Search Results (646)

The growing use of remote-sensing technologies has placed greater demands on object-detection algorithms, which still face challenges. This study proposes a hierarchical adaptive feature aggregation network (HAF-YOLO) to improve detection precision in remote-sensing images. It addresses issues such as small object size, complex backgrounds, scale variation, and dense object distributions by incorporating three core modules: dynamic-cooperative multimodal fusion architecture (DyCoMF-Arch), multiscale wavelet-enhanced aggregation network (MWA-Net), and spatial-deformable dynamic enhancement module (SDDE-Module). DyCoMF-Arch builds a hierarchical feature pyramid using multistage spatial compression and expansion, with dynamic weight allocation to extract salient features. MWA-Net applies wavelet-transform-based convolution to decompose features, preserving high-frequency detail and enhancing representation of small-scale objects. SDDE-Module integrates spatial coordinate encoding and multidirectional convolution to reduce localization interference and overcome fixed sampling limitations for geometric deformations. Experiments on the NWPU VHR-10 and DIOR datasets show that HAF-YOLO achieved mAP50 scores of 85.0% and 78.1%, improving on YOLOv8 by 4.8% and 3.1%, respectively. HAF-YOLO also maintained a low computational cost of 11.8 GFLOPs, outperforming other YOLO models. Ablation studies validated the effectiveness of each module and their combined optimization. This study presents a novel approach for remote-sensing object detection, with theoretical and practical value. Full article

Background/Objectives: Correction surgery for adult spinal deformity (ASD) reduces disability but may lead to spinal stiffness. Cultural diversity may also influence how this stiffness affects daily life. We aimed to evaluate the impact of correction surgery on Japanese patients with ASD using a newly developed questionnaire and to clarify how these patients adapt to their living environment postoperatively in response to spinal stiffness. Methods: This retrospective study included 74 Japanese patients with operative ASD (mean age: 68.2 ± 7.5 years; fusion involving >5 levels) with a minimum follow-up of 1 year. Difficulties in performing various activities of daily living (ADLs) were assessed using a novel 20-item questionnaire tailored to the Oriental lifestyle. The questionnaire also evaluated lifestyle and environmental changes after surgery. Sagittal and coronal spinal parameters were measured using whole-spine radiographs, and clinical outcomes were assessed using the ODI and SRS-22 scores. Results: Coronal and sagittal alignment significantly improved postoperatively. Although the total ADL score remained unchanged, four trunk-bending activities showed significant deterioration. The lower instrumented vertebrae level and pelvic fusion were associated with lower scores in 11 items closely related to trunk bending or the Oriental lifestyle. After surgery, 61% of patients switched from a Japanese-style mattress to a bed, and 72% swapped their low dining table for one with chairs. Both the ODI and SRS-22 scores showed significant postoperative improvements. Conclusions: Trunk-bending activities worsened postoperatively in Japanese patients with ASD, especially those who underwent pelvic fusion. Additionally, patients often modified their living environment after surgery to accommodate spinal stiffness. Full article

