Spatial Mechanisms Research Articles

A Transformer-Based Image-Guided Depth-Completion Model with Dual-Attention Fusion Module.

Depth information is crucial for perceiving three-dimensional scenes. However, depth maps captured directly by depth sensors are often incomplete and noisy, our objective in the depth-completion task is to generate dense and accurate depth maps from sparse depth inputs by fusing guidance information from corresponding color images obtained from camera sensors. To address these challenges, we introduce transformer models, which have shown great promise in the field of vision, into the task of image-guided depth completion. By leveraging the self-attention mechanism, we propose a novel network architecture that effectively meets these requirements of high accuracy and resolution in depth data. To be more specific, we design a dual-branch model with a transformer-based encoder that serializes image features into tokens step by step and extracts multi-scale pyramid features suitable for pixel-wise dense prediction tasks. Additionally, we incorporate a dual-attention fusion module to enhance the fusion between the two branches. This module combines convolution-based spatial and channel-attention mechanisms, which are adept at capturing local information, with cross-attention mechanisms that excel at capturing long-distance relationships. Our model achieves state-of-the-art performance on both the NYUv2 depth and SUN-RGBD depth datasets. Additionally, our ablation studies confirm the effectiveness of the designed modules.

Accurate crowd counting for intelligent video surveillance systems

The paper presents a novel deep learning approach for crowd counting in intelligent video surveillance systems, addressing the growing need for accurate monitoring of public spaces in urban environments. The demand for precise crowd estimation arises from challenges related to security, public safety, and efficiency in urban areas, particularly during large public events. Existing crowd counting techniques, including feature-based object detection and regression-based methods, face limitations in high-density environments due to occlusions, lighting variations, and diverse human figures. To overcome these challenges, the authors propose a new deep encoder-decoder architecture based on VGG16, which incorporates hierarchical feature extraction with spatial and channel attention mechanisms. This architecture enhances the model’s ability to manage variations in crowd density, leveraging adaptive pooling and dilated convolutions to extract meaningful features from dense crowds. The model’s decoder is further refined to handle sparse and crowded scenes through separate density maps, improving its adaptability and accuracy. Evaluations of the proposed model on benchmark datasets, including Shanghai Tech and UCF CC 50, demonstrate superior performance over state-of-the-art methods, with significant improvements in mean absolute error and mean squared error metrics. The paper emphasizes the importance of addressing environmental variability and scale differences in crowded environments and shows that the proposed model is effective in both sparse and dense crowd conditions. This research contributes to the advancement of intelligent video surveillance systems by providing a more accurate and efficient method for crowd counting, with potential applications in public safety, transportation management, and urban planning.

Attentional templates for target features versus locations

Visual search is guided by visual working memory representations (i.e., attentional templates) that are activated prior to search and contain target-defining features (e.g., color). In the present study, we tested whether attentional templates can also contain spatial target properties (knowing where to look for) and whether attentional selection guided by such feature-specific templates is equally efficient than selection that is based on feature-specific templates (knowing what to look for). In every trial, search displays were either preceded by semantic color or location cues, indicating the upcoming target color or location, respectively. Qualitative differences between feature- and location-based template guidance were substantiated in terms of selection efficiency in low-load (one target color/location) versus high-load trials (two target colors/locations). Behavioral and electrophysiological (N2pc) measures of target selection speed and accuracy were combined for converging evidence. In line with previous studies, we found that color search was highly efficient, even under high-low conditions, when multiple attentional templates were activated to guide attentional selection in a spatially global fashion. Importantly, results in the location task almost perfectly mirrored the findings of the color task, suggesting that multiple templates for different target locations were activated concurrently when two possible target locations were task relevant. Our findings align with accounts that assume a common neuronal network during preparation for location and color search, but regard spatial and feature-based selection mechanisms as independent.

