Search Results (32)

Advanced Driver Assistance Systems (ADAS) are increasingly shaping urban mobility and road safety, yet their benefits depend not only on technical performance, but also on driver acceptance. This study examines how Hungarian drivers perceive and evaluate key ADAS functions, Adaptive Cruise Control (ACC), Lane Keeping/Centering Assist (LKA/LCA), and Forward Cross Traffic Alert (FCTA), in urban driving contexts. The research is based on qualitative focus group discussions conducted in Győr, Hungary, involving drivers aged 20–50 from different age cohorts. Data were analyzed using thematic analysis. The findings show that the acceptance of ADAS is strongly context-dependent and function specific. ACC was perceived primarily as a comfort-enhancing tool, especially on longer or more monotonous routes, while LCA was often regarded intrusive and less reliable in urban conditions due to poor road markings, potholes, and frequent stop-and-go situations. On the contrary, blind spot and cross-traffic-related functions were evaluated more positively due to their direct safety benefits. Trust, perceived risk, and control emerged as key dimensions of acceptance, with many participants emphasising the importance of warning-based support rather than a strong autonomous intervention. In general, the study concludes that urban acceptance of ADAS is shaped by the interaction of infrastructure conditions, perceived usefulness, and driver trust, highlighting the need for more transparent, context sensitive, and user-centered system design in support of safer urban mobility. Full article

Background/Objectives: Vertebral body stenting (VBS) and balloon kyphoplasty (BKP) are widely used for the treatment of osteoporotic vertebral fractures (OVFs). However, it remains unclear whether the theoretical biomechanical advantages of VBS translate to superior clinical or radiographic outcomes. This study aimed to compare VBS and BKP with respect to clinical outcomes, radiographic parameters, and complications. Methods: In this multicenter retrospective comparative cohort study, 123 patients with OVF treated with VBS (n = 24) or BKP (n = 99) were analyzed. VBS was indicated for complex fracture patterns, including severe endplate injury, split-type fractures, and absence of interbody sclerosis; other fractures were treated with BKP. Pain outcomes, operative parameters, cement volume and leakage, and radiographic measures of vertebral kyphosis angle (VKA) and local kyphosis angle (LKA) were assessed. For group comparisons, we used independent-samples t tests or Mann–Whitney U tests for continuous variables and chi-squared or Fisher’s exact tests for categorical variables. Results: Baseline demographics and bone mineral density were comparable between groups. Surgical time was longer for VBS (39 ± 6 vs. 35 ± 9 min, p = 0.007). Both procedures produced significant pain reductions (p < 0.001), and postoperative VAS did not differ between VBS and BKP (18 ± 11 vs. 13 ± 12 mm, p = 0.06). Although VKA immediately after surgery was lower for VBS (4.8 ± 4.4° vs. 7.0 ± 4.9°, p = 0.03), the magnitude of correction, VKA, and LKA at final follow-up were comparable. Cement volume was similar (6.4 ± 1.4 vs. 6.7 ± 1.9 mL, p = 0.45), but cement leakage occurred more frequently with VBS (54% vs. 24%, p = 0.005). Rates of adjacent vertebral fracture (13% vs. 26%, p = 0.12) and revision surgery (4% vs. 8%, p = 0.44) were comparable between groups. Conclusions: Despite VBS being reserved for more complex fracture morphologies with split-type fractures and severe endplate defects, while BKP was generally used for uncomplicated OVF cases, VBS provided pain relief and radiographic correction comparable to BKP. Full article

To address the problem of insufficient detection accuracy, high false negative rate of small targets, and large positioning errors of ships in complex marine environments and foggy conditions, an improved DBL-YOLO method based on YOLOv11 is proposed. This method customizes and optimizes modules according to the characteristics of foggy scenes—the C3k2-MDSC module is designed to efficiently extract and fuse multi-scale spatial features, and a dynamic weight allocation mechanism is adopted to balance the contributions of features at different scales in the foggy and blurred environment; a lightweight BiFPN structure is introduced to enhance the efficiency of cross-scale feature transmission and solve the problem of feature attenuation in foggy conditions; a novel fusion of the Deformable-LKA attention mechanism is innovated, which combines a large receptive field and spatial adaptive adjustment capabilities to focus on the key contour features of blurred ships in foggy conditions; an Inner-SIoU regression loss function is proposed, which optimizes the positioning accuracy of dense and small targets through an auxiliary bounding box dynamic scaling strategy. Experimental results show that in foggy scenes, the recall rate is increased by 3.4%, the F1 score is increased by 1%, and mAP@0.5 and mAP@0.5:0.95 are increased by 1.4% and 3.1%, respectively. The final average precision reaches 98.6%, demonstrating excellent detection accuracy and robustness. Full article

