Search

Countersink inspection is crucial in various automated assembly lines, especially in the aerospace and automotive sectors. Advancements in machine vision introduced automated robotic inspection of countersinks using laser scanners and monocular cameras. Nevertheless, the aforementioned sensing pipelines require the robot to pause on each hole for inspection due to high latency and measurement uncertainties with motion, leading to prolonged execution times of the inspection task. The neuromorphic vision sensor, on the other hand, has the potential to expedite the countersink inspection process, but the unorthodox output of the neuromorphic technology prohibits utilizing traditional image processing techniques. Therefore, novel event-based perception algorithms need to be introduced. We propose a countersink detection approach on the basis of event-based motion compensation and the mean-shift clustering principle. In addition, our framework presents a robust event-based circle detection algorithm to precisely estimate the depth of the countersink specimens. The proposed approach expedites the inspection process by a factor of 10 × compared to conventional countersink inspection methods. The work in this paper was validated for over 50 trials on three countersink workpiece variants. The experimental results show that our method provides a standard deviation of 0.025 mm and an accuracy of 0.026 mm for countersink depth inspection despite the low resolution of commercially available neuromorphic cameras. Video Link: https://www.dropbox.com/s/pateqqwh4d605t3/final_video_new.mp4?dl=0. [ABSTRACT FROM AUTHOR]

This research work focuses on the design and implementation of a highly advanced field-programmable gate array (FPGA)-based system-on-chip (SoC) solution for real-time edge detection. By utilizing a Zynq processor and leveraging the powerful Vivado software, the aim is to overcome the significant computational challenges associated with achieving real-time edge detection. Edge detection in real-time scenarios presents several obstacles, including the possibility of missing edges due to noise and the substantial processing requirements of any edge detection technique. To address these challenges, the proposed SoC system synergistically combines the computational capabilities of an FPGA board and a Zynq processor, harnessing hardware acceleration to achieve high-performance edge detection. The OV7670 camera module serves as the primary input medium, capturing image frames for subsequent processing. These captured frames undergo initial processing before being seamlessly transferred to the FPGA fabric through customized intellectual property (IP) blocks. These IP blocks efficiently handle crucial tasks such as frame capturing, conversion to AXI Stream interface signals, and integration with the video direct memory access (VDMA) IP. The VDMA IP plays a pivotal role by facilitating high-speed data movement between the FPGA fabric and the Zynq processor IP, thereby enabling streamlined and efficient data transfer and processing. At the heart of this project lies the real-time edge detection algorithm, which is skillfully implemented on the Zynq processor. The resulting edge-detected frames are then visually presented and displayed on an output device utilizing the AXI4-Stream to Video Out IP. To ensure optimal utilization of available hardware resources, the comprehensive Vivado software suite provides a wide array of tools for designing, implementing, and programming the FPGA fabric. By leveraging FPGA-based systems, this project effectively addresses the critical need for real-time edge detection in time-sensitive scenarios. The result is a portable and manageable device that exhibits versatility, as it can be employed in various applications while reliably detecting edges in real-time situations. [ABSTRACT FROM AUTHOR]

The construction industry plays an important role in China's economy. However, traditional construction quality inspection methods have problems such as low efficiency, high leakage rate, and poor real-time performance. Therefore, taking the appearance quality defects of reinforced concrete engineering as an example, this study combines building information models and computer vision technology. By this way, it can achieve automatic quality inspection and intelligent quality problem prevention, to improve the quality management level during the construction process. In this study, ResNet50 network was pre-trained and classified using a self-made defect image database. After transfer learning, the accuracy values of the training and testing sets remained stable at around 0.95 and the loss value remained stable at around 0.10 after 10 epochs, indicating a significant improvement in learning performance. In the defect area quantification experiment, four corner coordinates of the defect image were calculated. These corner coordinates are simultaneously obtained and saved during on-site image acquisition. According to the calculation results, the defect area of honeycomb is approximately 67.67 square centimetres. These results confirm that this method improves the efficiency and accuracy of quality inspection and has potential application in quality inspection of prefabricated building construction. [ABSTRACT FROM AUTHOR]

In various countries worldwide, the incidence of colon cancer-related deaths has been on the rise in recent years. Early detection of symptoms and identification of intestinal polyps are crucial for improving the cure rate of colon cancer patients. Automated computer-aided diagnosis (CAD) has emerged as a solution to the low efficiency of traditional methods relying on manual diagnosis by physicians. Deep learning is the latest direction of CAD development and has shown promise for colonoscopic polyp segmentation. In this paper, we present a multi-level encoder-decoder architecture for polyp segmentation based on the Transformer architecture, termed NA-SegFormer. To improve the performance of existing Transformer-based segmentation algorithms for edge segmentation on colon polyps, we propose a patch merging module with a neighbor attention mechanism based on overlap patch merging. Since colon tract polyps vary greatly in size and different datasets have different sample sizes, we used a unified focal loss to solve the problem of category imbalance in colon tract polyp data. To assess the effectiveness of our proposed method, we utilized video capsule endoscopy and typical colonoscopy polyp datasets, as well as a dataset containing surgical equipment. On the datasets Kvasir-SEG, Kvasir-Instrument and KvasirCapsule-SEG, the Dice score of our proposed model reached 94.30%, 94.59% and 82.73%, with an accuracy of 98.26%, 99.02% and 81.84% respectively. The proposed method achieved inference speed with an Frame-per-second (FPS) of 125.01. The results demonstrated that our suggested model effectively segmented polyps better than several well-known and latest models. In addition, the proposed method has advantages in trade-off between inference speed and accuracy, and it will be of great significance to real-time colonoscopic polyp segmentation. The code is available at https://github.com/promisedong/NAFormer. [ABSTRACT FROM AUTHOR]

