Detection Performance Research Articles

Hyperbranched Thermosensitive Polymer-AuNP Composite Probe for Temperature Colorimetric Detection.

Temperature detection is particularly important in the medical and scientific fields. Although there are various temperature detection methods, most of them focus on broad temperature detection, and basic research in specific fields, especially the detection of subtle temperature changes (32-34 °C) during wound infection, is still insufficient. For this purpose, a novel colorimetric temperature sensing probe is designed in this paper, which can quickly and intuitively respond to small temperature changes within a specific range through color changes. In this paper, hyperbranched polyethyleneimine (HPEI) was modified by isobutyrylation to prepare hyperbranched temperature-sensitive polymer (HPEI-IBAm). And it was combined with gold nanoparticles (AuNPs) prepared by a sodium citrate reduction method to construct an HPEI-IBAm-AuNP colorimetric probe. The probe exhibits excellent stability, even at salt concentrations of up to 12 g/L, thanks to the abundant amino functional groups and the large steric hindrance effect unique to HPEI-IBAm. In particular, the temperature detection range of the probe is precisely locked within 32-34 °C, enabling it to respond quickly and accurately to small temperature changes of only 2 °C. This feature is perfectly suited to the practical needs of temperature detection in infected wounds. The linear fitting coefficient of the temperature response is as high as 0.9929, ensuring the accuracy of the test results. The detection performance of the probe remained highly consistent over 10 cycles, fully proving its excellent reusability and durability. In addition, a flexible colorimetric sensor was prepared by combining the probe with polydimethylsiloxane (PDMS) film. This sensor is capable of rapidly detecting human skin temperature in real time, achieving an accuracy of 99.07% to 100.61%. It can provide a possible solution to the challenges of delayed and difficult temperature detection caused by different body parts and uneven surfaces, among others. This demonstrates its extensive practical value and potential, and it is expected to be further applied in the monitoring of wound infections.

Facile Preparation and Study of Self-Healing Water-Absorbing Expanding Elastomers.

The absorbent expansion elastomer plays a crucial role in engineering sealing and holds a promising future in this field as infrastructure continues to develop. Traditional materials have their limitations, especially when used in large construction projects where the integrity and reliability of the material are of utmost importance. In this work, a self-healing water-absorbing expansion elastomer was developed for continuous production at a large scale to monitor the sealing conditions of massive infrastructure projects. At room temperature, the material exhibited a repairing efficiency of 57.77 % within 2 h, which increased to 84.02 % after 12 h. This extended reaction time allowed for effective repairs when defects were detected. The material's strength can attain 3 MPa, placing it at the upper echelon among common self-healing materials, thereby granting it a certain level of durability in its application environment. The material's volume expansion rate reached 200-400 % to achieve effective sealing, and the functional filling of the filler endowed the material itself with a favorable external force induction effect and prevented heat accumulation. The conductive detection performance of the absorbent expansion elastomer was improved by utilizing triple self-healing strategies, including dipole-dipole interaction, ion cross-linked network, and externally-aided restoration materials. These strategies were combined with a double packing strategy to enhance the material's properties. This innovative elastomer can be applied in various fields such as tunnel construction, infrastructure development, aerospace sealing, and railway transportation, showcasing significant potential for diverse engineering applications.

IG‐YOLOv8: Insulator Guardian Based on YOLO for Insulator Fault Detection

AbstractInsulators have an extremely important role in transmission lines, and they are important components for ensuring the safe operation of transmission lines. In order to solve the difficult problem of insulator fault detection under complex background, IG‐YOLOv8 insulator fault detection algorithm is proposed in this paper. First, the Wise‐IoU (WIoU) loss function is introduced to mitigate the adverse impact of low‐quality images by employing a dynamic non‐monotonic focusing mechanism, thereby enhancing the detection performance of the entire model. Second, a novel C2f network is constructed by integrating the receptive field coordination attention (RFCA) convolutional module to address the parameter‐sharing issue associated with large convolutional kernels. Additionally, the data set has been reorganized using k‐fold cross‐validation to ensure that each subset undergoes training and testing, consequently reducing generalization errors. Finally, a deformable attention (DA) mechanism is employed to augment the feature extraction capability pertaining to insulator fault region information. In order to evaluate the detection performance of the improved IG‐YOLOv8 algorithm, this study constructed an insulator target detection data set containing four fault types: Normal, Defect, Dirty, and Aging. The experimental results show that the average accuracy of the improved model is increased from 89.7% to 96.9%, and the Recall value of the Aging type insulator is increased from 71.8% to 89.1%. The occurrence of missed detection is greatly reduced, and the accuracy of detection is improved. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Study of conveyor belt deviation detection based on improved YOLOv8 algorithm