Precise identification of weeds at the maize seedling stage is pivotal for implementing Site-Specific Weed Management and minimizing herbicide environmental pollution. However, the performance of existing lightweight detectors is severely bottlenecked by unstructured field environments, characterized by the “green-on-green” spectral similarity between crops and weeds, diminutive seedling targets, and complex mutual occlusion of leaves. To address these challenges, this study proposes SLD-YOLO11, a topology-reconstructed lightweight detection model tailored for complex field environments. First, to mitigate the feature loss of tiny targets, a Lossless Downsampling Topology based on Space-to-Depth Convolution (SPD-Conv) is constructed, transforming spatial information into depth channels to preserve fine-grained features. Second, a Decomposed Large Kernel Attention (D-LKA) mechanism is designed to mimic the wide receptive field of human vision. By modeling long-range spatial dependencies with decomposed large-kernel attention, it enhances discrimination under severe occlusion by leveraging global structural context. Third, the DySample operator is introduced to replace static interpolation, enabling content-aware feature flow reconstruction. Experimental results demonstrate that SLD-YOLO11 achieves an mAP@0.5 of 97.4% on a self-collected maize field dataset, significantly outperforming YOLOv8n, YOLOv10n, YOLOv11n, and mainstream lightweight variants. Notably, the model achieves Zero Inter-class Misclassification between maize and weeds, establishing high safety standards for weeding operations. To further bridge the gap between visual perception and precision operations, a Visual Weed-Crop Competition Index (VWCI) is innovatively proposed. By integrating detection bounding boxes with species-specific morphological correction coefficients, the VWCI quantifies field weed pressure with low cost and high throughput. Regression analysis reveals a high consistency (R² = 0.70) between the automated VWCI and manual ground-truth coverage. This study not only provides a robust detector but also offers a reliable decision-making basis for real-time variable-rate spraying by intelligent weeding robots. Full article

This research focuses on vehicle Advanced Driver Assistance Systems (ADAS), with particular emphasis on Lane Keeping Assist (LKA) systems which is designed to help drivers keep a vehicle centered within its lane and reduce the risk of unintentional lane departures. These kinds of systems detect lane boundaries using computer vision algorithms applied to video data captured by a forward-facing camera and interpret this visual information to provide corrective steering inputs or driver alerts. The research investigates the performance, reliability, sustainability, and limitations of LKA systems under adverse road and environmental conditions, such as wet pavement and in the presence of degraded, partially visible, or missing horizontal road markings. Improving the reliability of lane detection and keeping systems enhances road safety, reducing traffic accidents caused by lane departures, which directly supports social sustainability. For the theoretical test, a modified road model using MATLAB software was used to simulate poor road markings and to investigate possible test outcomes. A series of field tests were conducted on multiple passenger vehicles equipped with LKA technologies to evaluate their response in real-world scenarios. The results show that it is very important to ensure high quality horizontal road markings as specified in UNECE Regulation No. 130, as lane keeping aids are not uniformly effective. Furthermore, the study highlights the need to develop more robust line detection algorithms capable of adapting to diverse road and weather conditions, thereby enhancing overall driving safety and system reliability. LKA system research supports sustainable mobility strategies promoted by international organizations—aiming to transition to safer, smarter, and less polluting transportation systems. Full article