Accelerable adaptive cepstrum and L2-Dual Net for acoustic emission-based quality monitoring in laser shock peening

Acoustic emission monitoring in laser shock peening facilitates real-time detection of potential quality issues arising from variations in industrial parameters, enabling iterative optimization of the manufacturing process through material behavior analysis. However, existing research still lacks a comprehensive understanding of the time-varying time-frequency characteristics in dynamic acoustic emission and efficient corresponding models. Therefore, this study proposes an innovative monitoring approach that integrates accelerable adaptive cepstrum (AAC) and L2-Dual Net. Specifically, AAC first employs variable frames and filters to map time-varying features in the signal, and then obtains representative frame length distributions and filter weights for different operating conditions based on statistical information. AAC not only unveils time-varying features in signals but also boasts an efficient computational process. L2-Dual Net is a novel quality assessment model with robust feature extraction and local spatial feature interactions. The incorporation of L2 norm equips the model with robust interference immunity, while the dual spatial attention mechanism helps the model to interact with spatial features exhibiting different time-frequencies. Variable process parameter experiments for aluminum alloy 7075 and titanium alloy TC4 were conducted to validate the reliability of the proposed method. Results demonstrate that AAC showcases optimal computational efficiency and higher feature resolution. When compared with state-of-the-art network architectures, L2-Dual Net exhibits superior information flow, along with higher recognition accuracy and robustness. Moreover, various variants of L2-Dual Net are explored and the code is accessible at https://github.com/Qinr1026/L2-Dual-Net. The proposed method holds promising potential for application in other areas of acoustic emission monitoring.

Detecting Driving Factors from Spatial Spectrums Perspective: A Multilevel Analysis of Homestay Industry in Heterogeneous Heritage Destinations

ABSTRACT Homestay represents a tourism product constrained by space and dependent on regional context. While academic attention has grown toward studying homestay distribution patterns in urban areas, heritage destinations have received limited focus. This study establishes a two-scale analytical framework to explore the spatial evolution patterns and formation mechanism of the homestay industry in diverse heritage destinations, identifying the main factors influencing spatial heterogeneity through geographic detectors. Our findings elucidate several key insights: (a) a consistent annual growth trend, alongside a distinct clustering and spatial autocorrelation in the distribution of homestays across the three types of heritage destinations – natural, cultural, and mixed World Heritage sites; (b) the predominant influence of topography, tourism development levels, and transportation infrastructure in shaping the spatial differentiation of homestays; and (c) socioeconomic and tourism development factors emerging as the primary drivers of this differentiation, while the transportation factor, particularly road mileage, exhibits a heightened significance in natural heritage sites. This study offers insights for planning, marketing, and managing tourism heritage destinations.

The multiscale response of global cropland cropping intensity to urban expansion

CONTEXTUrban expansion(UE) and multiple cropping(MC) are key factors in anthropogenic impacts on global environmental change. However, the multi-scale response patterns of UE and MC have not yet been revealed, and how urbanization affects cropland intensification is still not deeply explored. OBJECTIVEThis study examines the spatial and temporal trends in global UE and MC and analyses the multi-scale response patterns of both. METHODSThe GEE (Google Earth Engine) platform was used to count global cropland cropping intensity (CCI) and impervious surface rasters on an image-by-image basis, while GIS was employed for spatial analyses, and the generalized additive model (GAM) was applied to inscribe variable response trajectories. RESULTS AND CONCLUSIONThe global multiple cropping index(MCI) increased significantly (by 4.1 %) over the period 2001–2019, with growth in double- and triple-cropped cropland dominating this change. Double cropping, as a widespread global farming strategy, has led to a shift towards the intensification of agriculture, with countries in the northern hemisphere contributing more. Global UE significantly expands to twice the baseline level at an average annual growth rate of 2. 42 × 104 km2 over the period 2001–2019, with the expansion of world-class urban agglomerations in China, the United States and Europe dominates this trend. The spatial clustering of MC and UE has continued to intensify, with high-intensity cropping strategies progressively clustering towards areas of significant UE, and this tendency has a clear decreasing urban-rural gradient effect. The global CCI grows significantly and non-linearly with UE, but an important inflection point in the growth trajectory has occurred under the influence of threshold effects. Developed countries tend to be more flexible in their cropping intensity strategies as they move forward with urbanization. There is a clear increasing effect of the urban-rural gradient in the degree of non-linearity in the response of urbanization and cropping intensity. SIGNIFICANCEThe results of the study contribute to the understanding of the complex spatial and temporal coupling mechanisms between UE and MC, and provide useful insights for the development of trade-offs between urbanization and maturity strategies.