Leukemia is a type of blood tumour that occurs because of abnormal enhancement in WBCs (white blood cells) in the bone marrow of the human body. Blood-forming tissue cancer influences the lymphatic and bone marrow system. The early diagnosis and detection of leukaemia, i.e., the accurate difference of malignant leukocytes with little expense at the beginning of the disease, is a primary challenge in the disease analysis field. Despite the higher occurrence of leukemia, there is a lack of flow cytometry tools, and the procedures accessible at medical diagnostics centres are time-consuming. Distinct researchers have implemented computer-aided diagnostic (CAD) and machine learning (ML) methods for laboratory image analysis, aiming to manage the restrictions of late leukemia analysis. This study proposes a new Falcon optimization algorithm with deep convolutional neural network for Leukemia detection and classification (FOADCNN-LDC) technique. The main objective of the FOADCNN-LDC technique is to classify and recognize leukemia. The FOADCNN-LDC technique utilizes a median filtering (MF) based noise removal process to eradicate the image noise. Besides, the FOADCNN-LDC technique employs the ShuffleNetv2 model for the feature extraction process. Moreover, the detection and classification of the leukemia process are performed by utilizing the convolutional denoising autoencoder (CDAE) model. The FOA is implemented to select the hyperparameter of the CDAE model. The simulation process of the FOADCNN-LDC approach is performed on a benchmark medical dataset. The investigational analysis of the FOADCNN-LDC approach highlighted a superior accuracy value of 99.62% over existing techniques. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of granular image detection during image scaling, an image scaling algorithm combining the interpolation algorithm of protective features and Kalman filtering of neurons is proposed. Firstly, the interpolation algorithm of protective features is de‐designed according to the phenomenon of sudden change of edge grey values, and the difference and trend of grey values in horizontal and vertical directions are used to obtain the pre‐scaled image with maximum contrast. Then the grey value data input of the pre‐scaled image is introduced into the Kalman filter of neurons, and the filtering process is optimized by using the black‐box thinking of neurons, and the pre‐scaled image is smoothed. Finally, the scale transformation is implemented to obtain the final grey value to complete the final scaling, so that the image has both visual experience and features. Comparison with mainstream image scaling algorithms shows that the proposed algorithm can effectively overcome the degradation of granularity image detection accuracy due to image scaling, with point acutance value (PAV) improved by 10%–41%, and the granularity detection error caused by image scaling algorithms reduced from about 0.7% to about 0.1%, with a relative improvement of 85%. [ABSTRACT FROM AUTHOR]

Head pose estimation is an especially challenging task due to the complexity nonlinear mapping from 2D feature space to 3D pose space. To address the above issue, this paper presents a novel and efficient head pose estimation framework based on particle swarm optimized contrastive learning and multimodal entangled graph convolution network. Firstly, a new network, the region and difference‐aware feature pyramid network (RD‐FPN), is proposed for 2D keypoints detection to alleviate the background interference and enhance the feature expressiveness. Then, particle swarm optimized contrastive learning is constructed to alternatively match 2D and 3D keypoints, which takes the multimodal keypoints matching accuracy as the optimization objective, while considering the similarity of cross‐modal positive and negative sample pairs from contrastive learning as a local contrastive constraint. Finally, multimodal entangled graph convolution network is designed to enhance the ability of establishing geometric relationships between keypoints and head pose angles based on second‐order bilinear attention, in which point‐edge attention is introduced to improve the representation of geometric features between multimodal keypoints. Compared with other methods, the average error of our method is reduced by 8.23%, indicating the accuracy, generalization, and efficiency of our method on the 300W‐LP, AFLW2000, BIWI datasets. [ABSTRACT FROM AUTHOR]

Transformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors' ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors' proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost. [ABSTRACT FROM AUTHOR]

As generative models become more advanced and essential, interest in using these models for image editing is growing. Nevertheless, conventional image editing methods still have many problems and can alter the intrinsic properties (e.g. geometry) of an object during the editing process. In this article, a novel geometry‐preserved image editing method is presented, where key points, keyframe, or canny edges are utilized as inputs for geometric constraints. A text prompt is fed into the inversion pipeline along with the input image and key points/keyframes/canny for editing. Then, new images are generated based on the editing pipeline of the denoising diffusion implicit model. Experiments demonstrate that the method outperforms its baselines. [ABSTRACT FROM AUTHOR]

Potholes and other road surface damages pose significant risks to vehicles and traffic safety. The current methods of in situ visual inspection for potholes or cracks are inefficient, costly, and hazardous. Therefore, there is a pressing need to develop automated systems for assessing road surface conditions, aiming to efficiently and accurately reconstruct, recognize, and locate potholes. In recent years, various methods utilizing (a) computer vision, (b) three-dimensional (3D) point clouds, or (c) smartphone data have been employed to map road surface quality conditions. Machine learning and deep learning techniques have increasingly enhanced the performance of these methods. This review aims to provide a comprehensive overview of cutting-edge computer vision and machine learning algorithms for pothole detection. It covers topics such as sensing systems for acquiring two-dimensional (2D) and 3D road data, classical algorithms based on 2D image processing, segmentation-based algorithms using 3D point cloud modeling, machine learning, deep learning algorithms, and hybrid approaches. The review highlights that hybrid methods combining traditional image processing and advanced machine learning techniques offer the highest accuracy in pothole detection. Machine learning approaches, particularly deep learning, demonstrate superior adaptability and detection rates, while traditional 2D and 3D methods provide valuable baseline techniques. By reviewing and evaluating existing vision-based methods, this paper clarifies the current landscape of pothole detection technologies and identifies opportunities for future research and development. Additionally, insights provided by this review can inform the design and implementation of more robust and effective systems for automated road surface condition assessment, thereby contributing to enhanced roadway safety and infrastructure management. [ABSTRACT FROM AUTHOR]