The highly heterogeneous and irregular morphology of liver tumors presents considerable challenges for automated segmentation. To better capture complex tumor structures, this study proposes a liver tumor segmentation framework based on multi-scale deformable feature fusion and global context modeling. The method incorporates three key innovations: (1) a Deformable Large Kernel Attention (D-LKA) mechanism in the encoder to enhance adaptability to irregular tumor features, combining a large receptive field with deformable sensitivity to precisely extract tumor boundaries; (2) a Context Extraction (CE) module in the bottleneck layer to strengthen global semantic modeling and compensate for limited capacity in capturing contextual dependencies; and (3) a Dual Cross Attention (DCA) mechanism to replace traditional skip connections, enabling deep cross-scale and cross-semantic feature fusion, thereby improving feature consistency and expressiveness during decoding. The proposed framework was trained and validated on a combined LiTS and MSD Task08 dataset and further evaluated on the independent 3D-IRCADb01 dataset. Experimental results show that it surpasses several state-of-the-art segmentation models in Intersection over Union (IoU) and other metrics, achieving superior segmentation accuracy and generalization performance. Feature visualizations at both encoding and decoding stages provide intuitive insights into the model’s internal processing of tumor recognition and boundary delineation, enhancing interpretability and clinical reliability. Overall, this approach presents a novel and practical solution for robust liver tumor segmentation, demonstrating strong potential for clinical application and real-world deployment. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

With the development of electrification and intelligent technologies in vehicles, ride comfort issues represented by motion sickness have become a key constraint on the performance of autonomous driving. The occurrence of motion sickness is influenced by the comprehensive movement of the vehicle in the longitudinal, lateral, and vertical directions, involving ACC, LKA, active suspension, etc. Existing motion sickness control method focuses on optimizing the longitudinal, lateral, and vertical directions separately, or coordinating the optimization control of the longitudinal and lateral directions, while there is relatively little research on the coupling effect and coupled optimization of the longitudinal and vertical directions. This study proposes a coupled framework of ACC and active suspension control system based on MPC. By adding pitch angle changes caused by longitudinal acceleration to the suspension model, a coupled state equation of half-car vertical dynamics and ACC longitudinal dynamics is constructed to achieve integrated optimization of ACC and suspension for motion suppression. The suspension active forces and vehicle acceleration are regulated coordinately to optimize vehicle vertical, longitudinal, and pitch dynamics simultaneously. Simulation experiments show that compared to decoupled control of ACC and suspension, the integrated control framework can be more effective. The research results confirm that the dynamic coordination between the suspension and ACC system can effectively suppress the motion sickness, providing a new idea for solving the comfort conflict in the human vehicle environment coupling system. Full article

Object detection in complex road scenes is vital for autonomous driving, facing challenges such as object occlusion, small target sizes, and irregularly shaped targets. To address these issues, this paper introduces DGSS-YOLOv8s, a model designed to enhance detection accuracy and high-FPS performance within the You Only Look Once version 8 small (YOLOv8s) framework. The key innovation lies in the synergistic integration of several architectural enhancements: the DCNv3_LKA_C2f module, leveraging Deformable Convolution v3 (DCNv3) and Large Kernel Attention (LKA) for better the capture of complex object shapes; an Optimized Feature Pyramid Network structure (Optimized-GFPN) for improved multi-scale feature fusion; the Detect_SA module, incorporating spatial Self-Attention (SA) at the detection head for broader context awareness; and an Inner-Shape Intersection over Union (IoU) loss function to improve bounding box regression accuracy. These components collectively target the aforementioned challenges in road environments. Evaluations on the Berkeley DeepDrive 100K (BDD100K) and Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets demonstrate the model’s effectiveness. Compared to baseline YOLOv8s, DGSS-YOLOv8s achieves mean Average Precision (mAP)@50 improvements of 2.4% (BDD100K) and 4.6% (KITTI). Significant gains were observed for challenging categories, notably 87.3% mAP@50 for cyclists on KITTI, and small object detection (AP-small) improved by up to 9.7% on KITTI. Crucially, DGSS-YOLOv8s achieved high processing speeds suitable for autonomous driving, operating at 103.1 FPS (BDD100K) and 102.5 FPS (KITTI) on an NVIDIA GeForce RTX 4090 GPU. These results highlight that DGSS-YOLOv8s effectively balances enhanced detection accuracy for complex scenarios with high processing speed, demonstrating its potential for demanding autonomous driving applications. Full article

