering local and global characteristics. Finally, the analysis and experimental results show that the correction process can be completed by injecting the extracted input face features into the feature maps of corresponding sizes in the generation process using a pre-trained feature extractor. Thus, the face conversion efficiency can be improved. [ABSTRACT FROM AUTHOR]

Online detection of action start is a significant and challenging task that requires prompt identification of action start positions and corresponding categories within streaming videos. This task presents challenges due to data imbalance, similarity in boundary content, and real‐time detection requirements. Here, a novel Time‐Attentive Fusion Network is introduced to address the requirements of improved action detection accuracy and operational efficiency. The time‐attentive fusion module is proposed, which consists of long‐term memory attention and the fusion feature learning mechanism, to improve spatial‐temporal feature learning. The temporal memory attention mechanism captures more effective temporal dependencies by employing weighted linear attention. The fusion feature learning mechanism facilitates the incorporation of current moment action information with historical data, thus enhancing the representation. The proposed method exhibits linear complexity and parallelism, enabling rapid training and inference speed. This method is evaluated on two challenging datasets: THUMOS'14 and ActivityNet v1.3. The experimental results demonstrate that the proposed method significantly outperforms existing state‐of‐the‐art methods in terms of both detection accuracy and inference speed. [ABSTRACT FROM AUTHOR]

An adaptively hybrid method was proposed to improve the performance of fractal coding methods. First, it is found that the range blocks with large variances (RBLVs) play a crucial role in degrading decoded images, and the effect of the remaining range blocks with small variances (RBSVs) can be ignored. Then, an adaptive method was proposed to divide the range blocks into the above two categories: RBLVs and RBSVs. Second, RBLVs were designed to be encoded in an extended domain block pool (EDBP). Then, better block‐matching effect can be obtained, which will result in better decoded image quality. Further, the no‐search fractal encoding method is adopted for RBSVs to achieve faster encoding speed and fewer bits per pixel (bpp). Finally, four fractal coding methods were adopted to assess the performance of the proposed method. Experimental results show that compared with the previous methods, the PSNR quality of decoded images in the proposed method can be improved by about 0.15–0.4 dB, about 20%–35% of the total computations in encoding process can be saved, and about 0.2 bpp can be saved. Moreover, under the same decoding time, the proposed method can achieve comparable or smaller deviations regarding the decoded image. [ABSTRACT FROM AUTHOR]

To address the challenges of detecting a large number of objects and a high proportion of small objects in aerial drone imagery, an aerial dense small object detection algorithm called coordinate position attention module you only look once (CPAM‐YOLO) is proposed based on the coordinate position attention module (CPAM). In the backbone network of CPAM‐YOLO, a CPAM is proposed and embedded that decomposes channel attention into two 1D feature encoding processes, and selectively combines the features of each position through the weighted sum of all position features. Finally, features are aggregated along two spatial directions, increasing the effective information utilization of input feature positions and channels. The backbone network, feature enhancement network, and detection heads have been optimized to improve detection accuracy while ensuring a lightweight detection network. Using lightweight backbone networks to significantly reduce the number of parameters while using high‐resolution feature enhancement networks to retain more semantic and detailed features. The algorithm's performance was evaluated using the publicly available VisDrone2019 dataset. Compared to the baseline network YOLOv5l, CPAM‐YOLO achieved a 4.5% improvement in mAP0.5 and a 3.2% improvement in mAP0.95. These experimental results demonstrate the strong practicality of the CPAM‐YOLO object detection network for detecting dense small objects in aerial image. [ABSTRACT FROM AUTHOR]

In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model. [ABSTRACT FROM AUTHOR]