Explore the vast range of titles available.

The detection of infrared vehicle targets by UAVs poses significant challenges in the presence of complex ground backgrounds, high target density, and a large proportion of small targets, which result in high false alarm rates. To alleviate these deficiencies, a novel YOLOv7-based, multi-scale target detection method for infrared vehicle targets is proposed, which is termed YOLO-ViT. Firstly, within the YOLOV7-based framework, the lightweight MobileViT network is incorporated as the feature extraction backbone network to fully extract the local and global features of the object and reduce the complexity of the model. Secondly, an innovative C3-PANet neural network structure is delicately designed, which adopts the CARAFE upsampling method to utilize the semantic information in the feature map and improve the model’s recognition accuracy of the target region. In conjunction with the C3 structure, the receptive field will be increased to enhance the network’s accuracy in recognizing small targets and model generalization ability. Finally, the K-means++ clustering method is utilized to optimize the anchor box size, leading to the design of anchor boxes better suited for detecting small infrared targets from UAVs, thereby improving detection efficiency. The present article showcases experimental findings attained through the use of the HIT-UAV public dataset. The results demonstrate that the enhanced YOLO-ViT approach, in comparison to the original method, achieves a reduction in the number of parameters by 49.9% and floating-point operations by 67.9%. Furthermore, the mean average precision (mAP) exhibits an improvement of 0.9% over the existing algorithm, reaching a value of 94.5%, which validates the effectiveness of the method for UAV infrared vehicle target detection.

Extracting water-bodies accurately is a great challenge from very high resolution (VHR) remote sensing imagery. The boundaries of a water body are commonly hard to identify due to the complex spectral mixtures caused by aquatic vegetation, distinct lake/river colors, silts near the bank, shadows from the surrounding tall plants, and so on. The diversity and semantic information of features need to be increased for a better extraction of water-bodies from VHR remote sensing images. In this paper, we address these problems by designing a novel multi-feature extraction and combination module. This module consists of three feature extraction sub-modules based on spatial and channel correlations in feature maps at each scale, which extract the complete target information from the local space, larger space, and between-channel relationship to achieve a rich feature representation. Simultaneously, to better predict the fine contours of water-bodies, we adopt a multi-scale prediction fusion module. Besides, to solve the semantic inconsistency of feature fusion between the encoding stage and the decoding stage, we apply an encoder-decoder semantic feature fusion module to promote fusion effects. We carry out extensive experiments in VHR aerial and satellite imagery respectively. The result shows that our method achieves state-of-the-art segmentation performance, surpassing the classic and recent methods. Moreover, our proposed method is robust in challenging water-body extraction scenarios.

Rapid advancements in autonomous driving technology have highlighted the challenges of ensuring vehicle safety and driving efficiency in complex dynamic traffic environments. Current approaches typically define potential risks as safety constraints for compliance and use them in trajectory planning. However, the risks predefined in these constraints are often fixed, reducing driving efficiency. To address this limitation, we proposed a dynamic risk-information-driven adaptive trajectory planning method for autonomous vehicles (AVs). This study dynamically adjusted safety constraints using risk assessment results to improve driving efficiency without compromising safety. Firstly, considering the influence of vehicle suspension characteristics on driving safety, collision, and instability risk assessment indices were designed using a three-way-coupled dynamic model to assess driving safety risks. Next, we used the safety risk assessment module to evaluate specific potential risks and adaptively adjusted the safety constraints for constraint-based adaptive trajectory planning. Furthermore, considering trajectory traversal constraints, trajectory selection and optimization were performed on pre-planned trajectories using the cost function to determine the optimal driving trajectory. Lane-changing trajectory planning experiments showed that the method adaptively adjusts safety constraints based on risk assessment results. Under the premise of ensuring driving safety, driving efficiency improved by 55.9% in the preset instability constraint scenario and 27.86% in the preset collision constraint scenario.