SDAM: A dual attention mechanism for high-quality fusion of infrared and visible images.

Image fusion of infrared and visible images to obtain high-quality fusion images with prominent infrared targets has important applications in various engineering fields. However, current fusion processes encounter problems such as unclear texture details and imbalanced infrared targets and texture detailed information, which lead to information loss. To address these issues, this paper proposes a method for infrared and visible image fusion based on a specific dual-attention mechanism (SDAM). This method employs an end-to-end network structure, which includes the design of channel attention and spatial attention mechanisms. Through these mechanisms, the method can fully exploit the texture details in the visible images while preserving the salient information in the infrared images. Additionally, an optimized loss function is designed to combine content loss, edge loss, and structure loss to achieve better fusion effects. This approach can fully utilize the texture detailed information of visible images and prominent information in infrared images, while maintaining better brightness and contrast, which improves the visual effect of fusion images. Through conducted ablation experiments and comparative evaluations on public datasets, our research findings demonstrate that the SDAM method exhibits superior performance in both subjective and objective assessments compared to the current state-of-the-art fusion methods.

Universal mechanical modeling of fiber bundle under torsion: An experimental and numerical study

AbstractIn this paper, a universal mechanical model for the torsional behavior of fiber bundle was established, grounded in the principles of spatial geometry and continuum mechanics, incorporating differential geometry formulas. The model was validated through self‐designed experimental equipment and finite element simulations using Ansys Workbench, showing strong agreement between predicted torsional fracture behavior and experimental results. The study further examined the contributions of fiber bending, torsion, and tension to the overall torque, revealing that torsion plays the dominant role. Additionally, the effect of filament count on the torsional performance of fiber bundles was analyzed, demonstrating that while the number of fibers significantly influences stress distribution, its impact on overall torque is minimal.Highlights A universal mechanical model for fiber bundle torsional is proposed. High consistency between simulation and experimental results. Examined filament count effect on torsional strength. More filaments reduce stress concentration, improving performance.

Iterative Removal of G-PCC Attribute Compression Artifacts Based on a Graph Neural Network

As a compression standard, Geometry-based Point Cloud Compression (G-PCC) can effectively reduce data by compressing both geometric and attribute information. Even so, due to coding errors and data loss, point clouds (PCs) still face distortion challenges, such as the encoding of attribute information may lead to spatial detail loss and visible artifacts, which negatively impact visual quality. To address these challenges, this paper proposes an iterative removal method for attribute compression artifacts based on a graph neural network. First, the geometric coordinates of the PCs are used to construct a graph that accurately reflects the spatial structure, with the PC attributes treated as signals on the graph’s vertices. Adaptive graph convolution is then employed to dynamically focus on the areas most affected by compression, while a bi-branch attention block is used to restore high-frequency details. To maintain overall visual quality, a spatial consistency mechanism is applied to the recovered PCs. Additionally, an iterative strategy is introduced to correct systematic distortions, such as additive bias, introduced during compression. The experimental results demonstrate that the proposed method produces finer and more realistic visual details, compared to state-of-the-art techniques for PC attribute compression artifact removal. Furthermore, the proposed method significantly reduces the network runtime, enhancing processing efficiency.

Characterization Study of Deep-Level Defect Spatial Distribution, Emission Mechanisms, and Structural Identification

Abstract The characterization of defects in semiconductor materials and devices is crucial for enhancing the performance and reliability of semiconductor products. This tutorial review focuses on Deep Level Transient Spectroscopy (DLTS) as the primary analytical tool, thoroughly discussing its distinct advantages in deep-level defect characterization. However, it is unable to reveal the concentration-depth distribution of deep-level defects, neglects the dependency of carrier emission rates on the electric field, and fails to accurately identify defect structures.
To overcome these limitations, two enhanced DLTS techniques have been developed to extend the capabilities of DLTS. These enhancements include the utilization of graded fill pulse technology to accurately map defect distributions at various depths within devices, facilitating individual defect characterization across different layers of multilayered structures; the application of varying electric field strengths to samples to delve into the intricate physical mechanisms of defects during carrier emission processes; and the adjustment of the duration of electric pulse injection to monitor signal growth trends, deducing the microstructure of defects. The paper integrates research findings from a wide array of field experts, meticulously outlines a description of how to obtain the depth distribution of defect concentration in devices, furnishes quantitative criteria for both the Poole-Frenkel effect and phonon-assisted tunneling mechanisms of carrier emission, and provides specific examples for distinguishing between interface states/bulk defects and point defects/extended defects. This enhances both the theoretical and practical knowledge in this field. The advanced DLTS techniques outlined provide crucial guidance for defect characterization and performance optimization in semiconductor devices with new structures and materials.