Background/Objectives: We sought to characterize the variance and overlap among definitions of Proximal Junctional Kyphosis (PJK) used in the adult spinal deformity (ASD) literature. PJK is defined as excess in PJK angle, a Cobb angle between the upper-instrumented vertebra (UIV) and a supra-adjacent vertebra (SAV), either one (UIV+1) or two (UIV+2) levels rostral of the UIV. No expert consensus exists for threshold angle or which SAV to use. Methods: A total of 116 thoracolumbar fusion patients ≥ 65 years old were reviewed. The UIV+1 and UIV+2 angles were measured. Six definitions of PJK from the literature were evaluated. These definitions were selected based on citation frequency, historical relevance, and accessibility through commonly used databases. Pearson’s Chi-squared and pairwise comparisons were performed to evaluate the distinctness and agreement rates among these definitions. Results: The six definitions of PJK were as follows: [PJK20] PJK angle ≥ 20° with UIV+2 as the (SAV), [PJK10] PJK angle ≥ 10° with a >10° change from pre-op with UIV+2 as the SAV, [PJK2SD] PJK angle > 2 standard deviations from average with UIV+1 as the SAV, [PJK10+10] PJK angle ≥ 10° with a >10° change from pre-op with UIV+1 as the SAV, [PJK15] PJK angle > 15° with UIV+1 as the SAV, and [PJK30] PJK angle > 30° with UIV+2 as the SAV, or displaced rod fracture, or reoperation within 2 years for junctional failure, pseudoarthrosis, or rod fracture. [PJK10] and [PJK2SD] were the most distinct definitions while [PJK20], [PJK10+10], [PJK15], and [PJK30] showed no significant pairwise differences. [PJK2SD] was stringent, while definition [PJK30] included unique diagnostic information not captured by other definitions. Conclusions: The use of [PJK20], [PJK10+10], [PJK15], or [PJK30] is recommended for consistency, with [PJK15] presenting the best balance. Stringent [PJK2SD] may be beneficial for identifying severe PJK, though with low sensitivity. Overall, PJK definitions must be standardized for the consistent reporting of clinical outcomes and research comparability. Full article

A (NiCoCr)_99.25C_0.75 medium entropy alloy (MEA) was developed via laser powder bed fusion (LPBF) using pre-alloyed powder feedstock containing 0.75 at%C, followed by a precipitation heat treatment. The as-built alloy exhibited high density (>99.9%), columnar grains, fine substructures, and strong <111> texture. Heat treatment at 700 °C for 1 h promoted the precipitation of Cr-rich carbides (Cr₂₃C₆) along grain and substructure boundaries, which stabilized the microstructure through Zener pinning and the consumption of carbon from the matrix. The heat-treated alloy achieved excellent cryogenic tensile properties at 77 K, with a yield strength of 1230 MPa and an ultimate tensile strength of 1.6 GPa. Compared to previously reported LPBF-built NiCoCr-based MEAs, this alloy exhibited superior strength at both room and cryogenic temperatures, indicating its potential for structural applications in extreme environments. Deformation mechanisms at cryogenic temperature revealed abundant deformation twinning, stacking faults, and strong dislocation–precipitate interactions. These features contributed to dislocation locking, resulting in a work hardening rate higher than that observed at room temperature. This study demonstrates that carbon addition and heat treatment can effectively tune the stacking fault energy and stabilize substructures, leading to enhanced cryogenic mechanical performance of LPBF-built NiCoCr MEAs. Full article

Accurate detection of maize tassels plays a crucial role in yield estimation of maize in precision agriculture. Recently, UAV and deep learning technologies have been widely introduced in various applications of field monitoring. However, complex field backgrounds pose multiple challenges against the precision detection of maize tassels, including maize tassel multi-scale variations caused by varietal differences and growth stage variations, intra-class occlusion, and background interference. To achieve accurate maize tassel detection in UAV images under complex field backgrounds, this study proposes an MSMT-RTDETR detection model. The Faster-RPE Block is first designed to enhance multi-scale feature extraction while reducing model Params and FLOPs. To improve detection performance for multi-scale targets in complex field backgrounds, a Dynamic Cross-Scale Feature Fusion Module (Dy-CCFM) is constructed by upgrading the CCFM through dynamic sampling strategies and multi-branch architecture. Furthermore, the MPCC3 module is built via re-parameterization methods, and further strengthens cross-channel information extraction capability and model stability to deal with intra-class occlusion. Experimental results on the MTDC-UAV dataset demonstrate that the MSMT-RTDETR significantly outperforms the baseline in detecting maize tassels under complex field backgrounds, where a precision of 84.2% was achieved. Compared with Deformable DETR and YOLOv10m, improvements of 2.8% and 2.0% were achieved, respectively, in the mAP₅₀ for UAV images. This study proposes an innovative solution for accurate maize tassel detection, establishing a reliable technical foundation for maize yield estimation. Full article