In autonomous driving, detecting small and occluded objects remains a substantial challenge due to the complexity of real-world environments. To address this, we propose RSO-YOLO, an enhanced model based on YOLOv12. First, the bidirectional feature pyramid network (BiFPN) and space-to-depth convolution (SPD-Conv) replace the original neck network. This design efficiently integrates multi-scale features while preserving fine-grained information during downsampling, thereby improving both computational efficiency and detection performance. Additionally, a detection head for the shallower feature layer P2 is incorporated, further boosting the model’s capability to detect small objects. Second, we propose the feature enhancement and compensation module (FECM), which strengthens features in visible regions and compensates for missing semantic information in occluded areas. This module improves detection accuracy and robustness under occlusion. Finally, we propose a lightweight global cross-dimensional coordinate detection head (GCCHead), built upon the global cross-dimensional coordinate module (GCCM). By grouping and synergistically enhancing features, this module addresses the challenge of balancing computational efficiency with detection performance. Experimental results demonstrate that on the SODA10M, BDD100K, and FLIR ADAS datasets, RSO-YOLO achieves mAP@0.5 improvements of 8.0%, 10.7%, and 7.2%, respectively, compared to YOLOv12. Meanwhile, the number of parameters is reduced by 15.4%, and model complexity decreases by 20%. In summary, RSO-YOLO attains higher detection accuracy while reducing parameters and computational complexity, highlighting its strong potential for practical autonomous driving applications.

Supercapacitors with the advantages of high power density and fast discharging rate have full applications in energy storage. However, the low energy density restricts their development. Conventional methods for improving energy density are mainly confined to doping atoms and hybridizing with other active materials. Herein, a Co3O4/g‐C3N4 p–n junction with excellent capacity is developed and its application in an all‐solid‐state flexible device is demonstrated, whose capacity and energy density are considerably enhanced by simulated solar light irradiation. Under photoirradiation, the capacity is increased by 70.6% at the maximum current density of 26.6 mA cm−2 and a power density of 16.0 kW kg−1. The energy density is enhanced from 7.5 to 12.9 Wh kg−1 with photoirradiation. The maximum energy density reaches 16.4 Wh kg−1 at a power density of 6.4 kW kg−1. It is uncovered that the lattice distortion of Co3O4, reduces defects of g‐C3N4, and the facilitated photo‐generated charge separation by the Co3O4/g‐C3N4 p–n junction all make contributions to the promoted electrochemical storage performance. This work may provide a new strategy to enhance the energy density of supercapacitors and expand the application range of photocatalytic materials. Photoirradiation‐enhanced capacity behavior of Co3O4/g‐C3N4 p–n junction type all‐solid‐state supercapacitors is reported. The enhanced capacity and energy density under simulated solar light irradiation are ascribed to the built‐in electric field that facilitates the separation of photo‐generated charges. The structural distortion of Co3O4 under photoirradiation also accounts for the promoted electrochemical storage performance.

Exploring the components of soil organic carbon (SOC) and aggregate stability across different elevations is crucial to assessing the stability of SOC in subtropical forest ecosystems under climate change. In this study, we investigated the spatial variation of active carbon (C) compositions, aggregate distribution, and stability in Chinese fir ( Cunninghamia lanceolata ) plantations across an elevation gradient from 750 to 1150 m a.s.l. on the northern foothills of the Dabie Mountains, China. The results showed that macroaggregates accounted for more than 80% of all fractions at different elevations. In the 0–10 cm soil layer, the macroaggregates, mean weight diameter (MWD), geometric mean diameter (GMD), and SOC exhibited a U-shaped distribution trend with increasing elevation. Conversely, in the 10–50 cm soil layer, these indicators showed a consistent increasing trend. Similarly, the contents of easily oxidizable carbon (EOC) and particulate organic carbon (POC) gradually increased with increasing elevation. Microbial biomass carbon (MBC) and silt + clay C exhibited a unimodal distribution pattern along the elevational gradient, peaking at 850 m a.s.l., which is mainly related to soil pH and C/N ratio. Across all elevations, The silt + clay C was significantly higher than that of macro- and micro-aggregate C. Macro- and micro-aggregate C, and dissolved organic carbon (DOC) were significantly positively correlated with MWD. The results demonstrated that elevation and soil layer have significant effects on SOC and aggregate stability. The physical protection of silt + clay fractions and the active carbon pools may be the main mechanisms for organic carbon preservation in the Dabie Mountains. These results contribute to further deepening the impact of elevation on climate change and the C cycling of forest ecosystems.

Multistep-ahead prediction of critical states in the iron ore sintering process is essential for maintaining production stability, enhancing energy efficiency, and reducing industrial emissions. However, large time delays, strong coupling, and condition drifts challenge existing spatiotemporal graph neural networks (STGNNs). This paper proposes Process-aware Mixed Dynamic Graph Network (ProMix-DGNet), which integrates a Decoupled Two-Stream Topology Learning mechanism—fusing Adaptive Static Graph with a Radial Basis Function (RBF)-driven Dynamic Graph Constructor—to ensure robust spatial modeling under high-noise conditions. Furthermore, Process-View Global Mixer explicitly captures long-range process coupling across the entire sintering strand, overcoming the receptive field limitations of traditional graph convolutions. In the decoding phase, a future control-informed module utilizes a bidirectional Long Short-Term Memory (BiLSTM) and a global mixer to align known future control setpoints with the system’s spatial topology. These features are integrated via a gated residual mechanism that dynamically modulates the interaction between control intents and historical representations. Extensive experiments conducted on two real-world industrial datasets, Sinter-A and Sinter-B, demonstrate that ProMix-DGNet consistently outperforms mainstream baselines across multiple metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results verify the model’s higher accuracy and robustness in complex large-time-delay systems, offering a reliable framework for the intelligent monitoring and closed-loop optimization of sintering process.