Conveyor belt deviation is a commmon and severe type of fault in belt conveyor systems, often resulting in significant economic losses and potential environment pollution. Traditional detection methods have obvious limitations in fault localization precision and analysis accuracy, unable to meet the demands of efficient and real-time fault detection in complex industrial scenarios. To address these issues, this paper proposes an improved detection algorithm based on YOLOv8, aiming to achieve efficient and accurate detection during the operation of the belt. Firstly, an Enhanced Squeeze-and-Excitation (ESE) module is incorporated into C2f to boost feature extraction for rollers and belts. Secondly, the construction of the BiFPN_DoubleAttention module in the neck network enhances bidirectional feature fusion and attention mechanism, thereby improving multi-scale object localization accuracy under complex environments. Then, a Multi-Head Self-Attention (MHSA) mechanism is introduced in the head network, better capturing positional features of small roller targets and belt areas in various environments, thus enhancing detection performance. Finally, extensive experiments are conducted on a self-built dataset, achieving an accuracy of 98.1%, mAP0.5 of 99.0%, and a detection speed of 46 frames per second (FPS). This method effectively handles variations and disturbances in the conveyor belt transportation environment, meeting real-time diagnostic needs for belt misalignment in the industry.

An Improved UNet-Based Path Recognition Method in Low-Light Environments

The fruit industry is a significant economic sector in China, with modern orchards gradually transitioning to trellis orchards. For mechanized orchard operations, automatic vehicle navigation is essential. However, in trellis orchards, the shading from trees results in low average light intensity and large variations in lighting, posing challenges for path navigation. To address this, a path navigation algorithm for trellis orchards is proposed based on the UNet-CBAM model. The network structures of UNet, FCN, and SegNet are compared to identify and select the optimal structure for further improvement. Among the three attention mechanisms of channel attention, spatial attention, and combined attention, the most effective mechanism is identified. The optimal attention mechanism is incorporated into the optimized network to enhance the model’s ability to detect path edges and improve detection performance. To validate the effectiveness and generalizability of the model, a total of 400 images were collected under varying lighting intensities. The experimental results show that this method achieves an accuracy of 97.63%, a recall of 93.94%, and an Intersection over Union (IoU) of 92.19%. These results significantly enhance path recognition accuracy in trellis orchards, particularly under low light under conditions. Compared to the FCN and SegNet algorithms, this method provides higher detection accuracy and offers a new theoretical foundation and research approach for path recognition in low-light environments.

Large-Kernel Central Block Masked Convolution and Channel Attention-Based Reconstruction Network for Anomaly Detection of High-Resolution Hyperspectral Imagery

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

An automated pheochromocytoma and paraganglioma lesion segmentation AI-model at whole-body 68Ga- DOTATATE PET/CT.