Due to the high potential of shot peening to improve the surface quality of additively manufactured components, in this work, the influence on surface morphology and, thus, the surface topography and selected properties of the surface and subsurface regions of additively manufactured parts is analysed. For this, cubic specimens made of stainless steel 316L and AlSi10Mg were manufactured via powder bed fusion laser beam metal (PBF-LB/M), and subsequently, their “as-built” surfaces were shot peened. Shot peening was conducted with stainless steel or ceramic beads using pressures of 3 and 5 bar. The resulting morphologies were analysed regarding topography, microstructure and mechanical properties (hardness and cyclic deformation behaviour) in the subsurface region and the residual stresses. The results demonstrate a strong plastic deformation due to shot peening, resulting in a decreased surface roughness as well as an increased hardness and compressive residual stresses near the surface. These effects were generally more pronounced after using higher peening pressure and/or ceramic beads. Note that two sets of PBF-LB/M parameters were used to produce the AlSi10Mg specimens. The investigation of these specimens reveals an interrelation between the parameters used in shot peening and PBF-LB/M on the resulting surface morphology. Full article

The management of adult spinal deformity (ASD) has evolved dramatically over the past century, transitioning from external bracing and in situ fusion to complex, technology-driven surgical interventions. This review traces the historical development of spinal deformity correction and highlights contemporary enabling technologies that are redefining the surgical landscape. Advances in stereoradiographic imaging now allow for precise, low-dose three-dimensional assessment of spinopelvic parameters and segmental bone density, facilitating individualized surgical planning. Robotic assistance and intraoperative navigation improve the accuracy and safety of instrumentation, while patient-specific rods and interbody implants enhance biomechanical conformity and alignment precision. Machine learning and predictive modeling tools have emerged as valuable adjuncts for risk stratification, surgical planning, and outcome forecasting. Minimally invasive deformity correction strategies, including anterior column realignment and circumferential minimally invasive surgery (cMIS), have demonstrated equivalent clinical and radiographic outcomes to traditional open surgery with reduced perioperative morbidity in select patients. Despite these advancements, complications such as proximal junctional kyphosis and failure remain prevalent. Adjunctive strategies—including ligamentous tethering, modified proximal fixation, and vertebral cement augmentation—offer promising preventive potential. Collectively, these innovations signal a paradigm shift toward precision spine surgery, characterized by data-informed decision-making, individualized construct design, and improved patient-centered outcomes in spinal deformity care. Full article

Ensuring the structural safety of steel trusses in escalators is critical for the reliable operation of vertical transportation systems. While manual inspection remains widely used, its dependence on human judgment leads to extended cycle times and variable defect-recognition rates, making it less reliable for identifying subtle surface imperfections. To address these limitations, a novel context-aware, multi-scale deep learning framework based on the YOLOv5 architecture is proposed, which is specifically designed for automated structural defect detection in escalator steel trusses. Firstly, a method called GIES is proposed to synthesize pseudo-multi-channel representations from single-channel grayscale images, which enhances the network’s channel-wise representation and mitigates issues arising from image noise and defocused blur. To further improve detection performance, a context enhancement pipeline is developed, consisting of a local feature module (LFM) for capturing fine-grained surface details and a global context module (GCM) for modeling large-scale structural deformations. In addition, a multi-scale feature fusion module (MSFM) is employed to effectively integrate spatial features across various resolutions, enabling the detection of defects with diverse sizes and complexities. Comprehensive testing on the NEU-DET and GC10-DET datasets reveals that the proposed method achieves 79.8% mAP on NEU-DET and 68.1% mAP on GC10-DET, outperforming the baseline YOLOv5s by 8.0% and 2.7%, respectively. Although challenges remain in identifying extremely fine defects such as crazing, the proposed approach offers improved accuracy while maintaining real-time inference speed. These results indicate the potential of the method for intelligent visual inspection in structural health monitoring and industrial safety applications. Full article