Aiming at the problems of inaccurate segmentation and low detection efficiency caused by irregular tumor shape and large size differences in brain MRI images, this study proposes a brain tumor segmentation algorithm, YOLO-BT, based on YOLOv11. YOLO-BT uses UNetV2 as the backbone network to enhance the feature extraction ability of key regions through the attention mechanism. The BiFPN structure is introduced into the neck network to replace the traditional feature splicing method, realize the two-way fusion of cross-scale features, improve detection accuracy, and reduce the amount of calculations required. The D-LKA mechanism is introduced into the C3k2 structure, and the large convolution kernel is used to process complex image information to enhance the model’s ability to characterize different scales and irregular tumors. In this study, multiple sets of experiments were performed on the Figshare Brain Tumor dataset to test the performance of YOLO-BT. The data results show that YOLO-BT improves Precision by 2.7%, Recall, mAP50 by 0.9%, and mAP50-95 by 0.3% in the candidate box-based evaluation compared to YOLOv11. In mask-based evaluations, Precision improved by 2.5%, Recall by 2.8%, mAP50 by 1.1%, and mAP50-95 by 0.5%. At the same time, the mIOU increased by 6.1%, and the Dice coefficient increased by 3.6%. It can be seen that the YOLO-BT algorithm is suitable for brain tumor detection and segmentation. Full article

Background: This study aims to evaluate how surgical timing and the radiological characteristics of fragment blocks can affect the effectiveness of ligamentotaxis, in restoring the spinal canal area, and local kyphosis in adults with traumatic thoracolumbar A3 burst fractures without neurological impairment treated with percutaneous short-segment fixation. Methods: A retrospective observational study was conducted between January 2016 and December 2022 on neurologically intact adult patients with a single A3 thoracolumbar fracture. Data collected included demographics, injury mechanism, fracture level, and clinical and surgical details. Radiological assessments included spinal canal area, local kyphotic angle, anterior and posterior vertebral heights, and fragment block measurements. Results: Out of 101 treated patients, 9 met the criteria with a mean age of 52.22 years. Most fractures were at L1 (88.89%). All patients had moderate-to-severe pain (NRS 6.22 ± 1.09) at baseline. Five patients (55.55%) underwent surgery within 72 h, with a mean surgical time of 109.22 min. SCA and LKA values improved significantly in all patients post-surgery. Early surgical intervention (<72 h) correlated with greater improvements in spinal canal area (p = 0.016) and local kyphotic angle (p = 0.004). A significant association was found between spinal canal area improvement and the percentage ratio of fragment height to “normal” vertebral height (rho = 0.682; p = 0.043). Conclusions: Early (<72 h) short-segment percutaneous fixation is recommended for adults with high functional demands and moderate-to-severe axial pain due to single traumatic A3N0M0 thoracolumbar fracture. This “upfront” approach is associated with enhanced indirect decompression and better local kyphotic angle restoration. Considering the fragment morphology could also be important in surgical planning. Full article

During the rice harvesting process, severe occlusion and adhesion exist among multiple targets, such as rice, straw, and leaves, making it difficult to accurately distinguish between rice grains and impurities. To address the current challenges, a lightweight semantic segmentation algorithm for impurities based on an improved SegFormer network is proposed. To make full use of the extracted features, the decoder was redesigned. First, the Feature Pyramid Network (FPN) was introduced to optimize the structure, selectively fusing the high-level semantic features and low-level texture features generated by the encoder. Secondly, a Part Large Kernel Attention (Part-LKA) module was designed and introduced after feature fusion to help the model focus on key regions, simplifying the model and accelerating computation. Finally, to compensate for the lack of spatial interaction capabilities, Bottleneck Recursive Gated Convolution (B-${\mathrm{g}}^n$Conv) was introduced to achieve effective segmentation of rice grains and impurities. Compared with the original model, the improved model’s pixel accuracy (PA) and F1 score increased by 1.6% and 3.1%, respectively. This provides a valuable algorithmic reference for designing a real-time impurity rate monitoring system for rice combine harvesters. Full article