Somatostatin receptor (SSR) targeting radiotracer 68Ga-DOTATATE is used for Positron Emission Tomography (PET)/Computed Tomography (CT) imaging to assess patients with Pheochromocytoma and paraganglioma (PPGL), rare types of Neuroendocrine tumor (NET) which can metastasize thereby becoming difficult to quantify. The goal of this study is to develop an artificial intelligence (AI) model for automated lesion segmentation on whole-body 3D DOTATATE-PET/CT and to automate the tumor burden calculation. 132 68Ga-DOTATATE PET/CT scans from 38 patients with metastatic and inoperable PPGL, were split into 70, and 62 scans, from 20, and 18 patients for training, and test sets, respectively. The training set was further divided into patient-stratified 5 folds for cross-validation. 3D-full resolution nnUNet configuration was trained with 5-fold cross-validation. The model's detection performance was evaluated at both scan and lesion levels for the PPGL test set and two other clinical cohorts with NET (n = 9) and olfactory neuroblastoma (ONB, n = 5). Additionally, quantitative statistical analysis of PET parameters including SUVmax, total lesion uptake (TLU), and total tumor volume (TTV), was conducted. The nnUNet AI model achieved an average 5-fold validation dice similarity coefficient of 0.84 at the scan level. The model achieved dice similarity coefficients (DSC) of 0.88, 0.6, and 0.67 at the scan level, the sensitivity of 86%, 61.13%, and 61.64%, and a positive predictive value of 89%, 74%, and 86.54% at the lesion level for the PPGL test, NET and ONB cohorts, respectively. For PPGL cohorts, smaller lesions with low uptake were missed by the AI model (p < 0.001). Anatomical region-based failure analysis showed most of the false negative and false positive lesions within the liver for all the cohorts, mainly due to the high physiologic liver background activity and image noise on 68Ga- DOTATATE PET scans. The developed deep learning-based AI model showed reliable performance for automated segmentation of metastatic PPGL lesions on whole-body 68Ga-DOTATATE-PET/CT images, which may be beneficial for tumor burden estimation for objective evaluation during therapy follow-up. https://www. gov/study/NCT03206060 , https://www. gov/study/NCT04086485 , https://www. gov/study/NCT05012098 .

YOLOX-S-TKECB: A Holstein Cow Identification Detection Algorithm

Accurate identification of individual cow identity is a prerequisite for the construction of digital farms and serves as the basis for optimized feeding, disease prevention and control, breed improvement, and product quality traceability. Currently, cow identification faces challenges such as poor recognition accuracy, large data volumes, weak model generalization ability, and low recognition speed. Therefore, this paper proposes a cow identification method based on YOLOX-S-TKECB. (1) Based on the characteristics of Holstein cows and their breeding practices, we constructed a real-time acquisition and preprocessing platform for two-dimensional Holstein cow images and built a cow identification model based on YOLOX-S-TKECB. (2) Transfer learning was introduced to improve the convergence speed and generalization ability of the cow identification model. (3) The CBAM attention mechanism module was added to enhance the model’s ability to extract features from cow torso patterns. (4) The alignment between the apriori frame and the target size was improved by optimizing the clustering algorithm and the multi-scale feature fusion method, thereby enhancing the performance of object detection at different scales. The experimental results demonstrate that, compared to the traditional YOLOX-S model, the improved model exhibits a 15.31% increase in mean average precision (mAP) and a 32-frame boost in frames per second (FPS). This validates the feasibility and effectiveness of the proposed YOLOX-S-TKECB-based cow identification algorithm, providing valuable technical support for the application of dairy cow identification in farms.

Structural Health Monitoring and Failure Analysis of Large-Scale Hydro-Steel Structures, Based on Multi-Sensor Information Fusion

Large-scale hydro-steel structures (LS-HSSs) are vital to hydraulic engineering, supporting critical functions such as water resource management, flood control, power generation, and navigation. However, due to prolonged exposure to severe environmental conditions and complex operational loads, these structures progressively degrade, posing increased risks over time. The absence of effective structural health monitoring (SHM) systems exacerbates these risks, as undetected damage and wear can compromise safety. This paper presents an advanced SHM framework designed to enhance the real-time monitoring and safety evaluation of LS-HSSs. The framework integrates the finite element method (FEM), multi-sensor data fusion, and Internet of Things (IoT) technologies into a closed-loop system for real-time perception, analysis, decision-making, and optimization. The system was deployed and validated at the Luhun Reservoir spillway, where it demonstrated stable and reliable performance for real-time anomaly detection and decision-making. Monitoring results over time were consistent, with stress values remaining below allowable thresholds and meeting safety standards. Specifically, stress monitoring during radial gate operations (with a current water level of 1.4 m) indicated that the dynamic stress values induced by flow vibrations at various points increased by approximately 2 MPa, with no significant impact loads. Moreover, the vibration amplitude during gate operation was below 0.03 mm, confirming the absence of critical structural damage and deformation. These results underscore the SHM system’s capacity to enhance operational safety and maintenance efficiency, highlighting its potential for broader application across water conservancy infrastructure.