Motor imagery EEG signal classification based on deformable convolution v3 and adaptive spatial attention mechanism

This paper is dedicated to solving the issue of insufficient feature extraction and declining model performance in the classification of motor imagery electroencephalogram (EEG) signals. We propose an enhanced ResNet18 neural network model and introduce two pivotal innovations at the model level. Firstly, we present the deformable convolution v3 (DCNv3), an improved convolutional structure that overcomes the limitations of the original deformable convolution. Through unbiased design with center sampling points, DCNv3 achieves more precise feature localization, enhances the model’s representation capability for complex structures, and reduces the risk of overfitting. Simultaneously, it comprehensively captures features in effective information regions, thereby strengthening the model’s generalization ability. Furthermore, this enhancement design also improves computational efficiency, reducing computational and parameter burdens. Secondly, we introduce a novel Adaptive Spatial Attention Mechanism (ASAM) aimed at precisely capturing feature correlations, thereby avoiding information loss. We conducted extensive comparative experiments on publicly available datasets BCI IV dataset 2a, BCI IV dataset 2b, and BCI III dataset 3a, achieving accuracy rates of 91.32%, 92.3%, and 90.47% respectively. Compared to other methods, our approach not only significantly improves the average classification accuracy but also demonstrates remarkable generalization capabilities. These results validate the effectiveness and stability of our method, thereby better meeting the practical application requirements of brain-computer interface technology.

Target Recognition Based on Infrared and Visible Image Fusion and Improved YOLOv8 Algorithm.

In response to the issue that the fusion process of infrared and visible images is easily affected by lighting factors, in this paper, we propose an adaptive illumination perception fusion mechanism, which was integrated into an infrared and visible image fusion network. Spatial attention mechanisms were applied to both infrared images and visible images for feature extraction. Deep convolutional neural networks were utilized for further feature information extraction. The adaptive illumination perception fusion mechanism is then integrated into the image reconstruction process to reduce the impact of lighting variations in the fused images. A Median Strengthening Channel and Spatial Attention Module (MSCS) was designed to be integrated into the backbone of YOLOv8. In this paper, we used the fusion network to create a dataset named ivifdata for training the target recognition network. The experimental results indicated that the improved YOLOv8 network saw further enhancements of 2.3%, 1.4%, and 8.2% in the Recall, mAP50, and mAP50-95 metrics, respectively. The experiments revealed that the improved YOLOv8 network has advantages in terms of recognition rate and completeness, while also reducing the rates of false negatives and false positives.

Spatial structure and individual competition characteristics of secondary Mongolian oak mature forests in the mountainous area of eastern Liaoning Province, China.

The community structure of natural mature forests is determined by long-term forest succession, characterized by rational structure, rich biodiversity, and high ecological function. Understanding the spatial structure and formation mechanisms of mature forests is a fundamental prerequisite for forest management. We analyzed four structure parameters, including diameter structure, angular scale, size ratio, and mixture degree, as well as the Hegyi competition index, of secondary Quercus mongolica (Mongolian oak) mature forests in the mountainous area of eastern Liaoning Province. The results showed that Q. mongolica predominated the tree layer. In the sapling layer, Q. mongolica, Tilia amurensis, and Acer pictum were the dominant species. In the seedling layer, Acer pseudosieboldianum, T. amurensis, and A. amurensis dominated, with very few Q. mongolica seedlings. The overall diameter distribution of the stand showed an inverse "J" shape, while the diameter distribution of Q. mongolica, the dominant tree species, followed a normal distribution. The horizontal spatial structure of the stand was generally randomly distributed, with an average angle scale of 0.505, size ratio of 0.219, and mixture degree of 0.670 for Q. mongolica. From the perspective of spatial structure binary distribution, Q. mongolica individuals which had a random distribution exhibited greater growth advantages and higher levels of mixing, in comparison to other distribution types. Randomly distributed dominant and subdominant individuals made up nearly half individuals in the stand, and showed a high degree of mixing with surrounding trees. The stand-level individual tree competition index decreased with increasing diameter classes. When the diameter at breast height exceeded 20 cm, the competition index tended to stabilize (ΔCI<2). The competitive radius of individual Q. mongolica trees was 8 m, with intraspecific competition as the main pressure. Other species experienced competition pressure primarily from interspecific sources. Our results suggested that competition played an important role in shaping the spatial structure of secondary Q. mongolica mature forests.