In maritime transportation, a ship's draft survey serves as a primary method for weighing bulk cargo. The accuracy of the ship's draft reading determines the fairness of bulk cargo transactions. Human visual-based draft reading methods face issues such as safety concerns, high labor costs, and subjective interpretation. Therefore, some image processing methods are utilized to achieve automatic draft reading. However, due to the limitations in the spectral characteristics of RGB images, existing image processing methods are susceptible to water surface environmental interference, such as reflections. To solve this issue, we obtained and annotated 524 multispectral images of a ship's draft as the research dataset, marking the first application of integrating NIR information and RGB images for automatic draft reading tasks. Additionally, a dual-branch backbone named BIF is proposed to extract and combine spectral information from RGB and NIR images. The backbone network can be combined with the existing segmentation head and detection head to perform waterline segmentation and draft detection. By replacing the original ResNet-50 backbone of YOLOv8, we reached a mAP of 99.2% in the draft detection task. Similarly, combining UPerNet with our dual-branch backbone, the mIoU of the waterline segmentation task was improved from 98.9% to 99.3%. The inaccuracy of the draft reading is less than ±0.01 m, confirming the efficacy of our method for automatic draft reading tasks. [ABSTRACT FROM AUTHOR]

Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. Most existing re-identification methods rely on either hand-crafted local features or end-to-end learning of fur pattern similarity. The former does not need labeled training data, while the latter, although very data-hungry typically outperforms the former when enough training data is available. We propose a novel re-identification pipeline that combines the strengths of both approaches by utilizing modern learnable local features and feature aggregation. This creates representative pattern feature embeddings that provide high re-identification accuracy while allowing us to apply the method to small datasets by using pre-trained feature descriptors. We report a comprehensive comparison of different modern local features and demonstrate the advantages of the proposed pipeline on two very different species. [ABSTRACT FROM AUTHOR]

Public health initiatives must be made using evidence-based decision-making to have the greatest impact. Machine learning algorithms are created to gather, store, process, and analyze data to provide knowledge and guide decisions. A crucial part of any surveillance system is image analysis. The communities of computer vision and machine learning have become curious about it as of late. This study uses a variety of machine learning, and image processing approaches to detect and forecast malarial illness. In our research, we discovered the potential of deep learning techniques as innovative tools with a broader applicability for malaria detection, which benefits physicians by assisting in the diagnosis of the condition. We investigate the common confinements of deep learning for computer frameworks and organizing, including the requirement for data preparation, preparation overhead, real-time execution, and explaining ability, and uncover future inquiries about bearings focusing on these constraints. [ABSTRACT FROM AUTHOR]

Foundation models (FMs) have rapidly evolved and have achieved significant accomplishments in computer vision tasks. Specifically, the prompt mechanism conveniently allows users to integrate image prior information into the model, making it possible to apply models without any training. Therefore, we proposed a workflow based on foundation models and zero training to solve the tasks of photoacoustic (PA) image processing. We employed the Segment Anything Model (SAM) by setting simple prompts and integrating the model’s outputs with prior knowledge of the imaged objects to accomplish various tasks, including: (1) removing the skin signal in three-dimensional PA image rendering; (2) dual speed-of-sound reconstruction, and (3) segmentation of finger blood vessels. Through these demonstrations, we have concluded that FMs can be directly applied in PA imaging without the requirement for network design and training. This potentially allows for a hands-on, convenient approach to achieving efficient and accurate segmentation of PA images. This paper serves as a comprehensive tutorial, facilitating the mastery of the technique through the provision of code and sample datasets. [ABSTRACT FROM AUTHOR]

The salient object detection task tries to simulate the human visual system for most eye‐catching objects or regions detection. However, due to the complexity of the visual mechanisms, current methods will suffer from severe performance degradation, leading to inconsistent prediction results for the same regions, when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. Considering that consistency in predictions is essential for salient object detection, a cross‐scale resolution consistent salient object detection method, called RCNet, is proposed. Specifically, to enhance the model's capacity for generalization across images of varying resolutions and make the model implicitly learn the scale invariance, a multi‐resolution data enhancement module is constructed to generate images with arbitrary resolutions for the same scene. Moreover, to accomplish better multi‐level feature fusion, a cross‐scale fusion module is developed to fuse high‐level semantic features and low‐level detail features. Additionally, to explicitly learn the scale invariance of the salient scores, a hybrid salient consistency loss is formulated on salient object detection with different resolutions. Comprehensive evaluations on five benchmark datasets show that RCNet achieves a highly competitive result. [ABSTRACT FROM AUTHOR]

Image steganography is the art of concealing secret information within images to prevent detection. In deep‐learning‐based image steganography, a common practice is to fuse the secret image with the cover image to directly generate the stego image. However, not all features are equally critical for data hiding, and some insignificant ones may lead to the appearance of residual artifacts in the stego image. In this article, a novel network architecture for image steganography with hybrid attention mechanism based on generative adversarial network is introduced. This model consists of three subnetworks: a generator for generate stego images, an extractor for extracting the secret images, and a discriminator to simulate the detection process, which aids the generator in producing more realistic stego images. A specific hybrid attention mechanism (HAM) module is designed that effectively fuses information across channel and spatial domains, facilitating adaptive feature refinement within deep image representations. The experimental results suggest that the HAM module not only enhances the image quality during both the steganography and extraction processes but also improves the model's undetectability. Stego images are mixed with varying levels of noise in the training process, which can further improve robustness. Finally, it is verified that the model outperforms current steganography approaches on three datasets and exhibits good undetectability. [ABSTRACT FROM AUTHOR]