To explore the correlation between community-acquired pressure injury (CAPI) and comorbidities in elderly patients with emergency admission. Patients aged 65 years or above were enrolled from multiple departments, such as Internal Medicine, Surgery, Geriatrics, and Intensive Care Unit of Wuhan Third Hospital, which is affiliated to Wuhan University, from January to December 2020. Comorbidity data were extracted using the 10th edition of the International Classification of Diseases (ICD-10) from the hospital electronic medical record system, and the Charlson Comorbidity Index (CCI) was calculated using these data. Participants were divided into two groups according to whether pressure injury was present at admission. The baseline characteristics of the two groups were compared using Student's -tests, Mann-Whitney -tests, and chi-square tests. Univariate and multivariate logistic regression models were constructed to explore the relationship between CAPI and the CCI. Smooth curve fitting was used to show the relationship between the CCI and CAPI. By drawing the receiver operating characteristic curve, the CCI was used to predict CAPI. A total of 5759 participants with an average age of 75.1 ± 7.6 were included in this population-based study. The prevalence of CAPI was 4.3%. In logistic regression analysis, there was a positive relationship between the CCI and CAPI after adjustment for sex, age, hypoproteinemia, and anemia (OR = 1.37, 95% CI = 1.29-1.45, < 0.001, trend test < 0.001). The area under the receiver operating characteristic curve was 0.75, and the maximum value of the Youden index was 0.35, with a critical value of 5.5. The development of CAPI was positively correlated with the CCI. The risk of developing pressure injury increases with the number and severity of comorbidities. This study shows that the CCI has certain reference value in predicting CAPI.

A UAV infrared target detection model ITD-YOLOv8 based on YOLOv8 is proposed to address the issues of model missed and false detections caused by complex ground background and uneven target scale in UAV aerial infrared image target detection, as well as high computational complexity. Firstly, an improved YOLOv8 backbone feature extraction network is designed based on the lightweight network GhostHGNetV2. It can effectively capture target feature information at different scales, improving target detection accuracy in complex environments while remaining lightweight. Secondly, the VoVGSCSP improves model perceptual abilities by referencing global contextual information and multiscale features to enhance neck structure. At the same time, a lightweight convolutional operation called AXConv is introduced to replace the regular convolutional module. Replacing traditional fixed-size convolution kernels with convolution kernels of different sizes effectively reduces the complexity of the model. Then, to further optimize the model and reduce missed and false detections during object detection, the CoordAtt attention mechanism is introduced in the neck of the model to weight the channel dimensions of the feature map, allowing the network to pay more attention to the important feature information, thereby improving the accuracy and robustness of object detection. Finally, the implementation of XIoU as a loss function for boundary boxes enhances the precision of target localization. The experimental findings demonstrate that ITD-YOLOv8, in comparison to YOLOv8n, effectively reduces the rate of missed and false detections for detecting multi-scale small targets in complex backgrounds. Additionally, it achieves a 41.9% reduction in model parameters and a 25.9% decrease in floating-point operations. Moreover, the mean accuracy (mAP) attains an impressive 93.5%, thereby confirming the model’s applicability for infrared target detection on unmanned aerial vehicles (UAVs).

The ablation perforation damage of double-sided coated narrow-band filters based on RG-850 colored glass under out-of-band laser irradiation is investigated. A temperature-triggered nonlinear absorption mechanism is identified where substrate absorption sharply increases beyond a critical temperature. To quantify the resulting energy deposition dynamics, the multiple reflection model is employed, revealing the absorption enhancement by partial-transmission/high-reflection coatings. Building on this foundation, a parameter inversion method derives the equivalent average absorption coefficient from dual-transmittance laser-induced damage threshold (LIDT) ratios, thereby establishing a LIDT predictive framework for arbitrary transmittance. Finally, finite element analyses (FEA) provide validation for the multiple reflection model and inversion method, demonstrating the coating structure’s role in absorption enhancement and successfully predicting damage thresholds across three transmittance configurations.