Limited recovery of the viscoelastic properties of aged asphalt on RAP surfaces at ambient temperature reduces interface fusion and bonding with new emulsified asphalt, degrading pavement performance and limiting large-scale promotion and high-value applications of the emulsified asphalt cold recycled mixture (EACRM). Therefore, a cold regenerant was independently prepared to rapidly penetrate, soften, and activate aged asphalt at ambient temperature in this paper, and its effects on the volumetric composition, mechanical strength, and pavement performance of EACRM were systematically investigated. The results showed that as the cold regenerant content increased, the air voids, indirect tensile strength (ITS), and high-temperature deformation resistance of EACRM decreased, while the dry–wet ITS ratio, cracking resistance, and fatigue resistance increased. Considering the comprehensive pavement performance requirements of cold recycled pavements, the optimal content of the activated cold regenerant for EACRM was determined to be approximately 0.6%. Full article

To overcome the limitations of traditional image alignment methods in capturing deep semantic features, a deep feature information image alignment network (DFA-Net) is proposed. This network aims to enhance image alignment performance through multi-level feature learning. DFA-Net is based on the deep residual architecture and introduces spatial pyramid pooling to achieve cross-scalar feature fusion, effectively enhancing the feature’s adaptability to scale. A feature enhancement module based on the self-attention mechanism is designed, with key features that exhibit geometric invariance and high discriminative power, achieved through a dynamic weight allocation strategy. This improves the network’s robustness to multimodal image deformation. Experiments on two public datasets, MSRS and RoadScene, show that the method performs well in terms of alignment accuracy, with the RMSE metrics being reduced by 0.661 and 0.473, and the SSIM, MI, and NCC improved by 0.155, 0.163, and 0.211; and 0.108, 0.226, and 0.114, respectively, compared with the benchmark model. The visualization results validate the significant improvement in the features’ visual quality and confirm the method’s advantages in terms of stability and discriminative properties of deep feature extraction. Full article

UAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (e.g., deformation, occlusion, lighting variations). RGB-Thermal fusion methods integrate visible-light texture and thermal infrared temperature features effectively, but current approaches are constrained by limited datasets and insufficient exploitation of cross-modal complementary information, ignoring cross-level feature interaction. A time-synchronized multi-scene, multi-angle aerial RGB-Thermal dataset (RGBT-3M) with “Smoke–Fire–Person” annotations and modal alignment via the M-RIFT method was constructed as a way to address the problem of data scarcity in wildfire scenarios. Finally, we propose a CP-YOLOv11-MF fusion detection model based on the advanced YOLOv11 framework, which can learn heterogeneous features complementary to each modality in a progressive manner. Experimental validation proves the superiority of our method, with a precision of 92.5%, a recall of 93.5%, a mAP50 of 96.3%, and a mAP50-95 of 62.9%. The model’s RGB-Thermal fusion capability enhances early fire detection, offering a benchmark dataset and methodological advancement for intelligent forest conservation, with implications for AI-driven ecological protection. Full article

Foreign Object Debris (FOD) detection is paramount for airport operations. The precise identification and removal of FOD are critical for ensuring airplane flight safety. This study collected FOD images using optical imaging sensors installed at Urumqi Airport and created a custom FOD dataset based on these images. To address the challenges of small targets and complex backgrounds in the dataset, this paper proposes optimizations and improvements based on the advanced detection network Dab-Deformable. First, this paper introduces a Lightweight Deep-Shallow Feature Fusion algorithm (LDSFF), which integrates a hotspot sensing network and a spatial mapping enhancer aimed at focusing the model on significant regions. Second, we devise a Multi-Directional Deformable Channel Attention (MDDCA) module for rational feature weight allocation. Furthermore, a feedback mechanism is incorporated into the encoder structure, enhancing the model’s capacity to capture complex dependencies within sequential data. Additionally, when combined with a Threshold Selection (TS) algorithm, the model effectively mitigates the distraction caused by the serialization of multi-layer feature maps in the Transformer architecture. Experimental results on the optical small FOD dataset show that the proposed network achieves a robust performance and improved accuracy in FOD detection. Full article