Lip‐reading deciphers speech by observing lip movements without relying on audio data. The rapid advancements in deep learning have significantly improved lip‐reading for both English and Chinese; however, research on dialects such as Cantonese remains scarce. Consequently, most Chinese lip‐reading datasets focus on Mandarin, with only a few addressing Cantonese. To bridge this gap, a sentence‐level Cantonese lip‐reading dataset, designated as Cantonese lip‐reading sentences are introduced, comprising over 500 unique speakers and more than 30,000 samples. To ensure alignment with real‐world scenarios, no restrictions are imposed on factors such as gender, age, posture, lighting conditions, or speech rate. A comprehensive description of the pipeline employed is provided for collecting and constructing the dataset and introduce an innovative visual frontend, 3D‐visual attention net. This frontend combines the advantages of convolution and self‐attention mechanisms to extract fine‐grained lip region features. These features are subsequently input into the conformer backend for temporal sequence modelling, achieving comparable performance on Chinese Mandarin lip reading dataset, lip reading sentences 2, lip reading sentences 3, and Cantonese lip‐reading sentences datasets. Benchmark tests on Cantonese lip‐reading sentences demonstrate the challenges it poses, providing a novel research foundation for dialect lip‐reading and fostering the advancement of Cantonese lip‐reading tasks. [ABSTRACT FROM AUTHOR]

Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods. [ABSTRACT FROM AUTHOR]

Accurate detection of algae in microscopic image plays a crucial role in water quality monitoring. However, the existing object detection methods still face challenges in accurately detecting different categories of algae in microscopic image. In order to improve the accuracy, an improved YOLOv5s model is proposed for microalgae detection, by combining a Receptive Field Enhancement (RFE) module, the Wise‐IoU v3 dynamic non‐monotonic focal loss function, and a Dynamic head (Dyhead), which is termed receptive field enhancement wise‐IoU dyhead (RWD)‐you only look once (YOLO). Firstly, to detect microalgae of various scales, the Bottleneck in the C3 module of YOLOv5s is replaced with a more reasonable RFE module. Secondly, Wise‐IoU v3 is applied to enhance detection accuracy by assigning varying weights between high‐quality and low‐quality images. Finally, Dyhead is introduced to enhance the representation capacity of the detection head by integrating three attention mechanisms: scale awareness, spatial awareness, and task awareness. The proposed RWD‐YOLO model significantly enhances the accuracy of algae detection in microscopic image. Specifically, the experimental results on the microalgae dataset show that the RWD‐YOLO achieves an mAP@0.5 of 93.2% and an mAP@0.5:0.95 of 65.1%. Compared to the original YOLOv5s, mAP@0.5 and mAP@0.5:0.95 are improved by 3.7% and 5.7%, respectively. [ABSTRACT FROM AUTHOR]

Micro‐expressions are spontaneous and unconscious facial movements that reveal individuals' genuine inner emotions. They hold significant potential in various psychological testing fields. As the face is a 3D deformation object, the emergence of facial expression leads to spatial deformation of the face. However, existing databases primarily offer 2D video sequences, limiting descriptions of 3D spatial information related to micro‐expressions. Here, a new micro‐expression database is proposed, which contains 2D image sequences and corresponding 3D point cloud sequences. These samples were classified using both an objective method based on the facial action coding system and a non‐objective emotion classification method that considers video contents and participants' self‐reports. A variety of feature extraction techniques are applied to 2D data, including traditional algorithms and deep learning methods. Additionally, a novel local curvature‐based algorithm is developed to extract 3D spatio‐temporal deformation features from the 3D data. The authors evaluated the classification accuracies of these two features individually and their fusion results under leave‐one‐subject‐out (LOSO) and tenfold cross‐validation. The results demonstrate that fusing 3D features with 2D features results in improved recognition performance compared to using 2D features alone. [ABSTRACT FROM AUTHOR]

Synthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks. [ABSTRACT FROM AUTHOR]

Introduction: This research explores the application of generative artificial intelligence, specifically the novel ARISGAN framework, for generating highresolution synthetic satellite imagery in the challenging arctic environment. Realistic and high-resolution surface imagery in the Arctic is crucial for applications ranging from satellite retrieval systems to the wellbeing and safety of Inuit populations relying on detailed surface observations. Methods: The ARISGAN framework was designed by combining dense block, multireceptive field, and Pix2Pix architecture. This innovative combination aims to address the need for high-quality imagery and improve upon existing state-of-the-art models. Various tasks and metrics were employed to evaluate the performance of ARISGAN, with particular attention to land-based and sea icebased imagery. Results: The results demonstrate that the ARISGAN framework surpasses existing state-of-the-art models across diverse tasks and metrics. Specifically, land-based imagery super-resolution exhibits superior metrics compared to sea ice-based imagery when evaluated across multiple models. These findings confirm the ARISGAN framework's effectiveness in generating perceptually valid highresolution arctic surface imagery. Discussion: This study contributes to the advancement of Earth Observation in polar regions by introducing a framework that combines advanced image processing techniques with a well-designed architecture. The ARISGAN framework's ability to outperform existing models underscores its potential. Identified limitations include challenges in temporal synchronicity, multispectral image analysis, preprocessing, and quality metrics. The discussion also highlights potential avenues for future research, encouraging further refinement of the ARISGAN framework to enhance the quality and availability of high-resolution satellite imagery in the Arctic. [ABSTRACT FROM AUTHOR]