Fault Detection Strategy of Partial Least Squares Based on Temporal Neighborhood Difference

ABSTRACTAiming at the difficulty of detecting time‐lag faults in dynamic processes, a fault detection strategy based on time neighborhood difference (TND) is proposed, and it is introduced into the partial least squares (PLS) method to suggest the PLS‐TND fault detection method. The TND method takes the mean to the multibatch training set to obtain a baseline training set, and it constructs the mean squared Euclidean distance (MSED) statistic by calculating the average distance between the sample's first k‐moments neighborhood samples and samples at the same moment in the baseline training set. The TND method can help the PLS method to effectively detect time‐lag faults and significantly improve the fault detection capability of PLS by measuring the overall positional difference between the temporal neighborhood sample set of the sample and its temporal neighborhood sample set in the baseline training set. The PLS‐TND method is compared with some classical fault detection methods through a numerical simulation process and a Continuous Stirred Tank Reactor (CSTR) system design fault detection experiment. The PLS‐TND method gives the best performance of fault detection.

Luminescent iron phthalocyanine organic polymer nanosheets with space-separated dual-active sites for the detection and photocatalytic reduction of Cr(Ⅵ) from wastewater

Cr(Ⅵ) residues in livestock and poultry wastewater are a rising concern for human health and biotic environments. For the removal of Cr(Ⅵ), its simultaneous reduction and adsorption represents a sustainable and efficient strategy. Herein, iron nodes on covalently bonded two-dimensional phthalocyanine organic polymer (PcOP-Fe) nanosheets with space-separated dual-active sites are developed for the simultaneous detection and removal of Cr(VI) from wastewater. In the FeN4 structure of PcOP-Fe nanosheets, Fe acts as an electron capture center, effectively facilitating the accumulation of photogenerated electrons and transferring them to Cr(VI), thereby achieving its photocatalytic reduction. Meanwhile, pyrrolic nitrogen provides excellent adsorption sites, enabling the adsorption of Cr(III) or Cr(0). Fe accumulates the photogenerated electrons from pyrrole N and transfer them to Cr(Ⅵ). The formation of N-Cr(Ⅲ) bonds causes a space-separation between Cr(Ⅵ) and Cr(III). In addition, PcOP-Fe can be used for a Cr(Ⅵ) detection agent. The photoluminescence intensity decreases linearly with increasing Cr(Ⅵ) concentration from 80 μM to 2 mM, with a limit of detection of 0.18 μM. The PcOP-Fe nanosheets exhibit good Cr(Ⅵ) detection and reduction performance in livestock and poultry wastewater, suggesting their suitability for practical sensing applications. Thus, the PcOP-Fe nanosheets with space-separated dual-active sites are promising for the simultaneous detection and removal of Cr(Ⅵ) in water treatment processes.

Web Traffic Anomaly Detection Using Isolation Forest

As companies increasingly undergo digital transformation, the value of their data assets also rises, making them even more attractive targets for hackers. The large volume of weblogs warrants the use of advanced classification methodologies in order for cybersecurity specialists to identify web traffic anomalies. This study aims to implement Isolation Forest, an unsupervised machine learning methodology in the identification of anomalous and non-anomalous web traffic. The publicly available weblogs dataset from an e-commerce website underwent data preparation through a systematic pipeline of processes involving data ingestion, data type conversion, data cleaning, and normalization. This led to the addition of derived columns in the training set and manually labeled testing set that was then used to compare the anomaly detection performance of the Isolation Forest model with that of cybersecurity experts. The developed Isolation Forest model was implemented using the Python Scikit-learn library, and exhibited a superior Accuracy of 93%, Precision of 95%, Recall of 90% and F1-Score of 92%. By appropriate data preparation, model development, model implementation, and model evaluation, this study shows that Isolation Forest can be a viable solution for close to accurate web traffic anomaly detection.

Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection

Credit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive rates and fail to generalize well to emerging fraud patterns. In this paper, we propose a novel approach that integrates a Mixture of Experts (MoE) model with a Deep Neural Network-based Synthetic Minority Over-sampling Technique (DNN-SMOTE) to enhance fraud detection performance. The MoE modeleverages multiple specialized expert networks, each trained to detect specific types of fraud, while the DNN-SMOTE generates high-quality synthetic samples to address the class imbalance. Our experimental results on a publicly available dataset demonstrate that the proposed method achieves a classification accuracy of 99.93%, a true positive rate of 84.69%, and a true negative rate of 99.95%. The Matthews Correlation Coefficient (MCC) of 0.7883 further highlights the model’s balanced performance in detecting fraudulent transactions. These results underscore the effectiveness of combining MoE with DNN-SMOTE, offering a robust solution for real-world credit card fraud detection scenarios.

An Enhanced Shuffle Attention with Context Decoupling Head with Wise IoU Loss for SAR Ship Detection

Synthetic Aperture Radar (SAR) imagery is widely utilized in military and civilian applications. Recent deep learning advancements have led to improved ship detection algorithms, enhancing accuracy and speed over traditional Constant False-Alarm Rate (CFAR) methods. However, challenges remain with complex backgrounds and multi-scale ship targets amidst significant interference. This paper introduces a novel method that features a context-based decoupled head, leveraging positioning and semantic information, and incorporates shuffle attention to enhance feature map interpretation. Additionally, we propose a new loss function with a dynamic non-monotonic focus mechanism to tackle these issues. Experimental results on the HRSID and SAR-Ship-Dataset demonstrate that our approach significantly improves detection performance over the original YOLOv5 algorithm and other existing methods.

Quantitative evaluation of corrugation severity by using instrumented wheelset

Accurate evaluation of corrugation severity is essential for timely rail maintenance to prevent potential hazards. This paper aims at the excitation characteristics of corrugation and presents a study on the evaluation method using wheel-rail vertical force (WRVF). First, a 3D wheel-rail dynamic model is established by the parameters of service vehicles and track in China’s high-speed railway, corrugated rail was finely modelled with the consideration of out-of-roundness and random track short irregularity. The model was validated with measured data come from instrumented wheelset in time and frequency domain, the stability and dynamic response of the model are studied numerically to explore the excitation characteristics of corrugation. Then, the variation of WRVF with depth and wavelength respectively was discussed, the mapping relationship between the 95th percentile maximum of the WRVF and the corrugation wavelength is revealed, the influences of the natural frequency and contact behavior of the wheel-rail system on the mapping relationship were analyzed. Finally, the corrugation severity index (Csi) is introduced to quantify the degree of rail damage. The applicability of Csi was tested on 65 sets of corrugated sections on high-speed railway, and the results of field measurement showed that the hit rate of Csi in evaluating the severity of corrugation is 93.8%, indicating that the proposed method has a good performance in actual detection. Thus, Csi can provide a scientific reference for the quantitative evaluation of corrugation severity and decision-making for rail grinding in high-speed railway.

Early detection of age-related macular degeneration using Vision Transformer-based Architectures – A comparative study with offline metrics and data augmenting

Age-related macular degeneration (AMD) is one of the leading causes of vision loss in elderly adults around the world and is among the main visual impairments in Mexico. The difficulty of diagnosing AMD in its early stages motivates the use of advanced deep-learning methods that offer significant potential to improve diagnostic accuracy in retinal image analysis. In recent years, Transformer architectures for computer vision, such as Vision Transformer (ViT), Swin Transformer and BERT Pre-training of Image Transformers (BEiT) have provided a novel perspective for image analysis. This study presents a comparative analysis of these architectures, applied to AMD detection, focusing on each model's capability to classify the early stages of the disease. Although the small size of medical image datasets represented a challenge, our results suggest that ViT-based architectures and their derivatives achieve significant performance in AMD detection. BEiT is particularly notable for its consistently superior performance.