Applying deep learning to unsupervised bearing fault diagnosis in complex industrial environments is challenging. Traditional fault detection methods rely on labeled data, which is costly and labor-intensive to obtain. This paper proposes a novel unsupervised approach, WDCAE-LKA, combining a wide kernel convolutional autoencoder (WDCAE) with a large kernel attention (LKA) mechanism to improve fault detection under unlabeled conditions, and the adaptive threshold module based on a multi-layer perceptron (MLP) dynamically adjusts thresholds, boosting model robustness in imbalanced scenarios. Experimental validation on two datasets (CWRU and a customized ball screw dataset) demonstrates that the proposed model outperforms both traditional and state-of-the-art methods. Notably, WDCAE-LKA achieved an average diagnostic accuracy of 90.29% in varying fault scenarios on the CWRU dataset and 72.89% in the customized ball screw dataset and showed remarkable robustness under imbalanced conditions; compared with advanced models, it shortens training time by 10–26% and improves average fault diagnosis accuracy by 5–10%. The results underscore the potential of the WDCAE-LKA model as a robust and effective solution for intelligent fault diagnosis in industrial applications. Full article

Accurate and efficient tomato detection is one of the key techniques for intelligent automatic picking in the area of precision agriculture. However, under the facility scenario, existing detection algorithms still have challenging problems such as weak feature extraction ability for occlusion conditions and different fruit sizes, low accuracy on edge location, and heavy model parameters. To address these problems, this paper proposed D³-YOLOv10, a lightweight YOLOv10-based detection framework. Initially, a compact dynamic faster network (DyFasterNet) was developed, where multiple adaptive convolution kernels are aggregated to extract local effective features for fruit size adaption. Additionally, the deformable large kernel attention mechanism (D-LKA) was designed for the terminal phase of the neck network by adaptively adjusting the receptive field to focus on irregular tomato deformations and occlusions. Then, to further improve detection boundary accuracy and convergence, a dynamic FM-WIoU regression loss with a scaling factor was proposed. Finally, a knowledge distillation scheme using semantic frequency prompts was developed to optimize the model for lightweight deployment in practical applications. We evaluated the proposed framework using a self-made tomato dataset and designed a two-stage category balancing method based on diffusion models to address the sample class-imbalanced issue. The experimental results demonstrated that the D³-YOLOv10 model achieved an $mA{P}_{0.5}$ of 91.8%, with a substantial reduction of 54.0% in parameters and 64.9% in FLOPs, compared to the benchmark model. Meanwhile, the detection speed of 80.1 FPS more effectively meets the demand for real-time tomato detection. This study can effectively contribute to the advancement of smart agriculture research on the detection of fruit targets. Full article

In response to the challenges of remote sensing imagery, such as unmanned aerial vehicle (UAV) aerial imagery, including differences in target dimensions, the dominance of small targets, and dense clutter and occlusion in complex environments, this paper optimizes the YOLOv8n model and proposes an innovative small-object-detection model called DDSC-YOLO. First, a DualC2f structure is introduced to improve the feature-extraction capabilities of the model. This structure uses dual-convolutions and group convolution techniques to effectively address the issues of cross-channel communication and preserving information in the original input feature mappings. Next, a new attention mechanism, DCNv3LKA, was developed. This mechanism uses adaptive and fine-grained information-extraction methods to simulate receptive fields similar to self-attention, allowing adaptation to a wide range of target size variations. To address the problem of false and missed detection of small targets in aerial photography, we designed a Semantics and Detail Infusion Feature Pyramid Network (SDI-FPN) and added a dedicated detection scale specifically for small targets, effectively mitigating the loss of contextual information in the model. In addition, the coordinate adaptive spatial feature fusion (CASFF) mechanism is used to optimize the original detection head, effectively overcoming multi-scale information conflicts while significantly improving small target localization accuracy and long-range dependency perception. Testing on the VisDrone2019 dataset shows that the DDSC-YOLO model improves the mAP0.5 by 9.3% over YOLOv8n, and its performance on the SSDD and RSOD datasets also confirms its superior generalization capabilities. These results confirm the effectiveness and significant progress of our novel approach to small target detection. Full article