Railway transportation has been integrated into people's lives. According to the "Notice on the release of the General Technical Specification of High-speed Railway Power Supply Safety Testing (6C System) System" issued by the National Railway Administration of China in 2012, it is required to install pantograph and slide monitoring devices in high-speed railway stations, station throats and the inlet and exit lines of high-speed railway sections, and it is required to detect the damage of the slider with high precision. It can be seen that the good condition of the pantograph slider is very important for the normal operation of the railway system. As a part of providing power for high-speed rail and subway, the pantograph must be paid attention to in railway transportation to ensure its integrity. The wear of the pantograph is mainly due to the contact power supply between the slide block and the long wire during high-speed operation, which inevitably produces scratches, resulting in depressions on the upper surface of the pantograph slide block. During long-term use, because the depression is too deep, there is a risk of fracture. Therefore, it is necessary to monitor the slider regularly and replace the slider with serious wear. At present, most of the traditional methods use automation technology or simple computer vision technology for detection, which is inefficient. Therefore, this paper introduces computer vision and deep learning technology into pantograph slide wear detection. Specifically, this paper mainly studies the wear detection of the pantograph slider based on deep learning and the main purpose is to improve the detection accuracy and improve the effect of segmentation. From a methodological perspective, this paper employs a linear array camera to enhance the quality of the data sets. Additionally, it integrates an attention mechanism to improve segmentation performance. Furthermore, this study introduces a novel image stitching method to address issues related to incomplete images, thereby providing a comprehensive solution. [ABSTRACT FROM AUTHOR]

Cracks are a common defect in civil infrastructures, and their occurrence is often closely related to structural loading conditions, material properties, design and construction, and other factors. Therefore, detecting and analyzing cracks in civil infrastructures can effectively determine the extent of damage, which is crucial for safe operation. In this paper, Web of Science (WOS) and Google Scholar were used as literature search tools and "crack", "civil infrastructure", and "computer vision" were selected as search terms. With the keyword "computer vision", 325 relevant documents were found in the study period from 2020 to 2024. A total of 325 documents were searched again and matched with the keywords, and 120 documents were selected for analysis and research. Based on the main research methods of the 120 documents, we classify them into three crack detection methods: fusion of traditional methods and deep learning, multimodal data fusion, and semantic image understanding. We examine the application characteristics of each method in crack detection and discuss its advantages, challenges, and future development trends. [ABSTRACT FROM AUTHOR]

Occasionally intravenous insertion forms a challenge to a number of patients. Inserting an IV needle is a difficult task that requires a lot of skill. At the moment, only doctors and medical personnel are allowed to do this because it requires finding the right vein, inserting the needle properly, and carefully injecting fluids or drawing out blood. Even for trained professionals, this can be done incorrectly, which can cause bleeding, infection, or damage to the vein. It is especially difficult to do this on children, elderly people, and people with certain skin conditions. In these cases, the veins are harder to see, so it is less likely to be done correctly the first time and may cause blood clots. In this research, a low-cost embedded system utilizing Near-Infrared (NIR) light technology is developed, and two novel approaches are proposed to detect and select the best candidate veins. The two approaches utilize multiple computer vision tools and are based on contrast-limited adaptive histogram equalization (CLAHE). The accuracy of the proposed algorithm is 91.3% with an average 1.4 s processing time on Raspberry Pi 4 Model B. [ABSTRACT FROM AUTHOR]

Edge detection is an essential image processing act that is crucial for many computer vision applications such as object detection, image segmentation, face recognition, text recognition, medical imaging, and autonomous vehicles. Deep learning is the most advanced and widely used tool of them all. In this paper, we present a novel deep learning model and use image datasets to test it. Our model uses a fractional calculus tool, which could enhance gradient approaches' performances. Specifically, we approximate the fractional-order derivative-order neural network (GLFNet) using a Grünwald–Letnikov fractional definition. First, the original dataset is subjected to a Grünwald–Letnikov fractional order. After that, the CNN model is updated with the new dataset, concluding the standard CNN procedure. The training rate, the improvement in the F-measure for identifying the effective edge while maintaining the CNN model's memory consumption, and the values of the loss errors between the prediction and training processes were all tested using the MNIST dataset. Our experiments show that GLFNet considerably enhances edge detection. GLFNet outperformed CNN with an average loss error ratio of 15.40, suggesting fewer loss mistakes. The F1-measure ratio of 0.81 indicates that GLFNet can compete with CNN in terms of precision and recall. The training time for GLFNet was lowered by an average ratio of 1.14 when compared to CNN, while inference time was faster with a ratio of 1.14, indicating increased efficiency. These findings demonstrate the efficacy of introducing Grünwald–Letnikov fractional convolution into deep learning models, resulting in more precise and reliable edge detection while preserving comparable memory utilization. [ABSTRACT FROM AUTHOR]

In agriculture, crops are severely affected by illnesses, which reduce their production every year. The detection of plant diseases during their initial stages is critical and thus needs to be addressed. Researchers have been making significant progress in the development of automatic plant disease recognition techniques through the utilization of machine learning (ML), image processing, and deep learning (DL). This study analyses the recent advancements made by researchers in the field of ML techniques for identifying plant diseases. This study also examines various methods used by researchers to produce ML solutions, such as image preprocessing, segmentation, and feature extraction. This study highlights the challenges encountered while creating plant disease identification systems, such as small datasets, image capture conditions, and the generalizability of the models, and discusses possible solutions to cater to these problems. Still, the development of a solution that automatically detects various plant diseases for various plant species remains a big challenge. To address these challenges, there is a need to create a system that is trained on an extensive dataset that contains images of various types of diseases a plant can suffer from, and plant images should be taken at various stages of the disease's development. This study further presents an analysis of various methods used at different stages of plant disease identification. [ABSTRACT FROM AUTHOR]

In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional convolutional neural networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces and employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds. [ABSTRACT FROM AUTHOR]