Construction of two isomorphic multifunctional MOFs via a dual-ligand strategy for aromatic compounds detection and photocatalytic degradation performance

The development of multifunctional and structurally unique metal−organic frameworks (MOFs) presents a highly attractive yet challenging endeavor for chemists. In this study, we employ a dual-ligand strategy to synthesize two isomorphic Co/Zn MOFs, {[Co4(BMIP)3(MIP)4]·3DMF·H2O}n (SNUT-35-Co) and {[Zn4(BMIP)3(MIP)4]·2DMF·2H2O}n (SNUT-35-Zn). The photocatalytic performance of SNUT-35-Co and SNUT-35-Zn was evaluated using methylene blue (MB). Under UV/visible-light irradiation, the photocatalytic decolorization rates of MB for SNUT-35-Co and SNUT-35-Zn reached 95 % within 140 min and 120 min, respectively, indicating their superior degradation. Notably, SNUT-35-Zn demonstrated exceptional detection capabilities for aromatic compounds, such as aniline and nitrobenzene, at lower concentration range without interference from other components. The detection limits for these two small molecules were found to be 0.430 and 0.431 μM, respectively. Additionally, both MOFs exhibited large transient photocurrent and low impedance in electrochemical measurement. The results suggested that the photocatalytic activities of MOFs are influenced by their three-dimensional structures, which facilitate electrons passing due to the inherent semiconductor properties.

Piezoelectric-enhanced ultrasensitive ZnO/Ag microcavity SERS substrate for dopamine detection

In the complex human body fluids, neurotransmitters such as dopamine (DA) play a significant role in regulating physiological functions, thereby impacting the normal functioning of biological activities. Hence, employing a rapid and non-destructive analytical technique for precise measurement of these molecules is crucial. Here, a novel piezoelectric-enhanced ZnO/Ag microcavity SERS substrate was designed, enabling ultra-sensitive and instantaneous detection of DA molecules. This substrate achieves exceptional trace detection performance, with a detection limit for Rhodamine 6 G (R6G) molecules as low as 5×10−13 M and a EF of 1.05×1011, DA can be accurately identified even at exceedingly low concentrations, demonstrating outstanding capabilities in trace detection. This innovative structure not only represents a breakthrough in the rapid trace detection of neurotransmitters but also introduces new avenues for research and diagnostics in fields such as precision medicine, neuroscience, and pharmaceutical development.

WCAY object detection of fractures for X-ray images of multiple sites

The WCAY (weighted channel attention YOLO) model, which is meticulously crafted to identify fracture features across diverse X-ray image sites, is presented herein. This model integrates novel core operators and an innovative attention mechanism to enhance its efficacy. Initially, leveraging the benefits of dynamic snake convolution (DSConv), which is adept at capturing elongated tubular structural features, we introduce the DSC-C2f module to augment the model’s fracture detection performance by replacing a portion of C2f. Subsequently, we integrate the newly proposed weighted channel attention (WCA) mechanism into the architecture to bolster feature fusion and improve fracture detection across various sites. Comparative experiments were conducted, to evaluate the performances of several attention mechanisms. These enhancement strategies were validated through experimentation on public X-ray image datasets (FracAtlas and GRAZPEDWRI-DX). Multiple experimental comparisons substantiated the model’s efficacy, demonstrating its superior accuracy and real-time detection capabilities. According to the experimental findings, on the FracAtlas dataset, our WCAY model exhibits a notable 8.8% improvement in mean average precision (mAP) over the original model. On the GRAZPEDWRI-DX dataset, the mAP reaches 64.4%, with a detection accuracy of 93.9% for the “fracture” category alone. The proposed model represents a substantial improvement over the original algorithm compared to other state-of-the-art object detection models. The code is publicly available at https://github.com/cccp421/Fracture-Detection-WCAY .

Wavelet structure-texture-aware super-resolution for pedestrian detection

This study aims to tackle the challenge of detecting pedestrians in low-resolution (LR) images by using super-resolution techniques. The proposed Wavelet Structure-Texture-Aware Super-Resolution (WSTa-SR) method is a novel end-to-end solution that enlarges LR images into high-resolution ones and employs Yolov7 for detection, effectively solving the problems of low detection performance. The LR image is first decomposed into low and high-frequency sub-images with stationary wavelet transform (SWT), which are then processed by different sub-networks to more accurately distinguish pedestrian from background by emphasizing pedestrian features. Additionally, a high-to-low information delivery mechanism (H2LID mechanism) is proposed to transfer the information of high-frequency details to enhance the reconstruction of low-frequency structures. A novel loss function is also introduced that exploits wavelet decomposition properties to further enhance the network’s performance on both image structure reconstruction and pedestrian detection. Experimental results show that the proposed WSTa-SR method can effectively improve pedestrian detection.