The accurate inversion of mining subsidence prediction parameters is key to the precise prediction of deformation during mining. However, the use of traditional genetic algorithms (GA) for inversion prediction has problems such as poor resistance to differences, and the accuracy of inversion parameters is affected when key monitoring points are missing. In response to these issues, a probability integral parameter inversion method is proposed in this study that integrates a selection-weighted iterative robust genetic algorithm. This method combines the selection-weighted iteration method with a genetic algorithm to determine the weights of different observation values, and then a probability integral parameter inversion method is constructed for the fusion selection-weighted iterative robust GA. The results indicate that the fusion selection-weighted iterative robust GA is stronger than the traditional GA, and the parameters obtained have higher accuracy and greater reliability. An experiment using real working face engineering showed that, compared with the GA method, the RMSE (root mean square error) of the proposed method is reduced by 24.4 mm and 37.5 mm, thus verifying the usability of this method. Full article

Accurate pig counting is crucial for precision livestock farming, enabling optimized feeding management and health monitoring. Detection-based counting methods face significant challenges due to mutual occlusion, varying illumination conditions, diverse pen configurations, and substantial variations in pig densities. Previous approaches often struggle with complex agricultural environments where lighting conditions, pig postures, and crowding levels create challenging detection scenarios. To address these limitations, we propose EAPC-YOLO (enhanced adaptive pig counting YOLO), a robust architecture integrating density-aware processing with advanced detection optimizations. The method consists of (1) an enhanced YOLOv8 network incorporating multiple architectural improvements for better feature extraction and object localization. These improvements include DCNv4 deformable convolutions for irregular pig postures, BiFPN bidirectional feature fusion for multi-scale information integration, EfficientViT linear attention for computational efficiency, and PIoU v2 loss for improved overlap handling. (2) A density-aware post-processing module with intelligent NMS strategies that adapt to different crowding scenarios. Experimental results on a comprehensive dataset spanning diverse agricultural scenarios (nighttime, controlled indoor, and natural daylight environments with density variations from 4 to 30 pigs) demonstrate our method achieves 94.2% mAP@0.5 for detection performance and 96.8% counting accuracy, representing 12.3% and 15.7% improvements compared to the strongest baseline, YOLOv11n. This work enables robust, accurate pig counting across challenging agricultural environments, supporting precision livestock management. Full article

Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with their background, presenting significant challenges such as low contrast, complex textures, and blurred boundaries. Existing deep learning methods often struggle to achieve robust segmentation under these conditions. To address these limitations, this paper proposes a novel COD network, SAM2-DFBCNet, built upon the SAM2 Hiera architecture. Our network incorporates three key modules: (1) the Camouflage-Aware Context Enhancement Module (CACEM), which fuses local and global features through an attention mechanism to enhance contextual awareness in low-contrast scenes; (2) the Cross-Scale Feature Interaction Bridge (CSFIB), which employs a bidirectional convolutional GRU for the dynamic fusion of multi-scale features, effectively mitigating representation inconsistencies caused by complex textures and deformations; and (3) the Dynamic Boundary Refinement Module (DBRM), which combines channel and spatial attention mechanisms to optimize boundary localization accuracy and enhance segmentation details. Extensive experiments on three public datasets—CAMO, COD10K, and NC4K—demonstrate that SAM2-DFBCNet outperforms twenty state-of-the-art methods, achieving maximum improvements of 7.4%, 5.78%, and 4.78% in key metrics such as S-measure ($S_{\alpha }$), F-measure ($F_{\beta }$), and mean E-measure ($E_{\varphi }$), respectively, while reducing the Mean Absolute Error (M) by 37.8%. These results validate the superior performance and robustness of our approach in complex camouflage scenarios. Full article