Cervical cancer is a prevalent and concerning disease affecting women, with increasing incidence and mortality rates. Early detection plays a crucial role in improving outcomes. Recent advancements in computer vision, particularly the Swin transformer, have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). The Swin transformer adopts a hierarchical and efficient approach using shifted windows, enabling the capture of both local and global contextual information in images. In this paper, we propose a novel approach called Swin-GA-RF to enhance the classification performance of cervical cells in Pap smear images. Swin-GA-RF combines the strengths of the Swin transformer, genetic algorithm (GA) feature selection, and the replacement of the softmax layer with a random forest classifier. Our methodology involves extracting feature representations from the Swin transformer, utilizing GA to identify the optimal feature set, and employing random forest as the classification model. Additionally, data augmentation techniques are applied to augment the diversity and quantity of the SIPaKMeD1 cervical cancer image dataset. We compare the performance of the Swin-GA-RF Transformer with pre-trained CNN models using two classes and five classes of cervical cancer classification, employing both Adam and SGD optimizers. The experimental results demonstrate that Swin-GA-RF outperforms other Swin transformers and pre-trained CNN models. When utilizing the Adam optimizer, Swin-GA-RF achieves the highest performance in both binary and five-class classification tasks. Specifically, for binary classification, it achieves an accuracy, precision, recall, and F1-score of 99.012, 99.015, 99.012, and 99.011, respectively. In the five-class classification, it achieves an accuracy, precision, recall, and F1-score of 98.808, 98.812, 98.808, and 98.808, respectively. These results underscore the effectiveness of the Swin-GA-RF approach in cervical cancer classification, demonstrating its potential as a valuable tool for early diagnosis and screening programs. [ABSTRACT FROM AUTHOR]

This study aims to enhance the detection accuracy and efficiency of cotton bolls in complex natural environments. Addressing the limitations of traditional methods, we developed an automated detection system based on computer vision, designed to optimize performance under variable lighting and weather conditions. We introduced COTTON-YOLO, an improved model based on YOLOv8n, incorporating specific algorithmic optimizations and data augmentation techniques. Key innovations include the C2F-CBAM module to boost feature recognition capabilities, the Gold-YOLO neck structure for enhanced information flow and feature integration, and the WIoU loss function to improve bounding box precision. These advancements significantly enhance the model's environmental adaptability and detection precision. Comparative experiments with the baseline YOLOv8 model demonstrated substantial performance improvements with COTTON-YOLO, particularly a 10.3% increase in the AP50 metric, validating its superiority in accuracy. Additionally, COTTON-YOLO showed efficient real-time processing capabilities and a low false detection rate in field tests. The model's performance in static and dynamic counting scenarios was assessed, showing high accuracy in static cotton boll counting and effective tracking of cotton bolls in video sequences using the ByteTrack algorithm, maintaining low false detections and ID switch rates even in complex backgrounds. [ABSTRACT FROM AUTHOR]

This paper presents an innovative AI-based method for autonomous inspection, designed to enhance energy production efficiency by optimizing cleaning strategies for soiled photovoltaic panels, using advanced artificial intelligence algorithms to analyze panel conditions and environmental factors in real-time, allowing for targeted cleaning interventions. Based on the advanced YOLOv8 deep learning algorithm and computer vision approach, the proposed method offers distinct advantages in real-time detection and classification of various types of soiling and dust accumulation compared on solar panels to traditional methods, and underwent satisfactory testing across diverse scenarios. The NVIDIA Jetson Nano, the Raspberry Pi4 embedded devices, and the Raspberry Pi4 combined with NCS2 accelerator are used for implementing our approach. A comparison aims to provide a detailed exploration of the most suitable embedded platform for deploying our advanced system was discussed. This comparison considers processing speed and accuracy, energy consumption, and overall performance in executing the computationally intensive tasks. The results demonstrate that our model achieves high accuracy in detecting soiling and enhancing the model's detection speed. With an average precision of 99.5%, this approach ensures accurate fault identification, underscoring the effectiveness of computer vision using deep learning algorithms for detection tasks across a wide range of scenarios. [ABSTRACT FROM AUTHOR]

Most natural disasters result from geodynamic events such as landslides and slope collapse. These failures cause catastrophes that directly impact the environment and cause financial and human losses. Visual inspection is the primary method for detecting failures in geotechnical structures, but on-site visits can be risky due to unstable soil. In addition, the body design and hostile and remote installation conditions make monitoring these structures inviable. When a fast and secure evaluation is required, analysis by computational methods becomes feasible. In this study, a convolutional neural network (CNN) approach to computer vision is applied to identify defects in the surface of geotechnical structures aided by unmanned aerial vehicle (UAV) and mobile devices, aiming to reduce the reliance on human-led on-site inspections. However, studies in computer vision algorithms still need to be explored in this field due to particularities of geotechnical engineering, such as limited public datasets and redundant images. Thus, this study obtained images of surface failure indicators from slopes near a Brazilian national road, assisted by UAV and mobile devices. We then proposed a custom CNN and low complexity model architecture to build a binary classifier image-aided to detect faults in geotechnical surfaces. The model achieved a satisfactory average accuracy rate of 94.26%. An AUC metric score of 0.99 from the receiver operator characteristic (ROC) curve and matrix confusion with a testing dataset show satisfactory results. The results suggest that the capability of the model to distinguish between the classes 'damage' and 'intact' is excellent. It enables the identification of failure indicators. Early failure indicator detection on the surface of slopes can facilitate proper maintenance and alarms and prevent disasters, as the integrity of the soil directly affects the structures built around and above it. [ABSTRACT FROM AUTHOR]

Abstract In order to improve the accuracy of granular image detection during image scaling, an image scaling algorithm combining the interpolation algorithm of protective features and Kalman filtering of neurons is proposed. Firstly, the interpolation algorithm of protective features is de‐designed according to the phenomenon of sudden change of edge grey values, and the difference and trend of grey values in horizontal and vertical directions are used to obtain the pre‐scaled image with maximum contrast. Then the grey value data input of the pre‐scaled image is introduced into the Kalman filter of neurons, and the filtering process is optimized by using the black‐box thinking of neurons, and the pre‐scaled image is smoothed. Finally, the scale transformation is implemented to obtain the final grey value to complete the final scaling, so that the image has both visual experience and features. Comparison with mainstream image scaling algorithms shows that the proposed algorithm can effectively overcome the degradation of granularity image detection accuracy due to image scaling, with point acutance value (PAV) improved by 10%–41%, and the granularity detection error caused by image scaling algorithms reduced from about 0.7% to about 0.1%, with a relative improvement of 85%.