Design of a traction neck brace with two degrees-of-freedom via a novel architecture of a spatial parallel mechanism

Abstract Traction of the head-neck is important in the treatment of patients suffering from neck pain due to degeneration of the intervertebral discs. Conventional neck traction is provided manually by experienced physical therapists who maintain a desired orientation of the head-neck relative to the trunk while applying the traction. It is postulated that innovative designs of neck exoskeletons can provide the same function both flexibly and accurately. This article presents a novel architecture of a parallel mechanism whose base sits on the human shoulders with 4 parallel chains, each chain having a revolute-revolute-universal-revolute (RRUR) structure, while the end-effector is connected rigidly to the human head. Each chain has five degrees-of-freedom (DOF) and applies a constraint on the motion of the end-effector. As a result, this parallel mechanism allows two DOFs to the end-effector. These are (i) forward flexion or lateral bending of the head and (ii) vertical translation. An important motivation for the current design with RRUR structure is to characterize the range of forward flexion/lateral bending of the head-neck with this structure and the vertical translation to the end-effector. A physical prototype was constructed and tested to evaluate the performance of this mechanism in hardware for the proposed application.

Dual Channel‐Spatial Self‐Attention Transformer and CNN synergy network for 3D medical image segmentation

Even though the Vision Transformer leverages the self-attention mechanism to capture long-range dependencies, showing significant potential in medical image segmentation, the limited annotations in the image dataset make it difficult for the Transformer model to extract different global features, resulting in attention collapse and generating similar or identical attention maps. Previous studies have attempted to solve the problem by integrating convolutional neural layers into Transformer-based architectures. However, improper integration may lead to the inability of the model to effectively capture local and global information in both spatial and channel dimensions. To address the above issue, we propose a hybrid architecture using the Dual Channel-Spatial Self-Attention Transformer and CNN Synergy Network (DTC-SUNETR) for medical image segmentation. Specifically, we redesigned the self-attention mechanism. A novel Channel-Spatial Self-Attention (CSSA) block is introduced to integrate the enhanced channel and spatial self-attention mechanism to capture the global relationship and local structure among image features. This helps the model to more comprehensively understand the inter-dependencies between different channels and capture the relationships between different pixels, thus enhancing the feature representation of the corresponding dimensions. Simultaneously, it also improves the overall computational efficiency of the network. Extensive experiments on four different medical image segmentation datasets, including Synapse, ACDC, Brain Tumor, and Lung Tumor, demonstrate the superiority of the proposed DTC-SUNETR over state-of-the-art methods.

Snow Cover Extraction from Landsat 8 OLI Based on Deep Learning with Cross-Scale Edge-Aware and Attention Mechanism

Snow cover distribution is of great significance for climate change and water resource management. Current deep learning-based methods for extracting snow cover from remote sensing images face challenges such as insufficient local detail awareness and inadequate utilization of global semantic information. In this study, a snow cover extraction algorithm integrating cross-scale edge perception and an attention mechanism on the U-net model architecture is proposed. The cross-scale edge perception module replaces the original jump connection of U-net, enhances the low-level image features by introducing edge detection on the shallow feature scale, and enhances the detail perception via branch separation and fusion features on the deep feature scale. Meanwhile, parallel channel and spatial attention mechanisms are introduced in the model encoding stage to adaptively enhance the model’s attention to key features and improve the efficiency of utilizing global semantic information. The method was evaluated on the publicly available CSWV_S6 optical remote sensing dataset, and the accuracy of 98.14% indicates that the method has significant advantages over existing methods. Snow extraction from Landsat 8 OLI images of the upper reaches of the Irtysh River was achieved with satisfactory accuracy rates of 95.57% (using two, three, and four bands) and 96.65% (using two, three, four, and six bands), indicating its strong potential for automated snow cover extraction over larger areas.