Abstract Head pose estimation is an especially challenging task due to the complexity nonlinear mapping from 2D feature space to 3D pose space. To address the above issue, this paper presents a novel and efficient head pose estimation framework based on particle swarm optimized contrastive learning and multimodal entangled graph convolution network. Firstly, a new network, the region and difference‐aware feature pyramid network (RD‐FPN), is proposed for 2D keypoints detection to alleviate the background interference and enhance the feature expressiveness. Then, particle swarm optimized contrastive learning is constructed to alternatively match 2D and 3D keypoints, which takes the multimodal keypoints matching accuracy as the optimization objective, while considering the similarity of cross‐modal positive and negative sample pairs from contrastive learning as a local contrastive constraint. Finally, multimodal entangled graph convolution network is designed to enhance the ability of establishing geometric relationships between keypoints and head pose angles based on second‐order bilinear attention, in which point‐edge attention is introduced to improve the representation of geometric features between multimodal keypoints. Compared with other methods, the average error of our method is reduced by 8.23%, indicating the accuracy, generalization, and efficiency of our method on the 300W‐LP, AFLW2000, BIWI datasets.

Abstract Transformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors’ ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors’ proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost.

Abstract Image steganography is the art of concealing secret information within images to prevent detection. In deep‐learning‐based image steganography, a common practice is to fuse the secret image with the cover image to directly generate the stego image. However, not all features are equally critical for data hiding, and some insignificant ones may lead to the appearance of residual artifacts in the stego image. In this article, a novel network architecture for image steganography with hybrid attention mechanism based on generative adversarial network is introduced. This model consists of three subnetworks: a generator for generate stego images, an extractor for extracting the secret images, and a discriminator to simulate the detection process, which aids the generator in producing more realistic stego images. A specific hybrid attention mechanism (HAM) module is designed that effectively fuses information across channel and spatial domains, facilitating adaptive feature refinement within deep image representations. The experimental results suggest that the HAM module not only enhances the image quality during both the steganography and extraction processes but also improves the model's undetectability. Stego images are mixed with varying levels of noise in the training process, which can further improve robustness. Finally, it is verified that the model outperforms current steganography approaches on three datasets and exhibits good undetectability.

Abstract Accurate detection of algae in microscopic image plays a crucial role in water quality monitoring. However, the existing object detection methods still face challenges in accurately detecting different categories of algae in microscopic image. In order to improve the accuracy, an improved YOLOv5s model is proposed for microalgae detection, by combining a Receptive Field Enhancement (RFE) module, the Wise‐IoU v3 dynamic non‐monotonic focal loss function, and a Dynamic head (Dyhead), which is termed receptive field enhancement wise‐IoU dyhead (RWD)‐you only look once (YOLO). Firstly, to detect microalgae of various scales, the Bottleneck in the C3 module of YOLOv5s is replaced with a more reasonable RFE module. Secondly, Wise‐IoU v3 is applied to enhance detection accuracy by assigning varying weights between high‐quality and low‐quality images. Finally, Dyhead is introduced to enhance the representation capacity of the detection head by integrating three attention mechanisms: scale awareness, spatial awareness, and task awareness. The proposed RWD‐YOLO model significantly enhances the accuracy of algae detection in microscopic image. Specifically, the experimental results on the microalgae dataset show that the RWD‐YOLO achieves an mAP@0.5 of 93.2% and an mAP@0.5:0.95 of 65.1%. Compared to the original YOLOv5s, mAP@0.5 and mAP@0.5:0.95 are improved by 3.7% and 5.7%, respectively.

Abstract Lip‐reading deciphers speech by observing lip movements without relying on audio data. The rapid advancements in deep learning have significantly improved lip‐reading for both English and Chinese; however, research on dialects such as Cantonese remains scarce. Consequently, most Chinese lip‐reading datasets focus on Mandarin, with only a few addressing Cantonese. To bridge this gap, a sentence‐level Cantonese lip‐reading dataset, designated as Cantonese lip‐reading sentences are introduced, comprising over 500 unique speakers and more than 30,000 samples. To ensure alignment with real‐world scenarios, no restrictions are imposed on factors such as gender, age, posture, lighting conditions, or speech rate. A comprehensive description of the pipeline employed is provided for collecting and constructing the dataset and introduce an innovative visual frontend, 3D‐visual attention net. This frontend combines the advantages of convolution and self‐attention mechanisms to extract fine‐grained lip region features. These features are subsequently input into the conformer backend for temporal sequence modelling, achieving comparable performance on Chinese Mandarin lip reading dataset, lip reading sentences 2, lip reading sentences 3, and Cantonese lip‐reading sentences datasets. Benchmark tests on Cantonese lip‐reading sentences demonstrate the challenges it poses, providing a novel research foundation for dialect lip‐reading and fostering the advancement of Cantonese lip‐reading tasks.

Abstract Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods.