Reexploring the conception of heat-health risk: From the perspectives of dimensionality and spatiality.

Extreme heat events are more frequent and intense as a result of global climate change, thus posing tremendous threats to public health. However, extant literature exploring the multidimensional features of heat-health risks from a spatial perspective is limited. This study revisits extreme heat-health risk and decomposes this concept by integrating multi-sourced datasets, identifying compositional features, examining spatial patterns, and comparing classified characteristics based on local conditions. Using Maryland as the focal point, we found that the components of heat-health risk are different from traditional risk dimensions (i.e., vulnerability, hazards, and exposure). Through a local-level clustering analysis, heat-health risks were compared with areas having similar features, and among those with different features. The findings suggest a new perspective for understanding the socio-environmental and socio-spatial features of heat-health risks. They also offer an apt example of applying cross-disciplinary methods and tools for investigating an ever-changing phenomenon. Moreover, the spatial classification mechanism provides insights about the underlying causes of heat-health risk disparities and offers reference points for decision-makers regarding identification of vulnerable areas, resource allocation, and causal inferences when planning for and managing extreme heat disasters.

Accurate Prediction of Tea Catechin Content with Near-Infrared Spectroscopy by Deep Learning Based on Channel and Spatial Attention Mechanisms

Accurate Prediction of Tea Catechin Content with Near-Infrared Spectroscopy by Deep Learning Based on Channel and Spatial Attention Mechanisms

Scientific and Technological Innovation Effects on High-Quality Agricultural Development: Spatial Boundaries and Mechanisms

This study investigates the spatial boundaries and mechanisms of the effect of scientific and technological innovation (STI) on high-quality agricultural development (HQA) to enhance agricultural practices. By employing a double-fixed spatial Durbin model and analyzing panel data from 167 prefectural-level cities in major grain-producing regions spanning from 2004 to 2021, we revealed significant spatiotemporal variations in the impact of STI on HQA in both local and adjacent cities. Our findings remained robust after rigorous testing. The study identified the spillover range of STI to be 420 km, displaying a distinctive inverted U-shaped trend around 170 km. Mechanism analysis indicates that both agricultural industry upgrades and human capital levels within 420 km amplify the influence of STI on local HQA, with only the latter demonstrating spillover effects. Within 170 km, both factors effectively regulate HQA in adjacent cities, while beyond this distance, only human capital regulatory impact continues to exhibit spillover effects. These insights offer theoretical guidance for designing effective agricultural scientific and technology promotion policies aimed at elevating the quality of HQA.

Re-Examination of the Relationship between Industrial Agglomeration and Haze Pollution: From the Perspective of the Spatial Moderating Effect of Environmental Regulation

This paper uses panel data from 284 Chinese cities from 2004 to 2020 and employs a dynamic spatial panel Durbin model to re-examine the relationship between industrial agglomeration, environmental regulation, and haze pollution. It further adopts a dynamic spatial moderation effect model to explore the spatial regulatory mechanism of environmental regulation. The results show that both local and neighboring industrial agglomeration have a significant “inverted U-shaped” relationship with local haze pollution, and the scale cumulative optimization effect can only be effectively played after the industrial agglomeration level of the locality and neighboring areas exceeds the inflection point. Local environmental regulation significantly inhibits haze pollution, while neighboring environmental regulation plays a promoting role. The moderating effect of environmental regulation on the relationship between industrial agglomeration and haze pollution shows spatial heterogeneity in the local and neighboring areas. Local environmental regulation has a “U-shaped” non-linear moderating effect while neighboring environmental regulation has a positive linear moderating effect. Therefore, the government should pay attention to the joint effort and coordinated advancement of industrial agglomeration and environmental regulation to further reduce urban haze pollution and enhance urban air quality.