Abstract The salient object detection task tries to simulate the human visual system for most eye‐catching objects or regions detection. However, due to the complexity of the visual mechanisms, current methods will suffer from severe performance degradation, leading to inconsistent prediction results for the same regions, when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. Considering that consistency in predictions is essential for salient object detection, a cross‐scale resolution consistent salient object detection method, called RCNet, is proposed. Specifically, to enhance the model's capacity for generalization across images of varying resolutions and make the model implicitly learn the scale invariance, a multi‐resolution data enhancement module is constructed to generate images with arbitrary resolutions for the same scene. Moreover, to accomplish better multi‐level feature fusion, a cross‐scale fusion module is developed to fuse high‐level semantic features and low‐level detail features. Additionally, to explicitly learn the scale invariance of the salient scores, a hybrid salient consistency loss is formulated on salient object detection with different resolutions. Comprehensive evaluations on five benchmark datasets show that RCNet achieves a highly competitive result.

Abstract Micro‐expressions are spontaneous and unconscious facial movements that reveal individuals’ genuine inner emotions. They hold significant potential in various psychological testing fields. As the face is a 3D deformation object, the emergence of facial expression leads to spatial deformation of the face. However, existing databases primarily offer 2D video sequences, limiting descriptions of 3D spatial information related to micro‐expressions. Here, a new micro‐expression database is proposed, which contains 2D image sequences and corresponding 3D point cloud sequences. These samples were classified using both an objective method based on the facial action coding system and a non‐objective emotion classification method that considers video contents and participants’ self‐reports. A variety of feature extraction techniques are applied to 2D data, including traditional algorithms and deep learning methods. Additionally, a novel local curvature‐based algorithm is developed to extract 3D spatio‐temporal deformation features from the 3D data. The authors evaluated the classification accuracies of these two features individually and their fusion results under leave‐one‐subject‐out (LOSO) and tenfold cross‐validation. The results demonstrate that fusing 3D features with 2D features results in improved recognition performance compared to using 2D features alone.

Abstract Synthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks.

In response to the recent formalization of Filipino Sign Language (FSL) and the lack of comprehensive studies, this paper introduces a real-time FSL gesture recognition system. Unlike existing systems, which are often limited to static signs and asynchronous recognition, it offers dynamic gesture capturing and recognition of 10 common expressions and five transactional inquiries. To this end, the system sequentially employs cropping, contrast adjustment, grayscale conversion, resizing, and normalization of input image streams. These steps serve to extract the region of interest, reduce the computational load, ensure uniform input size, and maintain consistent pixel value distribution. Subsequently, a Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) model was employed to recognize nuances of real-time FSL gestures. The results demonstrate the superiority of the proposed technique over existing FSL recognition systems, achieving an impressive average accuracy, recall, and precision rate of 98%, marking an 11.3% improvement in accuracy. Furthermore, this article also explores lightweight conversion methods, including post-quantization and quantization-aware training, to facilitate the deployment of the model on resource-constrained platforms. The lightweight models show a significant reduction in model size and memory utilization with respect to the base model when executed in a Raspberry Pi minicomputer. Lastly, the lightweight model trained with the quantization-aware technique (99%) outperforms the post-quantization approach (97%), showing a notable 2% improvement in accuracy.

Abstract Current research on apron conflict detection is often limited to the interaction between the aircraft as a whole and other objects, making it difficult to accomplish targeted identification of vulnerable and high‐cost aircraft components. However, the implementation of detailed aircraft identification is of great significance to enhance the safety of airport surface operations. Based on the excellent performance of High‐Resolution Network (HRNet) in keypoint detection, a lightweight end‐to‐end keypoint detection network, namely Squeeze and Excitation High‐Resolution Network (SEHRNet), is proposed in this paper to solve the problems of HRNet's slower computation and more redundancy. First, the errors arising from coordinate transformations in the coding and decoding process are solved by an improved feature map coding and decoding process. Second, replace the BasicBlock in HRNet with the Depthwise separable convolutions based on the Squeeze‐and‐Excitation Networks, which drastically cuts the computational cost of the network. Third, the improved Bottleneck module is used to further enhance the capability of feature extraction. Experimental results prove that, based on the aircraft keypoint detection dataset, the SEHRNet proposed in this paper shows stronger applicability compared to the current mainstream networks. Compared with the original HRNet, the improved network has higher accuracy, faster speed, and lighter model for aircraft keypoint detection.

Abstract Accurate detection of underwater objects is a key indicator technology to effectively enhance the field of marine development and application, and is of great importance to various fields including marine military defense and seafood aquaculture. Efficient and rapid detection of underwater targets is a crucial technological challenge in this field. To meet the challenges posed by these issues, this study applies the convolutional omni‐efficient layer aggregation network (CO‐ELAN) module to the detector backbone to improve the ability of the network structure to acquire underwater objects from image information. The module improves the feature representation of gradient branching through a multi‐dimensional dynamic convolution and attention mechanism. In terms of loss calculation, the optimized normalized Wasserstein distance approach is used to predict the box distribution probabilistic modelling method to determine comparable distances to the ground box and obtain better samples of small target labels. Here, an underwater image enhancement algorithm based on white balance and underwater blur fusion is used to obtain clear images that enable improved detector performance. After the verification experiment on the URPC2018 dataset, it is found that the detector has better underwater detection ability compared with other detectors in the complex underwater environment. The proposed method achieves a 2.4% improvement over the YOLOv7 baseline model, while reducing computation costs by 5%.

Abstract The discrepancy in data distribution between training and testing scenarios, as well as the inductive bias of convolutional neural networks towards image styles, reduces the model's generalization ability. Many unsupervised domain generalization methods based on feature decoupling suffer from an initial neglect of explicit decoupling of content and style features, resulting in content features that still contain considerable redundant information, thereby restricting improvements in generalization capability. To tackle this problem, this paper optimizes the learning process of domain‐invariant (content) features into an information compression issue, minimizing redundancy in content features. Furthermore, to enhance decoupled learning, this paper introduces innovative cross‐domain loss functions and image reconstruction modules that explicitly decouple and merge content and style across different domains. Extensive experiments demonstrate the method's significant enhancements over recent cutting‐edge approaches.

Abstract 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 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 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.